Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
npx skills add https://github.com/pskoett/self-improving-agent/tree/main/skills/self-improvementCaptures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
Open-source local Agent orchestration for self-improving agent teams: run agents, review work, and turn feedback into reusable skills.
OpenCode Agent Team Harness - multi-agent coding workflow with orchestrator + 6 subagents + skills + memory
Official skill registry for ZeroClaw — community-contributed AI agent skills, tools, and workflows
skill does absolutely nothing, as well as the agent that uses it.
AI workflow skills for turning specs into GitHub issue trees, model-sized implementation tasks, autonomous PRs, and cited repo story/state reports across Codex, Claude Code, and OpenCode.
Sync, validate, and apply App Store metadata with the current asc canonical metadata workflow. Use when updating metadata, localizations, keywords, or migrating legacy fastlane metadata.