document-review
v2.56.0Structural review of documents for gaps, clarity, completeness, and organization. Use when a brainstorm, plan, spec, ADR, or any doc needs polish before the...
⭐ 0· 144·0 current·0 all-time
byIlia Alshanetsky@iliaal
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name and description align with the SKILL.md: it reads documents, runs structured checks, proposes edits, and can apply minor fixes. There are no unrelated env vars, binaries, or install steps requested.
Instruction Scope
The runtime instructions explicitly read repository paths (docs/brainstorms/, docs/plans/) and update documents inline. They also allow dispatching a zero-context sub-agent for a reader test. These actions are within the stated purpose but grant the skill the ability to read and overwrite local documents and to spawn a sub-agent — which may be surprising if you expect read-only reviews.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is written to disk by an installer. Low-install risk.
Credentials
No environment variables, credentials, or external config paths are requested. The SKILL.md does not reference any secrets or external services.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. However, it instructs the agent to save revisions inline and to auto-fix minor issues without asking. Because it can modify files, consider that it has effective write privilege to project documents when invoked.
Assessment
This skill appears to do what it says, but be aware it will read repository documents and can write edits directly (auto-fixing minor issues without confirmation and asking for approval only on substantive changes). Before enabling or running it on important content: (1) ensure the agent has only the file-system access you intend, (2) work on a copy or ensure version control/backups are in place, (3) confirm you’re comfortable with automatic inline edits (or request that the agent present proposed edits before saving), and (4) if you need to limit sub-agent spawning, check platform/sub-agent policies or disable that optional step.Like a lobster shell, security has layers — review code before you run it.
latestvk97e5kd5a1gss4qn5h1nzpmm3s84t1rm
License
MIT-0
Free to use, modify, and redistribute. No attribution required.