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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/diegosouzapw/awesome-omni-skill --skill spec-review命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.
AshAi extension guidelines for integrating AI capabilities with Ash Framework. Use when implementing vectorization/embeddings, exposing Ash actions as LLM tools, creating prompt-backed actions, or setting up MCP servers. Covers semantic search, LangChain integration, and structured outputs.
This skill should be used when solving hard questions, complex architectural problems, or debugging issues that benefit from GPT-5 Pro or GPT-5.1 thinking models with large file context. Use when standard Claude analysis needs deeper reasoning or extended context windows.
正在显示 SKILL.md
基于 SOC 职业分类
| name | spec-review |
| description | How to verify implementation against OpenSpec artifacts |
Guide for verifying that implementation matches spec artifacts.
| File | Required | Purpose |
|---|---|---|
{specs_path}/design.md | Yes | Requirements and scenarios to verify |
{specs_path}/tasks.md | Yes | Completion checklist |
{specs_path}/proposal.md | Optional | Original intent reference |
Question: Are all tasks done and all requirements covered?
| Check | Method | Issue Level |
|---|---|---|
All checkboxes marked [x] | Parse tasks.md | CRITICAL if incomplete |
| All requirements have code | Search codebase for keywords | CRITICAL if missing |
| All new files exist | Verify file paths from tasks | CRITICAL if missing |
Question: Does the code do what the spec says?
| Check | Method | Issue Level |
|---|---|---|
| GIVEN/WHEN/THEN satisfied | Trace scenario through code | WARNING if divergent |
| Tests cover scenarios | Match test names to scenarios | WARNING if uncovered |
| Edge cases handled | Check error paths in code | WARNING if missing |
| Validation commands pass | Run pytest / npm run validate | CRITICAL if failing |
Question: Does the code match design decisions?
| Check | Method | Issue Level |
|---|---|---|
| Design decisions followed | Compare Decisions section to code | WARNING if violated |
| Patterns consistent | Check naming, structure, style | SUGGESTION |
| No undocumented changes | Diff scope vs design scope | WARNING if extra |
| No design deviations | Cross-reference architecture | WARNING if different |
## Verification Report
### Summary
| Dimension | Status |
|--------------|---------------------|
| Completeness | X/Y tasks, N reqs |
| Correctness | M/N scenarios pass |
| Coherence | Followed / N issues |
### Critical Issues
| # | Dimension | Issue | File | Recommendation |
|---|-----------|-------|------|----------------|
| 1 | Completeness | Task 2.3 incomplete | - | Complete or mark blocked |
### Warnings
| # | Dimension | Issue | File | Recommendation |
|---|-----------|-------|------|----------------|
| 1 | Correctness | Scenario X not tested | test_foo.py | Add test case |
### Suggestions
- [Pattern deviation details with file reference]
### Assessment
[CRITICAL: N issues | WARNINGS: N | Ready for archive: Yes/No]
| Available Artifacts | Checks Performed |
|---|---|
| tasks.md only | Completeness (checkboxes) only |
| tasks.md + design.md | Completeness + Correctness |
| All three | All three dimensions |
Always note which checks were skipped and why.