メニュー
Create, patch, lint, discover, trace, and complete docs-first specs. Use when working in Claude Code and the user needs tx commands from this area.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | tx-docs-specs |
| description | Create, patch, lint, discover, trace, and complete docs-first specs. Use when working in Claude Code and the user needs tx commands from this area. |
| metadata | {"short-description":"Create, patch, lint, discover, trace, and complete docs-first specs."} |
Use when the user is working in PRDs, DDs, invariants, decision tracking, or markdown export flows.
tx doc add prd <name> --title "Title"tx spec discovertx spec statustx decision: Manage decisions as first-class artifactstx decompose: Create a task graph from a design spectx doc: Manage docs-as-primitivestx doc add: Create a new doctx doc attach: Attach a doc to a tasktx doc edit: Open doc markdown in editortx doc link: Link two docstx doc list: List all docstx doc lock: Lock a doc versiontx doc patch: Create a design patch doctx doc rm: Remove latest mutable doc versiontx doc rm: Remove latest mutable doc versiontx doc show: Show doc detailstx doc sync: Re-read docs from disk and update DB hashestx doc validate: Validate doc/task coverage and index search metadatatx doc version: Create new version from locked doctx invariant is deprecated. Use 'tx spec' instead.tx md-export: Export tasks to markdown filetx spec: Docs-first spec-to-test traceability primitivestx spec batch: Import test run results from stdintx spec complete: Record human completion sign-offtx spec discover: Refresh doc-derived invariants and upsert test mappingstx spec fci: Compute Feature Completion Indextx spec gaps: List uncovered invariants (no linked tests)tx spec health: Repo-level spec-driven development rolluptx spec link: Manually link an invariant to a testtx spec lint: All-in-one spec and doc checkertx spec matrix: Full invariant-to-test traceability matrixtx spec run: Record a pass/fail run result for a canonical test IDtx spec status: Explain scope closure statetx spec tests: List tests linked to an invarianttx spec unlink: Remove an invariant/test mappingtx triangle is a deprecated alias for 'tx spec health'.Read references/commands.md for the full generated CLI help text for this skill's commands.
When working in Claude Code, prefer rg -n <pattern> <path> and rg --files <path> over broad grep -r or fragile find pipelines.
If a shell/search command fails because of malformed flags, truncated paths, or broken quotes:
rg command with an explicit directorynode_modul or unterminated quotesgrep -r with rg -n unless rg is unavailablefind probes with rg --files when you are really locating source filesLong-running (multi-hour) adversarial hunt for P0/P1/P2 bugs across the codebase. Mixes codebase observation, mechanical linting, real test + telemetry verification, and parallel skeptic sub-agents that must REFUTE each candidate before it is accepted. Fixes verified bugs on a branch off main with surgical per-bug commits, re-runs gates, and writes a dated report to the Desktop. Never pushes or merges. Use when you want a deep, autonomous bug-finding-and-fixing pass.
Diagnose and durably eliminate flaky/intermittent test failures (passes locally but fails CI, rotates between tests, red only under load). Reproduce under contention, instrument the real state instead of guessing, root-cause by signal not duration, fix at the source, validate multi-run. Use when a test is flaky, CI is intermittently red, or fixing one flake unmasks others.
Safely prune dead local branches, git worktrees, and remote branches in this repo. Use when asked to "prune dead branches", "clean up worktrees", "delete merged branches", "tidy up git", or after a batch of PRs has merged. Knows this repo merges via squash, so it verifies death by PR state, not just git ancestry.
Reduce test-suite wall-clock (dev + CI) without losing coverage or telemetry. Measure the phase breakdown first, then apply proven levers (parallelize turbo, narrow imports vs barrels, lazy-load heavy graphs, pool/worker config, DB pool sizing) and capture the before/after delta. Use when tests are slow, CI time is high, or to set/check a perf baseline. Composes with the read-only test-perf and test-census skills.
Census the repo's tests by TYPE, not by name. Classifies every tracked test file via content heuristics into unit / integration / react-component / e2e (plus a separate db pgTAP count), in precedence order so buckets are mutually exclusive. Use when the user asks "what kinds of tests do we have", "how many component vs integration tests", "what's our e2e coverage", or wants a per-area test-type breakdown.
Snapshot test-suite timings in this repo. Runs the unit and/or integration suites (or a single integration project) and reports wall-clock time, Vitest's own phase breakdown (transform/setup/import/tests/environment), and the slowest test files. Use when the user asks "how slow are the tests", "where does the test time go", wants a perf baseline, or wants to check the suite hasn't regressed.