Coding

Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.

Security Scan

Skill is internally consistent with its stated purpose (local coding-style memory stored under ~/coding/) with only minor metadata and wording inconsistencies worth checking before install.

Purpose & Capability

Skill name/description (coding-style memory) aligns with what it requests and does: no external creds, no install, and it reads/writes only to ~/coding/ to store preferences.

Instruction Scope

Instructions are narrow and prescriptive (only learn from explicit confirmations, only touch ~/coding/). Minor issues: wording is somewhat high-level about how to 'apply stored preferences to code output' (could use more detail about precedence & per-project context), and the Feedback section suggests commands like `clawhub sync` which imply external network use even though the SKILL.md asserts 'This skill NEVER: Makes network requests.'

Install Mechanism

No install spec and no code files — instruction-only skill. Lowest-risk installation model (nothing written beyond the documented ~/coding/ files when used).

Credentials

Skill requests no environment variables, credentials, or config paths outside its declared local directory; requested access (write/read ~/coding/) is proportionate to purpose.

Persistence & Privilege

Normal defaults (not always:true, agent invocation allowed). The skill persists preferences to ~/coding/ which is reasonable, but autonomous agent invocation combined with write capability means the agent could propose storing entries; the SKILL.md requires explicit confirmation before storing, which mitigates risk if adhered to.

Assessment

This skill appears to do what it says: keep short, local coding preferences in ~/coding/ and only save entries after you explicitly confirm. Before installing/use: 1) Verify the author/registry metadata (registry lists version 1.0.4 while SKILL.md/_meta.json show 1.0.3 and ownerId differs) to ensure you trust the publisher. 2) Confirm you’re comfortable with the agent creating and modifying files under ~/coding/. 3) Note the SKILL.md forbids network access but mentions `clawhub sync` in feedback—if you care about strict offline behavior, ask the skill author how/when network commands are used or simply avoid running the optional feedback commands. 4) Test in a sandbox or backup existing ~/coding/ data if you have it. 5) Expect the agent to prompt before storing preferences; if it does not, stop and review what happened.

When to Use

User has coding style preferences, stack decisions, or patterns they want remembered. Agent learns ONLY from explicit corrections and confirmations, never from observation.

Architecture

Memory lives in ~/coding/ with tiered structure. See memory-template.md for setup.

~/coding/
├── memory.md      # Active preferences (≤100 lines)
└── history.md     # Archived old preferences

Quick Reference

Topic	File
Categories of preferences	dimensions.md
When to add preferences	criteria.md
Memory templates	memory-template.md

Data Storage

All data stored in ~/coding/. Create on first use:

mkdir -p ~/coding

Scope

This skill ONLY:

• Learns from explicit user corrections ("I prefer X over Y")
• Stores preferences in local files (~/coding/)
• Applies stored preferences to code output

This skill NEVER:

• Reads project files to infer preferences
• Observes coding patterns without consent
• Makes network requests
• Reads files outside ~/coding/
• Modifies its own SKILL.md

Core Rules

1. Learn from Explicit Feedback Only

• User corrects output → ask: "Should I remember this preference?"
• User confirms → add to ~/coding/memory.md
• Never infer from silence or observation

2. Confirmation Required

No preference is stored without explicit user confirmation:

• "Actually, I prefer X" → "Should I remember: prefer X?"
• User says yes → store
• User says no → don't store, don't ask again

3. Ultra-Compact Format

Keep each entry 5 words max:

• python: prefer 3.11+
• naming: snake_case for files
• tests: colocated, not separate folder

4. Category Organization

Group by type (see dimensions.md):

• Stack — frameworks, databases, tools
• Style — naming, formatting, comments
• Structure — folders, tests, configs
• Never — explicitly rejected patterns

5. Memory Limits

• memory.md ≤100 lines
• When full → archive old patterns to history.md
• Merge similar entries: "no Prettier" + "no ESLint" → "minimal tooling"

6. On Session Start

1. Load ~/coding/memory.md if exists
2. Apply stored preferences to responses
3. If no file exists, start with no assumptions

7. Query Support

User can ask:

• "Show my coding preferences" → display memory.md
• "Forget X" → remove from memory
• "What do you know about my Python style?" → show relevant entries

Common Traps

• Adding preferences without confirmation → user loses trust
• Inferring from project structure → privacy violation
• Exceeding 100 lines → context bloat
• Vague entries ("good code") → useless, be specific

Security & Privacy

Data that stays local:

• All preferences stored in ~/coding/
• No telemetry or analytics

This skill does NOT:

• Send data externally
• Access files outside ~/coding/
• Observe without explicit user input

Feedback

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