skill-improvement

Use when optimizing existing Claude skills, checking skill quality, auditing skill compliance, or when skills have obvious issues. Triggers on skill optimiza...

This skill appears internally consistent and requests no installs or secrets; it will read referenced documentation, create backups, propose and apply edits to skill files, and run verification subagents. Before installing or running it: (1) be prepared to review diffs and change logs — do not accept edits blindly; (2) ensure sensitive credentials are not stored in the skill files it will read or modify; (3) if you have change-control requirements, run the diagnostic/report phases only and do not allow automatic 'Fix selected' actions; and (4) if you want to limit impact, deny background/subagent execution or require explicit user confirmation before applying any edits. If you want stronger guarantees, ask the author for a dry-run mode that only produces reports and diffs without applying changes.

Type: OpenClaw Skill Name: skill-improvement Version: 1.0.0 The skill bundle is a comprehensive meta-toolkit designed to enable an AI agent to audit, optimize, and verify the quality of other skills within the OpenClaw ecosystem. It implements a structured workflow (Diagnose, Report, Select, Execute, Verify) supported by detailed quality standards and diagnostic checklists in files like `SKILL.md` and `references/quality-standards.md`. While the skill performs high-privilege actions such as file modification and spawning subagents for testing (as detailed in `references/verification-guide.md`), these behaviors are strictly aligned with its stated purpose and include safety-oriented instructions like mandatory backups, diff previews, and regression testing. No evidence of malicious intent, data exfiltration, or prompt injection was found.