ai-company-studio
claudeDesign and generate AI-only companies as repositories
3 skills · 3 commands
Shelve every document into its proper home — CLAUDE.md, README, docs/, project skills, adr/, references/, notes/ — inspect each one's content against reality, and reorganize on approval or bootstrap the structure, constitution seed and the guarantees that close private memory, keep attribution accurate, and keep emoji out of files included, in a new project.
Plugin shosoin from marketplace tks08-plugins in saita08/tks08-plugins. Commands read from the repo's manifest — 30 days ago.
close-notesCloses a task's notes by promoting what deserves a durable shelf and deleting the rest. Use when a task is closing — its pull request is merging, its feature has landed, its handover has been picked up — and notes/ holds what the task left behind. Triggers on "close the task", "clean up the notes",
shelve-knowledgeDecides which shelf a piece of written knowledge belongs on — CLAUDE.md, README, docs/, a skill in .claude/skills/, adr/, references/, or notes/ — before it is written. Use when about to create, extend, or move a documentation file, a docs/ page above all, or when someone asks where something should
write-adrRecords an architecture decision in adr/ before the implementation lands, and moves docs/ and the indexes in the same change. Use when a choice is being made that a future reader could not reconstruct — a structure, a data format, a stack, a distribution mechanism — or when a change to the repositor
shelving-contractThis skill should be used when the user asks where a document or a piece of knowledge belongs in a repository, asks about the roles of CLAUDE.md vs README.md vs docs/ vs adr/ vs references/ vs notes/, asks whether something should be a project skill or a rule rather than a docs page, mentions "ドキュメン
/shosoin:auditMap every document in the project to its proper shelf — CLAUDE.md, README, docs/, .claude/skills/, adr/, references/, notes/ — report misplacements with evidence, and reorganize after explicit approval.
/shosoin:inspectVerify each document's content against reality — stale claims in docs/, procedure skills whose steps no longer run, broken links, ADRs edited after acceptance, notes that outlived their task, reference data the code has moved past — and report what can no longer be trusted.
/shosoin:setupBootstrap the shelved documentation structure — CLAUDE.md, docs/, adr/, references/, the contract's three procedure skills, a README map — and install the guarantees that close private memory, keep attribution accurate, and keep emoji out of files, all in a project that does not have them yet.
Design and generate AI-only companies as repositories
3 skills · 3 commands
A spellbook of battle-tested Workflow scripts — cast them against a target, inscribe your own, and browse the collected spells.
1 skill · 3 commands
Conjure fenced autonomous routines that run on a schedule when you are away, each bound to report back so its work is never invisible.
1 skill · 3 commands
A personal eval harness that issues a report card to your Claude setup — register tasks as subjects, examine them with a fixed grader, and track how scores move when your configuration changes.
1 skill · 3 commands
Record the directions the user has rejected, and the principle behind each rejection, then replay them into every future session so a declined idea does not return in new clothes.
1 skill · 2 commands · hooks
A standard architecture for solo-developed products — a layered backend (Service Layer and Repository) under onion-style inward dependencies, thin entry points that all share one services layer, and views sorted by a single question — so Claude lays out a new project's skeleton and places each new file without the structure being explained again; scaffold the skeleton, and check an existing tree for violations.
1 skill · 2 commands
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.