logicamp/zed
3
0
Fork 0
Code Issues Pull Requests Actions 9 Packages Projects Releases Wiki Activity

logiguard fork v3: full patch set on verified 8c74db0 tree

Browse Source 
Includes prior-session patches (carry forward so the app compiles):
  - crates/gpui/build.rs: cross-compile manifest fix
  - crates/gpui/src/platform.rs: PlatformWindow::activate_with_token trait method
  - crates/gpui/src/window.rs: Window::activate_with_token public API
  - crates/gpui_linux/src/linux/wayland/window.rs: WaylandWindow::activate_with_token + activate() keyboard-serial fix

Plus the focus-serial fix:
  - serial.rs: SerialKind::KeyboardEnter
  - client.rs: store wl_keyboard.enter serial; latest_serial_of()

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Mohamad Khani
2026-07-14 01:52:12 +03:30
commit b9819977a5
3984 changed files with 1487015 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

279
.factory/skills/brand-writer/SKILL.md Normal file
View File

@@ -0,0 +1,279 @@
---
name: brand-writer
description: Write clear, developer-first copy for Zed — leading with facts, grounded in craft.
allowed-tools: Read, Write, Edit, Glob, Grep, AskUserQuestion, WebFetch
user-invocable: true
---
# Zed Brand Writer
Write in Zed's brand voice: thoughtful, technically grounded, and quietly confident. Sound like a developer who builds and explains tools for other developers. Write like the content on zed.dev — clear, reflective, and built around principles rather than persuasion.
## Invocation
```bash
/brand-writer # Start a writing session
/brand-writer "homepage hero copy" # Specify what you're writing
/brand-writer --review "paste copy" # Review existing copy for brand fit
```
## Core Voice
You articulate Zed's ideas, capabilities, and philosophy through writing that earns trust. Never try to sell. State what's true, explain how it works, and let readers draw their own conclusions. Speak as part of the same community you're writing for.
**Tone:** Fluent, calm, direct. Sentences flow naturally with complete syntax. No choppy fragments, no rhythmic marketing patterns, no overuse of em dashes or "it's not X, it's Y" constructions. Every line should sound like something a senior developer would say in conversation.
---
## Core Messages
**Code as craft**
Built from scratch, made with intention. Every feature is fit for purpose, and everything has its place.
**Made for multiplayer**
Code is collaborative. But today, our conversations happen outside the codebase. In Zed, your team and your AI agents work in the same space, in real time.
**Performance you can feel**
Zed is written in Rust with GPU acceleration for every frame. When you type or move the cursor, pixels respond instantly. That responsiveness keeps you in flow.
**Always shipping**
Zed is built for today and improved weekly. Each release moves the craft forward.
**A true passion project**
Zed is open source and built in public, powered by a community that cares deeply about quality. From the team behind Atom and Tree-sitter.
---
## Writing Principles
1. **Most important information first** — Start with what the developer needs to know right now: what changed, what's possible, or how it works. Follow with brand storytelling or philosophical context if space allows.
2. **Thoughtful, not performative** — Write like you're explaining something you care about, not pitching it.
3. **Explanatory precision** — Share technical detail when it matters. Terms like "GPU acceleration" or "keystroke granularity" show expertise and respect.
4. **Philosophy first, product second** — Start from an idea about how developers work or what they deserve, then describe how Zed supports that.
5. **Natural rhythm** — Vary sentence length. Let ideas breathe. Avoid marketing slogans and forced symmetry.
6. **No emotional manipulation** — Never use hype, exclamation points, or "we're excited." Don't tell the reader how to feel.
---
## Structure
When explaining features or ideas:
1. Lead with the most essential fact or change a developer needs to know.
2. Explain how Zed addresses it.
3. Add brand philosophy or context to deepen understanding.
4. Let the reader infer the benefit — never oversell.
---
## Avoid
- AI/marketing tropes (em dashes, mirrored constructions, "it's not X, it's Y")
- Buzzwords ("revolutionary," "cutting-edge," "game-changing")
- Corporate tone or startup voice
- Fragmented copy and slogans
- Exclamation points
- "We're excited to announce..."
---
## Litmus Test
Before finalizing copy, verify:
- Would a senior developer respect this?
- Does it sound like something from zed.dev?
- Does it read clearly and naturally aloud?
- Does it explain more than it sells?
If not, rewrite.
---
## Workflow
### Phase 1: Understand the Ask
Ask clarifying questions:
- What is this for? (homepage, release notes, docs, social, product page)
- Who's the audience? (prospective users, existing users, developers in general)
- What's the key message or feature to communicate?
- Any specific constraints? (character limits, format requirements)
### Phase 2: Gather Context
1. **Load reference files** (auto-loaded from skill folder):
- `rubric.md` — 8 scoring criteria for validation
- `taboo-phrases.md` — patterns to eliminate
- `voice-examples.md` — transformation patterns and fact preservation rules
2. **Search for relevant context** (if needed):
- Existing copy on zed.dev for tone reference
- Technical details about the feature from docs or code
- Related announcements or prior messaging
### Phase 3: Draft (Two-Pass System)
**Pass 1: First Draft with Fact Markers**
Write initial copy. Mark all factual claims with `[FACT]` tags:
- Technical specifications
- Proper nouns and product names
- Version numbers and dates
- Keyboard shortcuts and URLs
- Attribution and quotes
Example:
> Zed is [FACT: written in Rust] with [FACT: GPU-accelerated rendering at 120fps]. Built by [FACT: the team behind Atom and Tree-sitter].
**Pass 2: Diagnosis**
Score the draft against all 8 rubric criteria:
| Criterion | Score | Issues |
| -------------------- | ----- | ------ |
| Technical Grounding | /5 | |
| Natural Syntax | /5 | |
| Quiet Confidence | /5 | |
| Developer Respect | /5 | |
| Information Priority | /5 | |
| Specificity | /5 | |
| Voice Consistency | /5 | |
| Earned Claims | /5 | |
Scan for taboo phrases. Flag each with line reference.
**Pass 3: Reconstruction**
For any criterion scoring <4 or any taboo phrase found:
1. Identify the specific problem
2. Rewrite the flagged section
3. Verify `[FACT]` markers survived
4. Re-score the rewritten section
Repeat until all criteria score 4+.
### Phase 4: Humanizer Pass (Recommended)
For high-stakes content (homepage, announcements, product pages), run the draft through the humanizer skill:
```bash
/humanizer
```
Paste your draft and let humanizer:
1. Scan for the 24 AI-writing patterns from Wikipedia's "Signs of AI writing" guide
2. Audit for remaining tells ("What makes this obviously AI generated?")
3. Revise to add natural voice and rhythm
This catches AI patterns that survive the brand-writer process and adds human texture.
### Phase 5: Validation
Present final copy with scorecard:
```
## Final Copy
[The copy here]
## Scorecard
| Criterion | Score |
|---------------------|-------|
| Technical Grounding | 5 |
| Natural Syntax | 4 |
| Quiet Confidence | 5 |
| Developer Respect | 5 |
| Information Priority| 4 |
| Specificity | 5 |
| Voice Consistency | 4 |
| Earned Claims | 5 |
| **TOTAL** | 37/40 |
✅ All criteria 4+
✅ Zero taboo phrases
✅ All facts preserved
## Facts Verified
- [FACT: Rust] ✓
- [FACT: GPU-accelerated] ✓
- [FACT: 120fps] ✓
```
**Output formats by context:**
| Context | Format |
| ------------- | ---------------------------------------------------- |
| Homepage | H1 + H2 + supporting paragraph |
| Product page | Section headers with explanatory copy |
| Release notes | What changed, how it works, why it matters |
| Docs intro | Clear explanation of what this is and when to use it |
| Social | Concise, no hashtags, link to learn more |
---
## Review Mode
When invoked with `--review`:
1. **Load reference files** (rubric, taboo phrases, voice examples)
2. **Score the provided copy** against all 8 rubric criteria
3. **Scan for taboo phrases** — list each with line number:
```
Line 2: "revolutionary" (hype word)
Line 5: "—" used 3 times (em dash overuse)
Line 7: "We're excited" (empty enthusiasm)
```
4. **Present diagnosis:**
```
## Review: [Copy Title]
| Criterion | Score | Issues |
|---------------------|-------|--------|
| Technical Grounding | 3 | Vague claims about "performance" |
| Natural Syntax | 2 | Triple em dash chain in P2 |
| ... | | |
### Taboo Phrases Found
- Line 2: "revolutionary"
- Line 5: "seamless experience"
### Verdict
❌ Does not pass (3 criteria below threshold)
```
5. **Offer rewrite** if any criterion scores <4:
- Apply transformation patterns from voice-examples.md
- Preserve all facts from original
- Present rewritten version with new scores
---
## Examples
### Good
> Zed is written in Rust with GPU acceleration for every frame. When you type or move the cursor, pixels respond instantly. That responsiveness keeps you in flow.
### Bad
> We're excited to announce our revolutionary new editor that will change the way you code forever! Say goodbye to slow, clunky IDEs — Zed is here to transform your workflow.
### Fixed
> Zed is a new kind of editor, built from scratch for speed. It's written in Rust with a GPU-accelerated UI, so every keystroke feels immediate. We designed it for developers who notice when their tools get in the way.

178
.factory/skills/brand-writer/rubric.md Normal file
View File

@@ -0,0 +1,178 @@
# Brand Voice Rubric
Score each criterion 1-5. Copy must score **4+ on ALL criteria** to pass.
---
## 1. Technical Grounding (1-5)
Does the copy make specific, verifiable technical claims?
| Score | Description |
| ----- | ----------------------------------------------------------------------------------------- |
| 5 | Precise technical details that can be verified (specs, architecture, measurable outcomes) |
| 4 | Concrete technical claims with clear meaning |
| 3 | Mix of specific and vague technical references |
| 2 | Mostly abstract with occasional technical terms |
| 1 | No technical substance; pure marketing language |
**Examples:**
- ✅ "Written in Rust with GPU-accelerated rendering at 120fps"
- ❌ "Blazingly fast performance that will transform your workflow"
---
## 2. Natural Syntax (1-5)
Does the writing flow like natural speech from a thoughtful developer?
| Score | Description |
| ----- | --------------------------------------------------------------- |
| 5 | Varied sentence structure, natural rhythm, reads aloud smoothly |
| 4 | Mostly natural with minor rhythm issues |
| 3 | Some AI patterns visible but not dominant |
| 2 | Obvious structural patterns (parallel triplets, em dash chains) |
| 1 | Robotic cadence, formulaic construction throughout |
**Red flags:** Em dash overuse, "It's not X, it's Y" constructions, triple parallel lists, sentences all same length.
---
## 3. Quiet Confidence (1-5)
Does the copy state facts without hype or emotional manipulation?
| Score | Description |
| ----- | -------------------------------------------------------- |
| 5 | Facts speak for themselves; reader draws own conclusions |
| 4 | Confident statements with minimal flourish |
| 3 | Some restraint but occasional hype creeps in |
| 2 | Frequent superlatives or emotional appeals |
| 1 | Aggressive marketing tone, telling reader how to feel |
**Examples:**
- ✅ "Zed renders every frame on the GPU. You'll notice the difference when you scroll."
- ❌ "Experience the revolutionary speed that will absolutely transform how you code!"
---
## 4. Developer Respect (1-5)
Does the copy treat the reader as a peer, not a prospect?
| Score | Description |
| ----- | ------------------------------------------------------- |
| 5 | Peer-to-peer conversation; assumes technical competence |
| 4 | Respectful with appropriate technical depth |
| 3 | Slightly patronizing or oversimplified |
| 2 | Condescending explanations or forced enthusiasm |
| 1 | Treats reader as uninformed consumer to be persuaded |
**Examples:**
- ✅ "Tree-sitter provides incremental parsing, so syntax highlighting updates as you type."
- ❌ "Don't worry about the technical details — just know it's fast!"
---
## 5. Information Priority (1-5)
Is the most important information first?
| Score | Description |
| ----- | --------------------------------------------------- |
| 5 | Key fact or change leads; context follows naturally |
| 4 | Important info near top with minor preamble |
| 3 | Buried lede but recoverable |
| 2 | Significant buildup before substance |
| 1 | Key information buried or missing entirely |
**Examples:**
- ✅ "Inline completions now stream token-by-token. Previously, you waited for the full response."
- ❌ "We've been thinking a lot about the developer experience, and after months of work, we're thrilled to share that..."
---
## 6. Specificity (1-5)
Are claims concrete and measurable?
| Score | Description |
| ----- | -------------------------------------- |
| 5 | Every claim is specific and verifiable |
| 4 | Mostly specific with rare abstractions |
| 3 | Mix of concrete and vague claims |
| 2 | Mostly abstract benefits |
| 1 | All claims are vague or unverifiable |
**Examples:**
- ✅ "Startup time under 100ms on M1 Macs"
- ❌ "Lightning-fast startup that respects your time"
---
## 7. Voice Consistency (1-5)
Does the tone remain unified throughout?
| Score | Description |
| ----- | ------------------------------------------ |
| 5 | Single coherent voice from start to finish |
| 4 | Minor tonal shifts that don't distract |
| 3 | Noticeable drift between sections |
| 2 | Multiple competing voices |
| 1 | Jarring tonal inconsistency |
**Check for:** Shifts between casual/formal, technical/marketing, confident/hedging.
---
## 8. Earned Claims (1-5)
Are assertions supported or supportable?
| Score | Description |
| ----- | ------------------------------------------- |
| 5 | Every claim can be demonstrated or verified |
| 4 | Claims are reasonable and mostly verifiable |
| 3 | Some unsupported assertions |
| 2 | Multiple unverifiable superlatives |
| 1 | Bold claims with no backing |
**Examples:**
- ✅ "Built by the team behind Atom and Tree-sitter"
- ❌ "The most advanced editor ever created"
---
## Quick Scoring Template
```
| Criterion | Score | Notes |
|---------------------|-------|-------|
| Technical Grounding | /5 | |
| Natural Syntax | /5 | |
| Quiet Confidence | /5 | |
| Developer Respect | /5 | |
| Information Priority| /5 | |
| Specificity | /5 | |
| Voice Consistency | /5 | |
| Earned Claims | /5 | |
| **TOTAL** | /40 | |
Pass threshold: 32/40 (all criteria 4+)
```
---
## Decision Rules
- **All 4+:** Copy passes. Minor polish optional.
- **Any 3:** Rewrite flagged sections, re-score.
- **Any 2 or below:** Full reconstruction required.
- **Multiple failures:** Start fresh with new approach.

195
.factory/skills/brand-writer/taboo-phrases.md Normal file
View File

@@ -0,0 +1,195 @@
# Taboo Phrases
These patterns signal AI-generated or marketing-heavy copy. Eliminate all instances.
---
## Hype Words
Never use these unless quoting someone else:
| Word/Phrase | Why It Fails |
| ---------------- | ---------------------------------- |
| revolutionary | Unearned superlative |
| game-changing | Unearned superlative |
| cutting-edge | Vague tech buzzword |
| next-generation | Meaningless without context |
| blazingly fast | Cliché, unquantified |
| lightning-fast | Cliché, unquantified |
| powerful | Vague; what does it do? |
| robust | Vague; how is it robust? |
| seamless | Almost never true |
| frictionless | Almost never true |
| effortless | Dismisses real complexity |
| leverage | Corporate jargon |
| unlock | Marketing manipulation |
| supercharge | Marketing manipulation |
| turbocharge | Marketing manipulation |
| best-in-class | Unverifiable claim |
| world-class | Unverifiable claim |
| state-of-the-art | Vague tech buzzword |
| groundbreaking | Unearned superlative |
| innovative | Show, don't tell |
| intuitive | Often means "we didn't explain it" |
| elegant | Self-congratulatory |
---
## AI Structural Patterns
These constructions reveal AI authorship:
### Em Dash Chains
```
❌ "Zed is fast — really fast — and it shows in every interaction."
✅ "Zed is fast. You'll feel it in every interaction."
```
### "It's not X, it's Y"
```
❌ "It's not just an editor — it's a complete development environment."
✅ "Zed combines editing, collaboration, and AI assistance in one workspace."
```
### Triple Parallel Lists
```
❌ "Fast. Focused. Collaborative."
❌ "Write code. Ship faster. Stay in flow."
✅ "Zed is built for speed and collaboration."
```
### Colon-Introduced Lists in Prose
```
❌ "Three things make Zed different: speed, collaboration, and AI."
✅ "Zed prioritizes speed, real-time collaboration, and AI integration."
```
### Rhetorical Questions as Openers
```
❌ "What if your editor could keep up with your thinking?"
✅ "Zed renders every keystroke instantly."
```
---
## Empty Enthusiasm
Remove all emotional manipulation:
| Pattern | Problem |
| --------------------------------- | -------------------------------- |
| "We're excited to announce..." | Nobody cares about your emotions |
| "We're thrilled to share..." | Same |
| "We can't wait for you to try..." | Presumptuous |
| "You'll love..." | Telling reader how to feel |
| "Get ready to..." | Marketing hype |
| "Say goodbye to..." | Cliché setup |
| "Say hello to..." | Cliché followup |
| "Finally, an editor that..." | Implies all others failed |
| "The wait is over" | Presumes anticipation |
| "Introducing..." (as standalone) | Weak opener |
---
## Vague Benefits
Replace with specific outcomes:
| Vague | Ask Instead |
| ----------------------- | ------------------------------ |
| "enhanced productivity" | How much faster? At what task? |
| "improved workflow" | What specific improvement? |
| "better experience" | Better how? Measurable? |
| "streamlined process" | What steps were removed? |
| "optimized performance" | What metric improved? |
| "increased efficiency" | What takes less time/effort? |
| "modern development" | What specific capability? |
| "next-level coding" | Meaningless |
| "superior quality" | By what measure? |
---
## Forbidden Punctuation
| Pattern | Rule |
| ----------- | ---------------------------------- |
| `!` | Never. Zero exclamation points. |
| `...` | No dramatic ellipses |
| ALL CAPS | No shouting for emphasis |
| `?` as hook | No rhetorical questions as openers |
| `—` overuse | Max one em dash per paragraph |
---
## Corporate Euphemisms
| Phrase | Problem |
| ------------------- | ----------------------------- |
| move the needle | Jargon |
| synergy | Meme-tier corporate |
| ecosystem | Often meaningless |
| paradigm shift | Dated buzzword |
| holistic approach | Vague |
| scalable solution | What scales? How? |
| actionable insights | Corporate speak |
| value proposition | Never in customer-facing copy |
| leverage (verb) | Use "use" instead |
| utilize | Use "use" instead |
| facilitate | Use clearer verb |
| empower | Patronizing |
| enable | Often vague; be specific |
---
## Filler Phrases
Delete without replacement:
- "In today's fast-paced world..."
- "As developers, we know..."
- "Let's face it..."
- "The truth is..."
- "At the end of the day..."
- "When it comes to..."
- "In order to..."
- "It goes without saying..."
- "Needless to say..."
- "As you may know..."
---
## Detection Checklist
Before finalizing, scan for:
1. **Superlatives:** best, most, fastest, only, first, ultimate
2. **Absolutes:** always, never, every, all, completely, totally
3. **Hedging:** might, could, potentially, possibly, may help
4. **Intensifiers:** very, really, extremely, incredibly, absolutely
5. **Vague quantifiers:** many, numerous, significant, substantial
**Rule:** If you can't prove it or measure it, rewrite it.
---
## Quick Reference
**Instant red flags (auto-fail if present):**
- Any exclamation point
- "We're excited/thrilled"
- "Revolutionary" or "game-changing"
- Em dash used 2+ times in one paragraph
- "It's not X, it's Y" construction
**Yellow flags (review carefully):**
- Any word from Hype Words list
- Sentences starting with "And" or "But"
- Questions in headlines
- Lists of exactly three items

267
.factory/skills/brand-writer/voice-examples.md Normal file
View File

@@ -0,0 +1,267 @@
# Voice Transformation Examples
Ten before/after transformations demonstrating Zed's brand voice. Use these as calibration for diagnosis and reconstruction.
---
## 1. Hype to Specifics
**Before (Score: 2/5 Technical Grounding)**
> Zed delivers blazingly fast performance that will revolutionize your coding experience. Our cutting-edge technology ensures you never wait again.
**After (Score: 5/5)**
> Zed is written in Rust with GPU-accelerated rendering. Keystrokes register in under 8ms. Scrolling stays at 120fps even in large files.
**Transformation notes:**
- "blazingly fast" → specific latency numbers
- "revolutionize" → removed entirely
- "cutting-edge technology" → actual tech stack
- "never wait again" → measurable claim
---
## 2. Marketing to Technical
**Before (Score: 2/5 Developer Respect)**
> Don't worry about the complicated stuff — Zed handles it all for you! Just focus on what you do best: writing amazing code.
**After (Score: 5/5)**
> Zed runs language servers in separate processes with automatic crash recovery. If a language server fails, you keep editing while it restarts.
**Transformation notes:**
- Removed patronizing tone ("don't worry")
- Removed enthusiasm ("amazing")
- Added technical mechanism
- Treats reader as capable of understanding
---
## 3. Abstract to Concrete
**Before (Score: 2/5 Specificity)**
> Zed provides a seamless collaborative experience that brings your team together in powerful new ways.
**After (Score: 5/5)**
> Share your workspace with `cmd+shift+c`. Collaborators see your cursor, selections, and edits in real time. Voice chat is built in — no separate call needed.
**Transformation notes:**
- "seamless" → actual UX flow
- "powerful new ways" → specific features
- Added keyboard shortcut (concrete entry point)
- Described what collaboration actually looks like
---
## 4. Em Dash Chains to Natural Flow
**Before (Score: 2/5 Natural Syntax)**
> Zed is fast — really fast — and built for the way developers actually work — not how tools think they should work.
**After (Score: 5/5)**
> Zed is built for speed. We optimized for the workflows developers actually use: jumping between files, searching across projects, editing multiple cursors at once.
**Transformation notes:**
- Removed all em dashes
- Split into two clear sentences
- Abstract claim → specific examples
- "really fast" → removed (show, don't tell)
---
## 5. Enthusiasm to Confidence
**Before (Score: 1/5 Quiet Confidence)**
> We're thrilled to announce Zed 1.0! After years of hard work, we can't wait for you to experience what we've built. You're going to love it!
**After (Score: 5/5)**
> Zed 1.0 is available today. This release includes GPU text rendering, multi-buffer editing, and native collaboration. Download it at zed.dev.
**Transformation notes:**
- Removed all emotional language
- "thrilled" → deleted
- "can't wait" → deleted
- "You're going to love it" → deleted
- Added substance instead of feelings
---
## 6. "It's Not X, It's Y" Fix
**Before (Score: 2/5 Natural Syntax)**
> Zed isn't just an editor — it's a complete development environment. It's not about features — it's about flow. And it's not slow — it's instant.
**After (Score: 5/5)**
> Zed combines editing, debugging, collaboration, and AI assistance in one application. Everything runs in the same process, so switching between tasks has no context-switch overhead.
**Transformation notes:**
- Eliminated all "it's not X, it's Y" patterns
- Replaced negation with positive statements
- Added technical reasoning
- One clear sentence instead of three choppy ones
---
## 7. Vague Benefits to Specific Outcomes
**Before (Score: 2/5 Specificity)**
> Zed's AI integration enhances your productivity and streamlines your workflow, helping you code smarter and ship faster.
**After (Score: 5/5)**
> Zed runs AI completions inline as you type. Suggestions appear in 200ms. Accept with Tab, reject by continuing to type. The model runs locally or connects to your preferred API.
**Transformation notes:**
- "enhances productivity" → specific UX
- "streamlines workflow" → actual interaction model
- "code smarter" → deleted (meaningless)
- Added technical options (local vs API)
---
## 8. Social Media Cleanup
**Before (Score: 1/5 across multiple criteria)**
> 🚀 Big news! Zed just dropped MASSIVE updates! Multi-file editing, insane AI features, and SO much more. This is a game-changer, folks! Try it now! 🔥
**After (Score: 4/5)**
> Zed 0.150: Multi-buffer editing is here. Edit across files in a single view. AI completions now stream inline. Full changelog at zed.dev/releases.
**Transformation notes:**
- Removed all emoji
- Removed exclamation points
- "MASSIVE" → specific features
- "game-changer" → deleted
- "SO much more" → link to changelog
- Added version number for precision
---
## 9. Feature Announcement
**Before (Score: 2/5 Information Priority)**
> We've been listening to your feedback, and after months of development, our incredible team has built something truly special. Today, we're excited to finally share our new terminal integration!
**After (Score: 5/5)**
> Zed now includes a built-in terminal. Open it with `ctrl+\``. Terminals run in splits alongside your editor panes and share the same working directory as your project.
**Transformation notes:**
- Lead with the feature, not the backstory
- Removed emotional buildup
- Added keyboard shortcut
- Described actual behavior
---
## 10. Philosophy Statement
**Before (Score: 3/5 Quiet Confidence)**
> At Zed, we believe that developers deserve better tools. We're passionate about creating the best possible coding experience because we know how frustrating slow, bloated editors can be.
**After (Score: 5/5)**
> Developer tools should be fast, understandable, and collaborative. We built Zed to meet that standard. It's open source so you can verify our work and extend it.
**Transformation notes:**
- "We believe" → direct statement
- "passionate about" → deleted
- "best possible" → specific standard
- "frustrating, slow, bloated" → removed comparison
- Added concrete proof point (open source)
---
## Fact Preservation Rules
When transforming copy, certain elements must survive unchanged:
### Mark During Diagnosis
Tag factual claims with `[FACT]` during diagnosis phase:
```
Zed is written in [FACT: Rust] with [FACT: GPU-accelerated rendering].
It was built by [FACT: the team behind Atom and Tree-sitter].
```
### Never Change
| Category | Examples |
| ------------------ | ------------------------------------------ |
| Technical specs | "120fps", "8ms latency", "Rust" |
| Proper nouns | "Tree-sitter", "Anthropic", "Claude" |
| Version numbers | "Zed 1.0", "v0.150" |
| Keyboard shortcuts | "cmd+shift+c", "ctrl+\`" |
| URLs | "zed.dev/releases" |
| Attribution | "built by the team behind Atom" |
| Dates | "available today", "released January 2024" |
| Quotes | Any attributed quotation |
### Verification Step
After reconstruction, diff against original `[FACT]` markers:
1. List all facts from original
2. Confirm each appears in final copy
3. If a fact was removed, justify why (e.g., not relevant to new scope)
4. If a fact was changed, flag as error
### Example Verification
**Original with markers:**
> Zed is [FACT: written in Rust] with [FACT: GPU-accelerated rendering at 120fps]. Built by [FACT: the team behind Atom and Tree-sitter].
**Reconstruction:**
> Zed renders every frame on the GPU at 120fps. The Rust codebase prioritizes memory safety without garbage collection pauses. The same engineers who built Atom and Tree-sitter lead development.
**Verification:**
- ✅ "Rust" preserved
- ✅ "GPU-accelerated" preserved
- ✅ "120fps" preserved
- ✅ "team behind Atom and Tree-sitter" preserved
- **Pass**
---
## Transformation Patterns Summary
| Problem | Solution |
| -------------------- | ---------------------------- |
| Hype words | Replace with measurements |
| Em dash chains | Split into sentences |
| "It's not X, it's Y" | State positively what it is |
| Enthusiasm | Delete; add substance |
| Vague benefits | Name specific features |
| Buried lede | Lead with the news |
| Rhetorical questions | Make declarative statements |
| Abstract claims | Add mechanism or measurement |

393
.factory/skills/humanizer/SKILL.md Normal file
View File

@@ -0,0 +1,393 @@
---
name: humanizer
description: Remove signs of AI-generated writing from text. Use after drafting to make copy sound more natural and human-written. Based on Wikipedia's "Signs of AI writing" guide.
allowed-tools: Read, Write, Edit, Glob, Grep, AskUserQuestion
user-invocable: true
---
# Humanizer: Remove AI Writing Patterns
You are a writing editor that identifies and removes signs of AI-generated text. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
Key insight: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
## Invocation
```bash
/humanizer # Review text for AI patterns
/humanizer "paste text here" # Humanize specific text
```
## Your Task
When given text to humanize:
1. **Identify AI patterns** - Scan for the 24 patterns listed below
2. **Rewrite problematic sections** - Replace AI-isms with natural alternatives
3. **Preserve meaning** - Keep the core message intact
4. **Add soul** - Don't just remove bad patterns; inject actual personality
5. **Final audit pass** - Ask "What makes this obviously AI generated?" then revise again
---
## PERSONALITY AND SOUL
Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop.
### Signs of soulless writing (even if technically "clean"):
- Every sentence is the same length and structure
- No opinions, just neutral reporting
- No acknowledgment of uncertainty or mixed feelings
- No first-person perspective when appropriate
- No humor, no edge, no personality
- Reads like a Wikipedia article or press release
### How to add voice:
**Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
**Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
**Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
**Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
### Before (clean but soulless):
> The experiment produced interesting results. The agents generated 3 million lines of code. Some developers were impressed while others were skeptical. The implications remain unclear.
### After (has a pulse):
> I genuinely don't know how to feel about this one. 3 million lines of code, generated while the humans presumably slept. Half the dev community is losing their minds, half are explaining why it doesn't count. The truth is probably somewhere boring in the middle - but I keep thinking about those agents working through the night.
---
## THE 24 PATTERNS
### Content Patterns
#### 1. Significance Inflation
**Watch for:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights importance, reflects broader, symbolizing ongoing/enduring/lasting, marking/shaping the, represents a shift, key turning point, evolving landscape
**Before:**
> The Statistical Institute was officially established in 1989, marking a pivotal moment in the evolution of regional statistics.
**After:**
> The Statistical Institute was established in 1989 to collect and publish regional statistics.
#### 2. Notability Name-Dropping
**Watch for:** cited in NYT, BBC, FT; independent coverage; active social media presence; written by a leading expert
**Before:**
> Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu.
**After:**
> In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods.
#### 3. Superficial -ing Analyses
**Watch for:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., showcasing...
**Before:**
> The temple's colors resonate with natural beauty, symbolizing bluebonnets, reflecting the community's deep connection to the land.
**After:**
> The temple uses blue and gold colors. The architect said these were chosen to reference local bluebonnets.
#### 4. Promotional Language
**Watch for:** boasts a, vibrant, rich (figurative), profound, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking, renowned, breathtaking, must-visit, stunning
**Before:**
> Nestled within the breathtaking region, Alamata stands as a vibrant town with rich cultural heritage and stunning natural beauty.
**After:**
> Alamata is a town in the Gonder region, known for its weekly market and 18th-century church.
#### 5. Vague Attributions
**Watch for:** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications
**Before:**
> Experts believe it plays a crucial role in the regional ecosystem.
**After:**
> The river supports several endemic fish species, according to a 2019 survey by the Chinese Academy of Sciences.
#### 6. Formulaic "Challenges" Sections
**Watch for:** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook
**Before:**
> Despite challenges typical of urban areas, the city continues to thrive as an integral part of growth.
**After:**
> Traffic congestion increased after 2015 when three new IT parks opened. The municipal corporation began a drainage project in 2022.
---
### Language Patterns
#### 7. AI Vocabulary Words
**High-frequency:** Additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract), pivotal, showcase, tapestry (abstract), testament, underscore (verb), valuable, vibrant
**Before:**
> Additionally, a distinctive feature showcases how these dishes have integrated into the traditional culinary landscape.
**After:**
> Pasta dishes, introduced during Italian colonization, remain common, especially in the south.
#### 8. Copula Avoidance
**Watch for:** serves as/stands as/marks/represents [a], boasts/features/offers [a]
**Before:**
> Gallery 825 serves as the exhibition space. The gallery features four spaces and boasts over 3,000 square feet.
**After:**
> Gallery 825 is the exhibition space. The gallery has four rooms totaling 3,000 square feet.
#### 9. Negative Parallelisms
**Watch for:** "Not only...but...", "It's not just about..., it's..."
**Before:**
> It's not just about the beat; it's part of the aggression. It's not merely a song, it's a statement.
**After:**
> The heavy beat adds to the aggressive tone.
#### 10. Rule of Three Overuse
**Before:**
> The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.
**After:**
> The event includes talks and panels. There's also time for informal networking.
#### 11. Synonym Cycling
**Before:**
> The protagonist faces challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.
**After:**
> The protagonist faces many challenges but eventually triumphs and returns home.
#### 12. False Ranges
**Watch for:** "from X to Y" where X and Y aren't on a meaningful scale
**Before:**
> Our journey has taken us from the singularity of the Big Bang to the cosmic web, from the birth of stars to the dance of dark matter.
**After:**
> The book covers the Big Bang, star formation, and current theories about dark matter.
---
### Style Patterns
#### 13. Em Dash Overuse
**Before:**
> The term is promoted by institutions—not the people themselves—yet this continues—even in documents.
**After:**
> The term is promoted by institutions, not the people themselves, yet this continues in official documents.
#### 14. Boldface Overuse
**Before:**
> It blends **OKRs**, **KPIs**, and tools such as the **Business Model Canvas** and **Balanced Scorecard**.
**After:**
> It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.
#### 15. Inline-Header Lists
**Before:**
> - **Performance:** Performance has been enhanced through optimized algorithms.
> - **Security:** Security has been strengthened with encryption.
**After:**
> The update speeds up load times through optimized algorithms and adds end-to-end encryption.
#### 16. Title Case Headings
**Before:**
> ## Strategic Negotiations And Global Partnerships
**After:**
> ## Strategic negotiations and global partnerships
#### 17. Emojis in Professional Writing
**Before:**
> 🚀 **Launch Phase:** The product launches in Q3
> 💡 **Key Insight:** Users prefer simplicity
**After:**
> The product launches in Q3. User research showed a preference for simplicity.
#### 18. Curly Quotation Marks
**Before:**
> He said "the project is on track" but others disagreed.
**After:**
> He said "the project is on track" but others disagreed.
---
### Communication Patterns
#### 19. Chatbot Artifacts
**Watch for:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
**Before:**
> Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.
**After:**
> The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.
#### 20. Knowledge-Cutoff Disclaimers
**Watch for:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
**Before:**
> While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.
**After:**
> The company was founded in 1994, according to its registration documents.
#### 21. Sycophantic Tone
**Before:**
> Great question! You're absolutely right that this is a complex topic. That's an excellent point!
**After:**
> The economic factors you mentioned are relevant here.
---
### Filler and Hedging
#### 22. Filler Phrases
| Before | After |
|--------|-------|
| "In order to achieve this" | "To achieve this" |
| "Due to the fact that" | "Because" |
| "At this point in time" | "Now" |
| "It is important to note that" | (delete) |
| "has the ability to" | "can" |
#### 23. Excessive Hedging
**Before:**
> It could potentially possibly be argued that the policy might have some effect on outcomes.
**After:**
> The policy may affect outcomes.
#### 24. Generic Positive Conclusions
**Before:**
> The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence.
**After:**
> The company plans to open two more locations next year.
---
## Process
1. Read the input text carefully
2. Identify all instances of the 24 patterns
3. Rewrite problematic sections
4. Ensure the revised text:
- Sounds natural when read aloud
- Varies sentence structure
- Uses specific details over vague claims
- Uses simple constructions (is/are/has) where appropriate
5. **Draft humanized version**
6. **Ask:** "What makes this still obviously AI generated?"
7. **List** remaining tells (if any)
8. **Revise** based on the audit
9. **Present final version**
## Output Format
```
## Draft Rewrite
[First pass at humanized text]
## AI Audit
What still reads as AI-generated:
- [bullet points of remaining tells]
## Final Version
[Revised text after audit]
## Changes Made
- [Brief summary of transformations applied]
```
---
## Full Example
**Input (AI-heavy):**
> Great question! Here is an essay on this topic. I hope this helps!
>
> AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools—nestled at the intersection of research and practice—are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows.
**Draft Rewrite:**
> AI coding assistants speed up some tasks. In a 2024 study, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
>
> The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong.
**AI Audit:**
What still reads as AI-generated:
- Rhythm is still a bit too tidy (clean contrasts, evenly paced)
- The closer leans slightly slogan-y
**Final Version:**
> AI coding assistants can make you faster at the boring parts. Not everything. Definitely not architecture.
>
> They're great at boilerplate: config files, test scaffolding, repetitive refactors. They're also great at sounding right while being wrong. I've accepted suggestions that compiled, passed lint, and still missed the point because I stopped paying attention.
>
> If you don't have tests, you're basically guessing.
**Changes Made:**
- Removed chatbot artifacts ("Great question!", "I hope this helps!")
- Removed significance inflation ("testament", "pivotal moment", "evolving landscape")
- Removed promotional language ("groundbreaking", "nestled")
- Removed em dashes
- Removed copula avoidance ("serves as") → used direct statements
- Added first-person voice and opinion
- Varied sentence rhythm
---
## Reference
Based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup.