メニュー
Write tests to reach a coverage target. Uses 4 agents (analyzer, writer, checker, fixer) to iteratively generate and fix tests. Exits non-zero with explanation if production code needs changes.
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
Use this when you need a complete interactive report as a single HTML file with zero install dependencies — covers charts, tables, diagrams, math, KPIs, and prose out of the box.
Use this as the default toolset for coding sessions when you want faster navigation, search, file inspection, and git workflow execution with lower command overhead: tools: - fzf - ripgrep - bat - delta - lazygit - starship - zoxide - eza - atuin - yazi
Out-of-band codebase exploration using a cheap/fast model. Keeps your context clean while a cheap model runs 30-80 commands in parallel. Tunable precision and output size - works for broad orientation or precise targeted questions.
Deterministically fixes broken OpenAI Deep Research markdown citations without using an LLM: creates a .bkp backup, rewrites citation markers, rebuilds references, and runs strict regex validation.
Explore a codebase to gather context for coding tasks. Preserves context window and offloads work to cheaper models.
Dynamically generate and execute a specialized agent for any task. Use when the user has an arbitrary task that would benefit from a custom-generated agent.
| name | test-writer |
| description | Write tests to reach a coverage target. Uses 4 agents (analyzer, writer, checker, fixer) to iteratively generate and fix tests. Exits non-zero with explanation if production code needs changes. |
Run to generate tests for a Python file or project:
~/.agents/skills/test-writer/run.sh "<target>"
| Option | Description | Default |
|---|---|---|
--target=N | Coverage percentage to reach | 80 |
--max-rounds=N | Max test generation rounds | 3 |
# Cover a specific file to 80%
run.sh src/mymodule.py
# Cover entire project to 90%
run.sh --target=90 .
# Cover specific file to 95%
run.sh --target=95 src/utils.py
| Code | Meaning |
|---|---|
| 0 | Success - coverage target met |
| 1 | Production code likely has a bug (explanation provided) |
| 2 | Max iterations reached, tests still failing |