kiro-config

Audits agents, prompts, skills, knowledge, and documentation for gaps, inconsistencies, and improvement opportunities. Proposes changes for user approval. Triggers on "agent-audit", "audit agents", "review config", "what can we improve".

Use before any creative work or spec creation. Explores intent, challenges assumptions, and produces specs. Triggers on "brainstorm", "let's design", "spec out", "define requirements", "write a spec", "challenge this", "poke holes", "what am I missing".

Detects documentation drift after structural changes. Dispatches parallel specialist reviewers and auto-fixes. Triggers on "check my docs", "audit docs", "doc drift", "check doc drift", or auto from post-implementation when tracked categories change.

Automated post-implementation workflow. Triggers when the orchestrator receives DONE from an implementation subagent. Runs quality gate, doc staleness check, auto-review, and improvement capture.

Periodic codebase health check. Use when the user says "health check", "technical debt", "what needs attention", "codebase audit", "codebase health".

Takes a spec phase and generates an execution plan with parallel stages, agent routing, review gates, and verification criteria. Use before dispatching implementation work. Triggers on "plan execution", "generate execution plan", "how should we execute this", or internally when the orchestrator is about to implement a spec phase.

Use when executing implementation plans with independent tasks in the current session

Terraform-specific diagnostic workflow. Use when the user pastes a terraform error, plan failure, missing variable, or state drift issue. Triggers on "diagnose terraform", "why did plan fail", "trace terraform issue", "what broke in terraform", "missing variable".

Use when you have a spec or requirements for a multi-step task, before touching code

Create a GitHub pull request from the current feature branch. Use when the user says "create pr", "open pr", "merge request", "create mr", "open mr".

Use when reviewing TypeScript code quality — run ESLint, check types, verify tests, flag common issues. Trigger on "audit", "typescript audit", "lint", "check TypeScript code".

Create a versioned release with tag, push, and GitHub release. Use when the user says "ship", "release", "tag and release", "create release", "ship it".

Create a git commit following conventional commit format. Use when the user explicitly asks to commit changes.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when reviewing Python code quality — run ruff, check types, verify tests, flag common issues. Trigger on "audit", "code quality", "lint", "check code".

Deep code flow tracing with file:line references. Use when the user says "trace this", "how does this feature work end-to-end", "map the code flow", "what files are involved in", "walk through the execution".

Use when implementing any feature or bugfix, before writing implementation code

Explains code with analogies and visual diagrams. Use when the user asks how code works, wants to understand a codebase, or uses phrases like "explain", "how does this work", "walk me through".

Push the current branch to the configured remote. Use when the user explicitly asks to push changes.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when about to claim work is complete, fixed, or passing, before committing or creating MRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always