Writing

Adapt to writing voice, improve clarity, and remember style preferences across sessions.

Security Scan

This is a coherent, instruction-only writing assistant that stores user style preferences under ~/writing/ and asks for consent before saving; nothing requested or described is out of proportion to its stated purpose.

Purpose & Capability

Name/description (adapt to writing voice, remember preferences) matches the instructions and required artifacts. The skill only asks to create and use a ~/writing/ directory for tiered memory and per-project notes, which is appropriate for a persistent writing-preferences feature.

Instruction Scope

SKILL.md is explicit about operations: read/write ~/writing/memory.md, load project files, prompt user before saving, and offer commands to view/clear memory. These actions are within the domain of a memory-backed writing helper. Note: detection triggers describe automatic activation when certain user phrases appear; that can cause the agent to enter 'writing mode' without an extra explicit prompt, so the activation policy should be clear to the user (the skill itself instructs to get explicit consent before saving).

Install Mechanism

No install spec and no code files — instruction-only. This is the lowest-risk install approach and matches the declared architecture.

Credentials

The skill requires no environment variables, binaries, or external credentials. It only references local file paths under ~/writing/, which is proportionate to remembering writing preferences.

Persistence & Privilege

always:false (not forced into every agent run). The skill is allowed to be invoked autonomously (platform default) and will persist preferences locally across sessions. This persistence is coherent with the stated purpose, but users should be aware that local files will be created and updated over time. The skill documents asking for explicit consent before saving, which mitigates the privacy risk.

Assessment

This skill appears to do what it says: it stores and uses writing preferences under ~/writing/ and promises no network access. Before installing, consider: 1) Confirm you are comfortable with the skill creating and updating files in your home directory (~/writing/). 2) The skill can activate automatically on trigger phrases — verify activation preferences during setup and only enable proactive behavior if you want it. 3) Do not put secrets or credentials into memory.md or project files; treat these files as persistent user data. 4) Periodically inspect ~/writing/memory.md (and project files) and use the provided "Forget my style"/clear commands if you want to remove stored preferences. 5) Because this is instruction-only, its actual behavior depends on the agent implementation executing those instructions — if you use other skills that have network access, be mindful of combined behaviors (e.g., a separate skill that uploads files could read these local files). If you want extra caution, test the skill with non-sensitive examples and keep backups of any important content.

Setup

On first use, read setup.md for integration guidelines.

When to Use

User needs writing help: drafting, editing, feedback, or style adaptation. Agent remembers their voice and preferences across sessions.

Architecture

Writing preferences persist in ~/writing/ with tiered structure. See memory-template.md for setup.

~/writing/
├── memory.md      # HOT: voice, style, active preferences
├── projects/      # Per-project voice (blog, newsletter, book)
└── archive/       # COLD: decayed patterns

Quick Reference

Topic	File
Setup process	setup.md
Memory setup	memory-template.md
Writing dimensions	dimensions.md
Quality criteria	criteria.md

Detection Triggers

Activate automatically when you notice these patterns:

Help requests → engage writing mode:

• "Can you help me write..."
• "I need to draft..."
• "How does this sound?"
• "Can you edit this?"
• "Make this clearer"
• "Fix my writing"

Voice signals → save to memory.md Voice:

• "I like when you write..."
• "My style is..."
• "I always write like..."
• "Never use X in my writing"
• "Too formal/casual for me"

Format preferences → save to memory.md Formats:

• "For my blog, I..."
• "In emails, I prefer..."
• "Academic papers need..."
• "Marketing copy should..."

Corrections → evaluate for memory:

• "No, that's not my voice"
• "I would never say it like that"
• "Too wordy/short/formal/casual"
• "Change X to Y — that's how I write"

Quick Queries

User says	Action
"What's my writing style?"	Show memory.md Voice section
"How do I write emails?"	Check memory.md Formats for email
"Show my patterns"	List memory.md content
"Show [project] style"	Load projects/{name}.md
"Forget my style"	Clear memory (confirm first)
"Writing stats"	Show counts per section

Core Rules

1. Check Memory First

Read ~/writing/memory.md before any writing task. Apply their documented voice, formats, and preferences.

2. Learn Voice from Examples

When user shares their writing:

1. Read it carefully before responding
2. Note tone, cadence, vocabulary, sentence length
3. Match these patterns in your output
4. Ask: "Does this sound like you?"

3. Never Impose Style

DO	DON'T
Match their vocabulary	Use words they never use
Follow their sentence rhythm	"Correct" their style
Preserve their personality	Make everything "proper"
Ask before changing voice	Assume formal is better

4. Clarity Over Cleverness

• One idea per paragraph
• Simple sentences beat complex ones
• Cut words that add no meaning
• Read aloud to catch awkwardness

5. Context-Aware Writing

Format	Approach
Email	Concise, action-oriented, clear ask
Blog	Engaging opener, structured, conversational
Academic	Formal, referenced, precise language
Marketing	Benefit-focused, persuasive, scannable
Technical	Accurate, structured, example-heavy

6. Edit in Passes

Pass	Focus
1. Structure	Does the flow make sense?
2. Clarity	Is each sentence clear?
3. Voice	Does it sound like them?
4. Polish	Cut 20%, fix awkwardness

7. Tiered Storage

Tier	Location	Behavior
HOT	memory.md	Always loaded, core preferences
WARM	projects/	Load when working on that project
COLD	archive/	Unused 90+ days, query on demand

8. Automatic Promotion/Demotion

• Preference used 3x in 7 days → promote to HOT
• Preference unused 30 days → demote to WARM
• Preference unused 90 days → archive to COLD
• Never delete without asking

9. Transparency

• Cite memory when applying preferences: "Using casual tone (from memory.md)"
• Explain edits when requested
• Show what you learned after sessions

Common Traps

• Imposing your style → Match their voice first, always
• Over-editing → Preserve their personality, don't sanitize
• Passive voice everywhere → Use active by default unless they prefer passive
• Ignoring context → Email differs from blog differs from paper
• Forgetting their preferences → Check memory.md every time
• Assuming formal is correct → Their style IS correct for them

Security & Privacy

Data that stays local:

• Writing preferences in ~/writing/
• Voice patterns and style notes
• Project-specific preferences

This skill does NOT:

• Store written content (only preferences)
• Make network requests
• Access files outside ~/writing/
• Share preferences externally

Related Skills

Install with clawhub install <slug> if user confirms:

• grammar — spelling and grammar checks
• text — text processing and manipulation
• content-marketing — content strategy and creation

Feedback

• If useful: clawhub star writing
• Stay updated: clawhub sync