tdmcp-test-coverage
SkillDev toolsOrchestrate any tdmcp test-coverage work: run the coverage harness, inspect coverage gaps, plan focused Vitest/msw or bridge tests, delegate coverage writers, verify coverage deltas, and re-run gates. Use whenever the user asks to raise coverage, add broad regression coverage, create a test harness, improve tests, re-run a coverage wave, or fix a coverage gate.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the tdmcp-test-coverage skill
What this skill tells your AI
The instructions your AI receives, as published by pantani/tdmcp in .agents/skills/tdmcp-test-coverage/SKILL.md and read by ahel’s review.
Use this skill for coverage-improvement work in this repository. The goal is more tested behavior, not prettier percentages.
Phase 0 - Context
- Read
AGENTS.md,package.json,vitest.config.ts, and the nearest tests. - Run
npm run coverage:harnessunless the user asked for a static-only pass. - Read
_workspace/coverage/latest.md. - Treat the actionable scope as
src/**/*.ts;src/knowledge/data/**is generated reference data and is intentionally excluded.
Phase 1 - Select gaps
Choose one to three independent gaps. Prefer seams where a test can lock a real contract:
- CLI/config: parsing, defaulting, env precedence, diagnostics, and exit behavior.
- Resource/knowledge loaders: URI matching, malformed input, ranking, and stable result shape.
- Tool implementations: Zod defaults, bridge payloads, warnings, and
isErrorpaths using msw. - Server/client boundaries: offline TD behavior, auth forwarding, timeout/retry, event streaming, and transport setup.
Skip generated data, docs-only files, and import-only tests.
Phase 2 - Build tests
For parallel work, spawn tdmcp-coverage-writer agents with one seam each. Give
each writer:
- target file(s) and nearest existing test to mirror;
- behavior to assert;
- expected failure mode or branch to cover;
- exact narrow command to run.
The lead is the single writer for shared config, package scripts, and harness docs. Do not let multiple agents edit the same test file.
Phase 3 - Verify
Run narrow tests first. Then run:
npm run typecheck
npm run build
./node_modules/.bin/biome check .
npm run coverage:harness
npm run validate:recipes
npm run test:bridge
If a gate fails, fix forward. Do not lower coverage thresholds, delete assertions, or exclude executable code to pass.
Phase 4 - Report
Write _workspace/coverage/wave-<date>.md with:
- starting and ending coverage summary;
- tests added and behaviors covered;
- commands run;
- PASS/FAIL/UNVERIFIED buckets;
- next suggested gaps from
_workspace/coverage/latest.md.
Test scenarios
- Normal flow: coverage harness identifies
src/cli/chat.ts; writer adds focused CLI behavior tests; lead runs coverage and gates; report includes delta. - Error flow: a new test exposes a production bug; report the failing behavior, patch the smallest safe code path, keep the regression test, and re-run gates.
Signals
- GitHub stars
- 41
- Forks
- 9
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
tdmcp-test-coverage- Source
- github.com/pantani/tdmcp