Consolidate a repo's pending-task tracking into its single task ledger (default .notes/TASKS.md) — bootstrap it if missing, sweep handoff / audit / remaining-issues files and auto-memory for stray task lines, verify pending entries against git log and actual code, archive detail files of completed tasks. Use when the…
Run one cycle of the task-triage loop over a repo's task ledger — judge every open task (verify its premise in code, check its start condition against the 照合先, decide whether it is still worth doing, look for a better solution), then dispatch the accepted ones to fresh implementation sessions and act as their…
A repository setup and audit process that chooses mechanical checks for the languages and tools actually present in a codebase. A mechanical check is an automated gate such as formatting, linting, or tests.
A read-only tool that scans an Obsidian vault, a folder of linked Markdown notes, and finds research ideas that could change the next steps in a code repository. It saves a ranked, source-linked list in the repository’s .notes folder.
A query tool for an Obsidian vault, which is a folder of linked Markdown notes, including a wiki of concepts and research notes. It combines information from several notes and includes links back to its sources.
A writing workflow that turns one daily research report into a Japanese draft for a long X post. X is the social platform formerly known as Twitter; the workflow stops at a copyable draft.
Audit installed Claude skills for quality and surface Keep/Improve/Update/Retire/Merge verdicts. Use when the user says "audit my skills", "stocktake", "review my skills", "which skills should I retire or merge", "do a quality pass over my skills", or "/skill-stocktake". NOT for creating or improving a single skill…
Five-question triage for routing AI work to the right architecture — script, algorithmic search, LLM workflow, or autonomous agentic loop — before any agent is built. Use when someone says "let's build an agent for X", when deciding whether a use case actually needs an autonomous agent, when reviewing an agent…