菜单
This skill MUST be invoked when the user says "review spec", "find gaps", "what's missing", or "clarify requirements". SHOULD also invoke when reviewing spec.md for completeness. Focuses on product decisions and generates clarifying questions with concrete options.
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 | analysis-specifications |
| description | This skill MUST be invoked when the user says "review spec", "find gaps", "what's missing", or "clarify requirements". SHOULD also invoke when reviewing spec.md for completeness. Focuses on product decisions and generates clarifying questions with concrete options. |
Find gaps in specifications and generate clarifying questions that a product owner or stakeholder can answer. Focus on WHAT is missing, not HOW to implement.
humaninloop:authoring-requirements firstAsk product questions, not implementation questions.
| Wrong (Technical) | Right (Product) |
|---|---|
| "What happens if the database connection fails?" | "What should users see if the system is temporarily unavailable?" |
| "Should we use optimistic or pessimistic locking?" | "Can two users edit the same item simultaneously?" |
| "What's the retry policy for failed API calls?" | "How long should users wait before seeing an error?" |
| "What HTTP status code for invalid input?" | "What message should users see for invalid input?" |
Every question must be framed as a decision the stakeholder can make:
**Question**: [Clear product decision]
**Options**:
1. [Concrete choice] - [What this means for users]
2. [Concrete choice] - [What this means for users]
3. [Concrete choice] - [What this means for users]
**Why this matters**: [User or business impact]
Focus on these user-facing gaps:
| Category | Example Questions |
|---|---|
| User expectations | "What should users see when...?" |
| Business rules | "Is X allowed? Under what conditions?" |
| Scope boundaries | "Is Y in scope for this feature?" |
| Success/failure states | "What happens if the user...?" |
| Permissions | "Who can do X? Who cannot?" |
These are valid concerns but belong in the planning phase, not specification.
| Severity | Definition | Action |
|---|---|---|
| Critical | Cannot build without this answer | Must ask now |
| Important | Will cause rework if not clarified | Should ask now |
| Minor | Polish issue, can defer | Log and continue |
## Gaps Found
### Critical
- **Gap**: [What's missing]
- **Question**: [Product decision needed]
- **Options**: [2-3 choices]
### Important
- **Gap**: [What's missing]
- **Question**: [Product decision needed]
- **Options**: [2-3 choices]
### Minor (Deferred)
- [Gap description] - can be resolved during planning
Before finalizing the review, verify:
❌ "What retry policy should we use?" ✅ "How long should users wait before seeing an error?"
❌ "What about errors?" ✅ "What message should users see when payment fails?"
❌ "How should we handle this case?" ✅ "Options: (1) Show warning and continue, (2) Block action, (3) Ask for confirmation"
❌ Presenting 20+ gaps to stakeholders ✅ Limit to 5-7 critical/important gaps per review round
❌ Just listing the gap without context ✅ Explain user or business impact for each question
❌ "Should we cache this data?" (assumes caching) ✅ "How quickly should users see updated data?"
❌ Adding new features as "missing requirements" ✅ Only clarify scope of existing features
❌ Asking questions already answered elsewhere ✅ Reference existing patterns and decisions before asking
This skill MUST be invoked when the user says "implementation strategy", "cycle sequencing", or "implement workflow patterns". SHOULD also invoke when user mentions "execute-then-verify", "targeted retry", "fix pass", or "implementation escalation". Provides implementation-workflow patterns consumed alongside strategy-core for targeted briefings.
This skill MUST be invoked when the user says "audit agent", "review agent", "check agent compliance", or "agent audit checklist". SHOULD also invoke when user mentions "AGENT-GUIDELINES compliance", "agent review", or "coupling detection". Provides the procedural framework for auditing agents against AGENT-GUIDELINES.md.
This skill MUST be invoked when the user says "execute cycle", "implement tasks", "TDD cycle", or "red green refactor". SHOULD also invoke when implementing cycle task lists, encountering `[EXTEND]`/`[MODIFY]` markers, generating cycle reports, or handling retry after checkpoint failure.
This skill MUST be invoked when the user says "create task mapping", "structure implementation", "define cycles", "vertical slice", "TDD", "test first", "cycle structure", or "testable increment". SHOULD also invoke when user mentions "red green refactor" or "implementation tasks".
This skill MUST be invoked when the user says "TEST:", "TEST:VERIFY", "TEST:CONTRACT", "execute verification", "run test task", or "verification test". SHOULD also invoke when the user says "Setup/Action/Assert", "verify against infrastructure", or "capture evidence".
This skill MUST be invoked when the user says "write technical requirements", "define constraints", "define NFRs", "map integrations", "classify data sensitivity", or "infrastructure requirements". SHOULD also invoke when user mentions "TR-", "C-", "NFR-", "IP-", "INT-", "DS-", "non-functional", "system integration", "infrastructure provisioning", or "data classification". Produces three traceable analysis artifacts from business specifications.