Ensure Docs
v1.0.0Verify documentation coverage and generate missing docs interactively
⭐ 0· 76·1 current·1 all-time
byKevin Anderson@anderskev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (verify and generate docs) match the instructions: language detection, per-language verification, consolidation, and optional generation. There are no unrelated environment variables, binaries, or installs requested.
Instruction Scope
The runtime instructions use shell commands (find/grep/ls/head) to enumerate repository files and spawn platform 'Task' subagents for verification and generation; this is appropriate for scanning a codebase. Note: the scan runs against the target directory (default: current working directory) and the generation phase will produce content that could modify repository files if the user requests generation—the skill does not explicitly describe committing or remote pushes, but it can write changes locally via generated agents.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is downloaded or written by an installer. Low install risk.
Credentials
The skill requires no environment variables, credentials, or config paths. It uses platform tools (Task, AskUserQuestion) but does not request secrets or unrelated service tokens.
Persistence & Privilege
always is false and disable-model-invocation is true (so the skill will not autonomously invoke the model). The skill does not request persistent system-wide changes or modify other skills' configurations.
Assessment
This skill appears coherent and safe in scope: it will scan the target directory (default: your current working directory) to find source files and may generate docstrings/files if you choose that option. Before running: (1) run it in a copy or ensure you have version control so you can review generated changes, (2) ensure any linters or language toolchains you want used by the skill are available if you expect lint verification to run, and (3) be aware it spawns platform subagents (Task) to perform per-language analysis — these subagents will access files in the target directory but the skill does not request external credentials or network endpoints. If you need the skill to never modify files, use the --report-only option.Like a lobster shell, security has layers — review code before you run it.
latestvk972tw71dvj1djayfbkw0s9bh184khyq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.