Repairs, implements, tests, and validates ttsc source, tests, fixtures, workflows, and package wiring. Use before editing any of them; acknowledgments belong to contracts and the typescript-go shim to typescript-go-sync.
Keeps ttsc's compiler-target shims synchronized with TypeScript-Go and complete for plugin authors. Use before adding a shim re-export, bumping a target's compiler, changing the shim audit or generators, or chasing a missing compiler API.
Defines the @evidence checklists every maintained ttsc declaration and test answers, and their evidence.config.json wiring. Use when writing or reviewing maintained source or tests, or changing Evidence selection.
Owns ttsc's writing rules and writes its READMEs, website guides, and doc comments. Use before writing or changing a README, anything under website/src/content, or a doc comment.
Runs ttsc's issue campaign, repeating full discovery rounds until one finds nothing new, publishing the issues, and landing them in one pull request per cycle. Use for a broad audit or repeated issue-to-pull-request work, not for one defined issue.
Runs, supervises, changes, and publishes ttsc's performance, graph, and evidence benchmarks under benchmarks/. Use before running, changing, or publishing any benchmark or its fixtures.
Writes and trims ttsc's prompts for agents, namely AGENTS.md, CLAUDE.md, and the skills under .agents/skills. Use before changing any of them, together with the documentation skill's writing rules.
Branches, commits, pushes, opens, updates, and merges ttsc pull requests. Use only when the user asks for one of those actions or a mandate names delivery.
Runs ttsc's Overall Self-Review of a complete change, which any unqualified review request means, and an issue campaign's per-commit Individual Self-Review. Use for every review or self-review.
Defines frontend implementation order, contract use, resident development checking, live integration, and the frontend gate. Read before frontend work, then read every sibling topic.
Defines the Evidence Graph tag grammar, per-citation reviews, truthfulness rules, claim activation, frozen configuration, behavioral proof, citations, exclusions, and the stub marker. Read before Evidence implementation or handling a graph diagnostic;…
Defines what a Review decides about each acknowledgement, how that judgement is recorded as its review, and the configuration and gates each scope owns. Read only for a review objective; backend.md and frontend.md carry the per-scope carriers, configuration,…
Defines backend layer ownership, implementation order, compiler checking, generation boundaries, and the backend gate. Read before backend work, then read every sibling topic.
Defines the authored and generated parts of packages/api, its public entry, shared diagnosers, SDK connections, and simulation boundary. Read before editing or importing the API package.
Defines the workspace, package boundaries, generated artifacts, phase order, compiler gates, development processes, and canonical commands. Read before choosing where to work or which command to run.
Defines the full-scope review loop until dry for backend, frontend, and overall review objectives. Read for a review objective or when a final objective must complete an omitted review.
Defines how to read the immutable requirement set under docs/analysis without omission or invention. Read before implementation and during completeness review.