Coding
v1.0.3Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
⭐ 15· 11.5k·180 current·194 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (coding-style memory) align with the contents: the skill stores, applies, and manages compact user preferences in ~/coding/. It does not request unrelated credentials, binaries, or external services.
Instruction Scope
Runtime instructions are narrowly scoped to creating, reading, and writing files under ~/coding/ and to asking the user for explicit confirmation before storing preferences. This matches the stated purpose. One operational note: SKILL.md includes a shell snippet (mkdir -p ~/coding) and an explicit 'On Session Start: Load ~/coding/memory.md' rule — these cause the agent to read files from the user's home directory (expected for this skill) so users should be aware stored preferences are readable by any process with access to their home directory.
Install Mechanism
No install spec and no code files — lowest-risk model. Nothing is downloaded or written beyond the local memory files the skill explicitly instructs the agent to create/manage.
Credentials
The skill requests no environment variables, credentials, or external config paths. All data is intended to be local to ~/coding/. There are no unexplained secrets or broad access requests.
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges or modify other skills. Autonomous invocation is allowed (platform default) but nothing in the skill grants elevated privileges or cross-skill config changes.
Assessment
This skill appears coherent and local-only: it will create and manage ~/coding/memory.md and ~/coding/history.md and will only store preferences after you explicitly confirm. Before installing, consider: (1) inspect ~/coding/memory.md periodically and remove any entries you don't want retained; (2) avoid storing secrets or project-specific sensitive data in this memory; (3) confirm your agent implementation actually enforces the 'explicit-only' rule (the SKILL.md is a policy — the agent must follow it); (4) be cautious if you run any suggested external commands (e.g., clawhub sync) since those may perform network activity outside the skill. Overall, nothing here requests unrelated credentials or external downloads, so it is internally consistent with a local preference memory.Like a lobster shell, security has layers — review code before you run it.
latestvk97027xz2f06kg7283c7zrw76981efzv
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
💻 Clawdis
OSLinux · macOS · Windows