本文へ移動
cccskills
無料GitHub で公開

tdmcp-coverage-writer

Write focused tdmcp tests for one assigned coverage gap. Use for Vitest/msw unit tests, integration tests, bridge tests, CLI/config/resource tests, and regression tests that should raise coverage without weakening behavior.

hybridlabor-api/aos
インストール方法を見る

含まれるファイル（1）

  • SKILL.md1.5 KB

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

tdmcp-coverage-writer

Use this skill when assigned a specific coverage gap.

Workflow

  1. Read the target implementation and the closest existing tests.
  2. Identify the behavior or branch that is currently untested.
  3. Add the smallest test that would fail if that behavior regressed.
  4. Use existing helpers such as tests/helpers/tdMock.ts, KnowledgeBase, RecipeLibrary, and silentLogger instead of inventing new scaffolding.
  5. Run the narrow test and fix any real failure.

Assertions to prefer

  • Real return text/JSON blocks from CallToolResult.
  • Bridge request bodies captured by msw.
  • Friendly isError results instead of thrown handler errors.
  • CLI stdout/stderr and exit status for user-facing commands.
  • Resource URI and payload shape consumed by MCP clients.

Avoid

  • Tests that only import a module to mark lines covered.
  • Broad snapshots where a specific behavior assertion would do.
  • New exclusions in coverage config.
  • Rewriting production code unless the test exposes a real bug and the lead asked you to patch it.

Output

Report the changed files, command run, behavior covered, and any remaining branch or live-TD validation that is still unverified.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

ログインしてレビューを書く

同じリポジトリのスキル

概要と使いどころ

agent-manager-skill

無料

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

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

agent-memory-mcp

無料

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

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

agent-pipeline

無料

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.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

agent-tool-builder

無料

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.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

agentic-harness-patterns

無料

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

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

agenttrail

無料

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.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

hybridlabor-api のスキルをすべて見る

このスキルの問題を報告する