from bkit-gemini59
Manage Plan → Design → Do → Check → Act cycles: create plan/design docs, run gap analysis, iterate fixes, and generate completion reports.
Provides an end-to-end PDCA workflow skill that guides product or feature work through Plan, Design, Do, Check, Act phases. It creates plan and design documents from templates, generates architecture options, runs gap analysis against implementation, and can iterate fixes until a target match rate is reached. The skill integrates with agent tools (gap-detector, pdca-iterator, report-generator) to automate analysis and reporting.
Use when you need structured execution and verification of feature delivery — drafting plans and designs, producing implementation guides, measuring implementation vs design (match rate), and auto-iterating until quality targets are met. Not for trivial one-line fixes or non-development tasks.
Best with agents and tools that support file operations and programmatic analysis (gap-detector, pdca-iterator, report-generator, and CLI-based extensions such as Gemini CLI).
This skill has not been reviewed by our automated audit pipeline yet.
Batch
Run PDCA workflow commands across multiple features in parallel or bulk, with progress tracking, fail-forward behavior, and retry options.
BTW (By-The-Way) Suggestion Collector
Capture lightweight improvement suggestions while you work and store them locally in .bkit/btw.json for later review, analysis, or promotion into PDCA planning.
Loop (Recurring Command Runner)
Run prompts or shell commands on a recurring interval (seconds/minutes/hours) with safety limits and optional stop conditions — useful for monitoring and period
