md-docs
v2.53.0Manages project documentation: CLAUDE.md, AGENTS.md, README.md, CONTRIBUTING.md. Use when asked to update, create, or init these context files. Not for gener...
⭐ 0· 17·0 current·0 all-time
byIlia Alshanetsky@iliaal
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the actual behavior: the SKILL.md instructs the agent to read repository files, detect stack/commands, and generate or update AGENTS.md, README.md, and CONTRIBUTING.md (with restrictions). No unrelated binaries, env vars, or network endpoints are requested.
Instruction Scope
Instructions explicitly direct reading of repo files (package.json, pyproject.toml, lockfiles, .git history) and performing local edits (mv, ln -sf, cp backups). This is within the skill's purpose but implies the agent will modify repository files (including an automatic CLAUDE→AGENTS migration if present). Recommend always using --dry-run and reviewing diffs before applying changes.
Install Mechanism
Instruction-only skill with no install spec and no code files. No packages or remote downloads are referenced.
Credentials
The skill requests no environment variables, credentials, or config paths. Its file reads/writes are limited to repository files consistent with documentation tasks.
Persistence & Privilege
always:false (default). The skill does not request permanent/privileged presence or to modify other skills' configurations. Autonomous invocation remains possible (platform default) but is not a special privilege here.
Scan Findings in Context
[no_code_files_scan] expected: Regex-based scanner had no code files to analyze (instruction-only SKILL.md and reference docs). Absence of findings is expected but not proof of safety; primary surface is the runtime instructions.
Assessment
This skill is coherent for managing repo documentation. It will read repository files and can modify Markdown (including renaming CLAUDE.md → AGENTS.md and creating a symlink). Before installing or allowing autonomous runs: (1) prefer --dry-run to review proposed edits and diffs, (2) ensure backups or commit your repo so changes can be reverted, (3) be aware the migration step (mv + ln -sf) will overwrite files and may behave differently on Windows, and (4) do not rely on the skill to create policy-sensitive docs (CONTRIBUTING.md is only updated, never auto-created). If you need tighter control, disable autonomous invocation for this skill or require manual approval for write operations.Like a lobster shell, security has layers — review code before you run it.
latestvk9716dh0hzwtzev48ds0xmwdrs84a9bp
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
