Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
9 engineering disciplines for AI agents — TDD, debugging, code review, planning, and multi-agent coordination. Build software like it matters.
9 engineering disciplines for AI agents — TDD, debugging, code review, planning, and multi-agent coordination. Build software like it matters.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
9 skills that turn AI agents into disciplined software engineers. Battle-tested on a 4-agent team shipping production software.
SkillWhat It Enforcescraftwork:test-driven-developmentNo production code without a failing test firstcraftwork:systematic-debuggingNo fixes without root cause investigationcraftwork:verification-before-completionNo "done" claims without fresh evidencecraftwork:brainstormingNo code without exploring approaches firstcraftwork:writing-plansNo implementation without exact file paths, code, and testscraftwork:subagent-driven-developmentOne subagent per task, structured review between eachcraftwork:dispatching-parallel-agentsSafe parallel execution for independent taskscraftwork:requesting-code-reviewStructured diff review with security and spec checklistcraftwork:receiving-code-reviewTechnical rigor over performative agreement
clawhub install craftwork
Agents are fast but sloppy. They skip tests, guess at fixes, claim "done" without checking, and agree with every review comment. These skills add guardrails — not to slow agents down, but to make their speed count. Every skill follows the same pattern: stop, verify, then act.
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.