From copilot-cli-toolkit
Implements changes incrementally in thin vertical slices using TDD, atomic commits, and complexity assessment. Run after /plan for structured builds.
How this skill is triggered — by the user, by Claude, or both
Slash command
/copilot-cli-toolkit:buildThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
@CLAUDE.md
@CLAUDE.md
Build: $ARGUMENTS
If $ARGUMENTS is empty, check for recent /plan output in the conversation. If none found, ask the user what to build.
Before implementation, Task(subagent_type="analyst"): Read .claude/skills/analyze/references/engineering-complexity-tiers.md and the task description. Classify as Tier 1-5. Return: tier, rationale, and recommended oversight level. Use this to calibrate implementation approach:
Task(subagent_type="implementer"): You are a senior engineer. Discover the project's tech stack, coding patterns, and test conventions by reading the codebase. Build in thin vertical slices. Test-first when the project has tests. Commit atomically.
For each slice:
After implementation, invoke Skill(skill="code-qualities-assessment") to score the result.
The agent should self-check:
npx claudepluginhub rjmurillo/ai-agentsBreaks multi-file features into incremental slices. Implement, test, verify, then commit each vertical slice. Useful for large changes that should leave the system in working state.
Implementation skill emphasizing verification-driven coding with tight feedback loops. Guides multi-step implementation work: orient, plan, implement, verify, commit. Based on analysis of 21k+ operations.
Executes an implementation plan — writes code and tests, runs quality review, and ships a pull request.