Coding Custom

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

Security Scan

The skill's claimed behavior (local coding preference memory stored under ~/coding and updated only with explicit user confirmation) matches its instructions and requirements; minor metadata inconsistencies are present but not security-critical.

Purpose & Capability

The skill's name/description (coding-style memory) aligns with what it asks the agent to do: create and read/write small local files under ~/coding and apply preferences when generating code. It does not request unrelated binaries, credentials, or system paths.

Instruction Scope

SKILL.md limits operations to creating ~/coding, loading/saving memory.md and history.md, and applying stored preferences to outputs. It explicitly forbids reading project files, making network requests, or touching files outside ~/coding, which is coherent with its stated scope.

Install Mechanism

No install spec or bundled code — instruction-only. This minimizes the disk/write/execute footprint and matches the declared design.

Credentials

The skill requires no environment variables, credentials, or external config paths. Its only persistence is local files under the user's home directory, which is proportionate to a preference-memory feature.

Persistence & Privilege

The skill persists user preferences on disk (~/coding/memory.md and history.md) which is expected. always:false (not force-included). The agent is allowed autonomous invocation by platform default — this is normal, but it means the agent could apply stored preferences automatically during interactions. The skill's rules state it must ask before storing preferences.

Scan Findings in Context

[no-code-files] expected: Regex scanner had nothing to analyze because the skill is instruction-only; this is expected for a memory-style skill that stores plain text files locally.

Assessment

This skill appears coherent and only stores small local files under ~/coding, which is appropriate for a coding-preferences memory. Before installing: (1) confirm you are comfortable with the agent writing to ~/coding (check or back up that path if needed); (2) verify the agent actually asks for confirmation before saving preferences (the SKILL.md mandates it, but it's enforced by runtime behavior); (3) be aware the agent may use stored preferences to change code output automatically — review entries in ~/coding/memory.md if results seem unexpected; (4) note minor metadata mismatches (registry name/slug/version/owner vs. SKILL.md) — not a security issue but worth asking the publisher for consistency if that concerns you.

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