Loading...
Loading...
Found 102 Skills
Streamlines bug fixing by creating a GitHub issue first, then a feature branch for implementing and thoroughly testing the solution before merging.
Inline adversarial plan review — 3 sequential checks (Feasibility, Completeness, Scope & Alignment) performed by the calling LLM in its own context. No subagents spawned. Call after saving a plan. Returns GATE_PASS or GATE_FAIL with blocking issues.
Ensures tasks are genuinely resolved before marking them done. Activates at task checkpoints during plan execution — validates that fixes actually work, tests genuinely pass, and acceptance criteria are met. Prevents premature completion declarations.
STUB — installed at ~/openclaw/skills/skill-creator/SKILL.md
Update documentation based on lessons learned. Use after completing work to capture learnings and prevent future issues.
Capture user corrections and feedback after any skill runs, persist them as learned instructions, and silently apply them on future invocations. TRIGGER when: user gives feedback or corrections after a skill runs — e.g. "next time only show top 5", "always use bullet points", "don't include X", "from now on...", "remember to...". Also: "What have you learned about {skill}?", "Show skill tuning", "Clear skill tuning for {skill}"