Coding 1.0.3

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

Security Scan

The skill's behavior (local, file-based coding preference memory) is coherent with its description, but small metadata inconsistencies and a few optional external commands/suggestions raise questions you should verify before installing.

Purpose & Capability

Name/description (coding style memory) match the declared behavior: it stores and applies compact preferences in ~/coding/. It requires no binaries, no env vars, and no network access — all proportional to the stated purpose.

Instruction Scope

SKILL.md limits actions to reading/writing ~/coding/memory.md and history.md and explicitly forbids reading project files or making network requests. This scope is appropriate. However, the instructions include optional feedback commands (e.g., 'clawhub star coding', 'clawhub sync') which, if executed by the agent, could cause network activity outside the stated 'never make network requests' guarantee. The skill also relies on the agent to strictly follow the 'explicit confirmation only' rule — enforcement is platform-dependent.

Install Mechanism

No install spec and no code files — instruction-only. This minimizes filesystem and supply-chain risk; nothing is downloaded or written beyond the documented ~/coding/ files.

Credentials

No environment variables, no credentials, and no config-path access are requested. That aligns with a simple local preference memory skill.

Persistence & Privilege

always is false and the skill does not request system-wide changes or modify other skills. It persists only to ~/coding/, which is reasonable. Confirm whether your platform sandbox or permissions allow skills to read other home-directory files — the skill asserts it will not, but the platform enforces actual file access.

Scan Findings in Context

[no_regex_findings] expected: The regex-based scanner found nothing. That's expected for an instruction-only skill with no code files to analyze.

What to consider before installing

This skill appears to do what it says: store compact coding preferences locally in ~/coding/ and apply them only after explicit confirmation. Before installing: (1) verify the package metadata — _meta.json ownerId and version differ from the registry metadata (minor inconsistency that could indicate packaging issues); (2) decide whether you’re comfortable with a skill writing a small file in your home directory and set ~/coding/ permissions accordingly (e.g., create the directory yourself with restrictive mode); (3) confirm your agent/platform enforces the skill’s 'no network' and 'do not read project files' promises — the SKILL.md can state this but enforcement depends on the platform; (4) be cautious about running optional commands like 'clawhub sync' suggested in the docs, as they may perform network actions. If any metadata or provenance concerns remain, ask the skill maintainer for clarification or run the skill in a restricted/test environment first.

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