跳到正文
cccskills
免费在 GitHub 公开

tdmcp-test-coverage

Orchestrate 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.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

tdmcp-test-coverage

Use this skill for coverage-improvement work in this repository. The goal is more tested behavior, not prettier percentages.

Phase 0 - Context

  1. Read AGENTS.md, package.json, vitest.config.ts, and the nearest tests.
  2. Run npm run coverage:harness unless the user asked for a static-only pass.
  3. Read _workspace/coverage/latest.md.
  4. 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 isError paths 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.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

查看 hybridlabor-api 的全部技能

报告此技能的问题