Humanize Ai Writing
v1.0.0Rewrite AI-generated developer text to sound human — fix inflated language, filler, tautological docs, and robotic tone. Use after review-ai-writing identifi...
⭐ 0· 17·1 current·1 all-time
byKevin Anderson@anderskev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
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
The name/description, declared dependencies (docs-style, review-ai-writing) and the runtime instructions align: the skill expects to consume review-ai-writing results and rewrite files. However, the SKILL.md uses git and jq commands yet the registry metadata lists no required binaries — the skill should declare git and jq (or equivalent) as required tooling.
Instruction Scope
Instructions stay within scope (load review results, read reference docs, apply text fixes). They do perform repository operations: check git status, create a git stash automatically if the working tree is dirty, edit files in-place for 'safe' fixes, and interactively prompt for 'needs review' fixes. There are no network/external endpoints or hidden exfiltration steps in the provided text. Automatic stashing and in-place file edits are legitimate for this task but could be surprising if you have uncommitted work.
Install Mechanism
Instruction-only skill with no install spec or code files — lowest installation risk. Nothing will be written to disk by an installer step beyond what the agent's normal execution does (editing repo files).
Credentials
No environment variables, credentials, or config paths are requested. The requested accesses (reading .beagle/ai-writing-review.json and local repo files) are proportional to the stated purpose.
Persistence & Privilege
always:false and disable-model-invocation:true — the skill will not be force-included or autonomously invoked. It does modify the repository it runs in (stashing and editing files), but it does not request system-wide privileges or change other skills' configs.
Assessment
This skill appears to do what it says: load results from a prior review and rewrite developer-facing prose. Before using it: (1) Ensure git and jq (used in the instructions) are available in your environment — the skill metadata doesn't list them. (2) Run it on a clean branch or commit, or back up uncommitted changes — the skill will auto-create a git stash (it warns, but will push a stash by default). (3) Be prepared to review the interactive prompts for 'needs review' fixes; safe fixes are applied automatically. (4) Confirm you have the upstream 'review-ai-writing' results (.beagle/ai-writing-review.json) or run with --all so the skill can generate them. If you need extra caution, run with --dry-run to see exactly what changes would be made before applying them.Like a lobster shell, security has layers — review code before you run it.
latestvk97cxf1z0fgah3rtx0hq3fam9984jnat
License
MIT-0
Free to use, modify, and redistribute. No attribution required.