Skill Quick Index

Build a wide-trigger, precise-match index for local OpenClaw skills (L1-L3), then quickly route by intent/category/keywords.

This package appears to be a local, read-only lookup tool (scripts/skill_lookup.py) operating on a shipped index (index/skill_index.json). However, the documentation claims the skill 'scans local skills' and 'builds' an index — those behaviors are not implemented in the included script. Before installing or relying on it: (1) confirm whether you need an index builder (the supplied index is static and may be stale); (2) if you expect automatic scanning of ~/.openclaw/workspace, ask the author for the scanner code or review any additional scripts — scanning user directories would read your local skill files and needs explicit consent; (3) inspect the shipped index JSON for any sensitive references you don't want shared; and (4) if you plan to run or extend it, consider running the Python script in a restricted environment (no network access) and review any future changes for network calls or subprocess execution. The inconsistency looks like poor documentation rather than active malicious behavior, but clarification from the author is recommended.

Type: OpenClaw Skill Name: skill-quick-index Version: 1.0.1 The skill-quick-index bundle is designed to provide a local lookup for OpenClaw skills based on keywords. The `scripts/skill_lookup.py` script safely reads a local JSON index (`index/skill_index.json`) and performs string matching on user input from `sys.argv[1]`. There is no evidence of command injection, network activity, sensitive data exfiltration, or persistence mechanisms. The `SKILL.md`, `README.md`, and `clawhub.yaml` files contain only descriptive text and usage examples, with no malicious instructions or prompt injection attempts against the AI agent. The code's behavior aligns perfectly with its stated purpose.