菜单
Use when something is broken, a test is failing, behavior is wrong, when investigating a production incident, when a user reports a bug, when a feature works locally but not in another environment, or when the system behaves differently than the contract specifies.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when implementing features or fixing bugs test-first, when user mentions "red-green-refactor", when test discipline is required for a specific task, when incremental-implementation needs TDD enforcement, or when a behavior change needs a failing test before any code is written.
Use when .forge/prd.md exists and the system needs a structural design before task breakdown, when modules will be implemented in parallel and need interface contracts to prevent integration failures, or when non-obvious technical decisions need to be recorded for future reference.
Use when .forge/prd.md and .forge/architecture.md exist and the work needs to be decomposed before implementation, when sizing tasks for a sprint, when mapping dependencies between modules, or when a critical path needs to be identified before parallel work begins.
Use when user wants to write a spec, create a PRD, or plan a new feature before implementation begins, when .forge/idea-brief.md exists and is ready to formalize, when requirements need to be captured before architecture or planning, or when a feature's scope and acceptance criteria need to be documented.
Use when creating a new forge-skill, editing an existing skill, when planning to contribute to forge-skills, when a session has produced a one-off prompt that should be promoted to a skill, or when verifying a skill works before deployment.
Use when checking if .forge/ artifacts are stale after a change to requirements, architecture, or any upstream artifact. Use before running /build, /review, or /ship to confirm the artifact chain is consistent. Use when the user says "is anything out of date" or "what needs to be regenerated".
| name | debugging-and-recovery |
| description | Use when something is broken, a test is failing, behavior is wrong, when investigating a production incident, when a user reports a bug, when a feature works locally but not in another environment, or when the system behaves differently than the contract specifies. |
Reproduce → localize → fix → guard. Never guess at root cause. The fix is not done until a regression test guards it. For bugs with GitHub issues, see triage-issue for the full investigation + issue creation flow.
tddspec-driven-developmentcode-review-and-quality| Thought | Reality |
|---|---|
| "I know what the bug is" | You think you do. Reproduce it first. |
| "I'll just try this fix and see" | Untested fixes introduce new bugs |
| "The root cause is obvious from the stack trace" | Stack traces show symptoms, not causes |
| "A unit test would be too hard to write for this" | Write an integration test — the behavior is observable |
| "The fix is one line, no test needed" | One-line bugs are re-introduced in one line |
Get the minimal reproduction: exact steps, inputs, environment. If you can't reproduce it, you don't understand it. Run the failing scenario manually or via test before writing any fix.
Before fixing:
RED: Write a test that reproduces the bug
→ The test must fail
→ If it passes, your reproduction is wrong
The test proves you understand the bug.
With a failing test, trace the code path:
git log -p <files>)Implement the smallest change that makes the failing test pass. Do not refactor adjacent code. Do not fix other bugs you notice. Do not add features.
Run the full test suite. Confirm:
If the bug was non-obvious: add a comment explaining WHY the fix is correct, not what it does. Consider whether the bug points to a missing contract invariant in .forge/contracts/.
.forge/contracts/ updated with the missing invariant