菜单
Break a plan or feature into vertical-slice GitHub issues. Each issue is a tracer bullet: independently deliverable, testable, and mergeable. Use when decomposing work from ROADMAP.md, a PRD, or a conversation.
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
| name | to-issues |
| description | Break a plan or feature into vertical-slice GitHub issues. Each issue is a tracer bullet: independently deliverable, testable, and mergeable. Use when decomposing work from ROADMAP.md, a PRD, or a conversation. |
Turn the current plan into a set of vertical-slice GitHub issues ready for implementation.
If the plan is vague, interview the user briefly (max 3 questions) to clarify scope and boundaries. Check ROADMAP.md and existing issues for overlap.
Each issue must be a tracer bullet: a thin vertical slice that:
Anti-pattern: Horizontal slices like "add all domain entities", "add all tests", "wire DI for everything". These delay feedback.
Number issues in implementation order. Earlier issues should unblock later ones. First issue should be the thinnest possible end-to-end path (the tracer bullet).
## Title
feat(scope): concise description
## Description
What this slice delivers and why it matters independently.
## Acceptance Criteria
- [ ] Criterion using Should/When language
- [ ] Tests pass: `{test command}`
- [ ] Lint passes: `{lint command}`
## Technical Notes
- Affected files/modules
- Key design decisions (reference ADRs if applicable)
- Dependencies on other issues (if any)
Show the full issue list as a numbered table before creating anything:
| # | Title | Scope | Depends On |
|---|-------|-------|------------|
| 1 | feat(sdk-dotnet): add ISecretProvider port | Domain | n/a |
| 2 | feat(sdk-dotnet): implement AWS SSM provider | Infra | #1 |
Wait for user confirmation. Then create issues via gh issue create.
needs-triage unless user specifies otherwiseWorkflow for investigating and reproducing bugs before fixing via TDD. Use when a bug report or GitHub issue is received. Covers issue fetching, root cause analysis, reproduction planning, and handoff to TDD cycle.
CRAP score quality gate for code complexity and test coverage. Use when reviewing methods for complexity risk, deciding whether to split methods, or determining minimum test coverage requirements.
Code smell detection and safe incremental refactoring patterns. Use when improving code structure, reducing technical debt, or cleaning up after a TDD cycle. Covers SOLID principles, smell catalog, and the propose-apply workflow.
Five independent analysis perspectives for code review: correctness, architecture, security, conventions, and complexity. Use when reviewing PRs, commits, or local changes. Includes severity model and output format.
Index of Architecture Decision Records (ADRs) for cross-cutting technical decisions. Use when making design choices, reviewing proposals for consistency with prior decisions, or onboarding to understand why specific tools or patterns were chosen. Covers test tooling, SDK architecture, code quality, and acceptance test infrastructure.
Git commit messages, PR workflow, and branching strategy using Conventional Commits and Semantic Versioning. Use when creating commits, pull requests, or managing Git workflow.