liauw-media/CodeAssist - Page 2

git-workflow

Use when making commits, creating branches, or managing Git operations. Ensures consistent Git practices and proper commit messages.

root-cause-tracing

Use when symptoms don't reveal the cause. Trace backward through call chains to find where problems originate. Follow: Observe symptom → Find immediate cause → Identify caller → Keep tracing → Locate trigger.

sharing-skills

Use when contributing skills back to the community. Follow git workflow: sync upstream → create branch → develop skill → test with writing-skills → commit → push → PR. One skill per PR.

testing-skills-with-subagents

Use to validate process documentation. Apply TDD to skill writing: RED (run without skill, document failures) → GREEN (write skill) → REFACTOR (close loopholes). Test under pressure: time constraints, sunk cost, exhaustion, authority.

writing-skills

Use when creating reusable process documentation. Apply TDD: baseline without skill → document failures → write skill → test → iterate. Four types: Discipline, Technique, Pattern, Reference. Iron Law: No skill without failing test first.

testing-anti-patterns

Use to avoid critical testing mistakes. Five Iron Laws: Never test mock behavior, Never add test-only methods, Never mock without understanding, Always integration test, Always test error paths.

subagent-driven-development

Use when decomposing complex work. Dispatch fresh subagent per task, review between tasks. Flow: Load plan → Dispatch task → Review output → Apply feedback → Mark complete → Next task. No skipping reviews, no parallel dispatch.

receiving-code-review

Use when processing code review feedback. Technical evaluation of feedback, verify before implementing. No performative agreement or gratitude.

requesting-code-review

Use when completing tasks or major features. Know when and how to request reviews. Provides git commit range to code-reviewer agent.

defense-in-depth

Use when implementing validation or safety checks. Multi-layer validation approach prevents bugs through redundant safeguards. Makes bugs structurally impossible.

condition-based-waiting

Use when tests fail intermittently. Replace arbitrary timeouts with condition polling. Eliminates flaky tests caused by timing assumptions.

brainstorming

Use when starting new features, major changes, or unclear requirements. Establishes shared understanding before implementation.

executing-plans

Use when implementing a multi-step plan. Execute systematically with verification checkpoints to catch errors early.

writing-plans

Use after brainstorming, before implementation. Breaks work into discrete, actionable tasks with clear verification points.

systematic-debugging

Use when encountering bugs or unexpected behavior. Methodical approach to identify root cause: Reproduce → Isolate → Identify → Fix → Verify.

test-driven-development

Use when adding features or fixing bugs. Follow RED/GREEN/REFACTOR cycle. Write failing test first, implement minimal code to pass, then refactor.

dispatching-parallel-agents

Use when multiple independent tasks can run simultaneously. Enables efficient parallel work execution with specialized agents.

finishing-a-development-branch

Use when ready to merge feature branch. Complete checklist before creating PR/MR. Ensures professional quality and prevents embarrassing mistakes.

git-worktrees

Use when working on multiple features simultaneously. Creates isolated workspaces without branch switching, enabling parallel development.