Reflect Critique Revise

Performs a multi-pass senior engineer critique and revision of code, improving quality by catching bugs, API misuse, and style issues across domains like iOS...

This skill will transmit your provided code and task text to whatever LLM endpoint is configured (OPENCLAW_LLM_ENDPOINT, defaulting to http://localhost:8080). Before installing: 1) Verify the endpoint is trusted (prefer local or vetted cloud endpoints); sensitive or proprietary code should not be sent to an untrusted remote service. 2) Ensure python3 and aiohttp are installed in the runtime environment. 3) Note the registry metadata inconsistency (the top-level 'Requirements' said none, yet SKILL.md and the script expect OPENCLAW_LLM_ENDPOINT and aiohttp); ask the publisher to clarify if needed. 4) Be aware triggers may auto-run after code generation—if you don't want automatic reviews, control invocation or remove triggers. 5) The included code references a model name string ("m27-jangtq-crack") in requests; this is just a parameter sent to your configured endpoint but may warrant extra attention to confirm intended backend/model. If you cannot verify the endpoint or publisher, run the script in a sandbox or inspect/modify it so it posts only to a trusted LLM.

Type: OpenClaw Skill Name: reflect-critique-revise Version: 1.0.0 The skill implements a legitimate multi-pass reflection loop designed to improve the quality of AI-generated code through automated critique and revision. The implementation in `reflect_critique_revise.py` uses standard asynchronous HTTP requests to a configurable LLM endpoint and contains no evidence of data exfiltration, unauthorized execution, or malicious intent. Furthermore, the `SKILL.md` instructions include security-positive checklists that specifically direct the agent to identify vulnerabilities like SQL injection, XSS, and unsafe function usage in the code being reviewed.