// Run unit tests and fix failures. Use when the user asks to run tests, fix failing tests, make tests pass, tests are broken, fix test errors, or get tests green.
Upgrade outdated npm dependencies in the pnpm monorepo (recursive update, latest, targeted packages). Use when the user asks to upgrade dependencies, bump packages, refresh lockfile, pnpm update, outdated packages, latest versions, or dependency refresh—not monorepo release versions.
Format code, run linters and static analysis, and find unused code (ESLint + Knip). Use when the user asks to fix lint, format code, run formatters, find dead code, unused exports, run knip, fix style, tidy code, or run eslint --fix.
Manage Architecture Decision Records (ADRs). Use this to initialize, create, list, and link ADRs to document architectural evolution. Requires 'adr-tools' to be installed.
Use at the end of a coding session to summarize outcomes, failures, inefficiencies, and root causes, then output a concise postmortem report with ranked improvements for next time. Output only in chat; do not edit project files unless the user explicitly asks. Skip nit-picks and one-off mistakes.
Interactively bump package versions for the parser package. Use when the user asks to bump version, increment version, set release version, or release dbt-artifacts-parser.
Regenerates TypeScript types from dbt artifact JSON schemas. Use when the user asks to update parsers, sync with upstream, refresh types, or regenerate parser types from existing schemas.
| name | test-fix |
| description | Run unit tests and fix failures. Use when the user asks to run tests, fix failing tests, make tests pass, tests are broken, fix test errors, or get tests green. |
| compatibility | Requires pnpm (or npm/yarn); project must define a test script. |
Activate this skill when the user says or implies:
Run the test suite; if it fails, read the output, apply minimal fixes, and re-run until tests pass or an iteration limit is reached.
Run from the repository root.
pnpm test (runs pnpm --recursive test; the package uses vitest run).pnpm test:coverage (runs Vitest with coverage across workspace).pnpm coverage:report — runs tests with coverage, writes coverage-report.json, exits 1 if below thresholds. Use when verifying test coverage before completion.pnpm test from the repository root.pnpm test.First run (tests fail):
pnpm test
After editing files to fix reported failures:
pnpm test
Verifier step 3 is the coverage report gate—use the Coverage report command in Commands for this repo above (pnpm coverage:report).
When used by the verifier agent, the verifier also runs pnpm coverage:report after tests pass. If coverage:report fails (belowThreshold or test failures), add or improve tests per this skill's fixer loop and re-run pnpm coverage:report until it exits 0.
If the project uses a different package manager or test command, run the equivalent from the repo root (e.g. npm test, yarn test, pnpm test, cargo test). Use the same fixer loop: run tests → read failures → fix → re-run.