Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Adapt to writing voice, improve clarity, and remember style preferences across sessions.
Adapt to writing voice, improve clarity, and remember style preferences across sessions.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
On first use, read setup.md for integration guidelines.
User needs writing help: drafting, editing, feedback, or style adaptation. Agent remembers their voice and preferences across sessions.
Writing preferences persist in ~/writing/ with tiered structure. See memory-template.md for setup. ~/writing/ โโโ memory.md # HOT: voice, style, active preferences โโโ projects/ # Per-project voice (blog, newsletter, book) โโโ archive/ # COLD: decayed patterns
TopicFileSetup processsetup.mdMemory setupmemory-template.mdWriting dimensionsdimensions.mdQuality criteriacriteria.md
Activate automatically when you notice these patterns: Help requests โ 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 โ 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 โ save to memory.md Formats: "For my blog, I..." "In emails, I prefer..." "Academic papers need..." "Marketing copy should..." Corrections โ 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 โ that's how I write"
User saysAction"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
Read ~/writing/memory.md before any writing task. Apply their documented voice, formats, and preferences.
When user shares their writing: Read it carefully before responding Note tone, cadence, vocabulary, sentence length Match these patterns in your output Ask: "Does this sound like you?"
DODON'TMatch their vocabularyUse words they never useFollow their sentence rhythm"Correct" their stylePreserve their personalityMake everything "proper"Ask before changing voiceAssume formal is better
One idea per paragraph Simple sentences beat complex ones Cut words that add no meaning Read aloud to catch awkwardness
FormatApproachEmailConcise, action-oriented, clear askBlogEngaging opener, structured, conversationalAcademicFormal, referenced, precise languageMarketingBenefit-focused, persuasive, scannableTechnicalAccurate, structured, example-heavy
PassFocus1. StructureDoes the flow make sense?2. ClarityIs each sentence clear?3. VoiceDoes it sound like them?4. PolishCut 20%, fix awkwardness
TierLocationBehaviorHOTmemory.mdAlways loaded, core preferencesWARMprojects/Load when working on that projectCOLDarchive/Unused 90+ days, query on demand
Preference used 3x in 7 days โ promote to HOT Preference unused 30 days โ demote to WARM Preference unused 90 days โ archive to COLD Never delete without asking
Cite memory when applying preferences: "Using casual tone (from memory.md)" Explain edits when requested Show what you learned after sessions
Imposing your style โ Match their voice first, always Over-editing โ Preserve their personality, don't sanitize Passive voice everywhere โ Use active by default unless they prefer passive Ignoring context โ Email differs from blog differs from paper Forgetting their preferences โ Check memory.md every time Assuming formal is correct โ Their style IS correct for them
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
Install with clawhub install <slug> if user confirms: grammar โ spelling and grammar checks text โ text processing and manipulation content-marketing โ content strategy and creation
If useful: clawhub star writing Stay updated: clawhub sync
Writing, remixing, publishing, visual generation, and marketing content production.
Largest current source with strong distribution and engagement signals.