Most Used Tags
Enforce evidence-based completion claims — require fresh command output before reporting success. Use when completing any task, fixing a bug, finishing a phase, running tests, building, deploying, or making any "it works" claim.
Use AI DevKit memory via CLI commands. Search before non-trivial work, store verified reusable knowledge, update stale entries, and avoid saving transcripts, secrets, or one-off task progress.
Structured SDLC workflow with 8 distinct phases for feature development.
Test-driven development — write a failing test before writing production code. Use when implementing new functionality, adding behavior, or fixing bugs during active development.
Proactively orchestrate running AI agents — scan statuses, assess progress, send next instructions, and coordinate multi-agent workflows. Use when users ask to manage agents, orchestrate work across agents, or check on agent progress.
Scaffold feature documentation from requirements to implementation readiness.
The toolkit for AI-assisted software development, enhancing coding agent efficiency.
Review and improve documentation for novice users. Use when users ask to review docs, improve documentation, audit README files, evaluate API docs, review guides, or improve technical writing.
Streamline update planning documentation to reflect implementation progress.
Capture structured knowledge about code entry points and document it effectively.
Store reusable guidance in the knowledge memory service.
Ensure implementation aligns with design and requirements documentation.
Streamline the process of adding tests for new features.
Pre-push code review against design docs.
Review feature requirements for completeness.
Execute a feature plan task by task for streamlined development.
Analyze and simplify existing code implementations to enhance maintainability and scalability.
Guide structured debugging before code changes by clarifying expected behavior, reproducing issues, identifying likely root causes, and agreeing on a fix plan with validation steps. Use when users ask to debug bugs, investigate regressions, triage incidents, diagnose failing behavior, handle failing tests, analyze production incidents, investigate error spikes, or run root cause analysis (RCA).
Review feature design for completeness.