菜单
Estimate task complexity and route high-complexity tasks (>=80%) to deep architectural review - use before plan generation
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 multiple Claude agents to investigate and fix independent problems concurrently
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas.
Synthesize a Claude Code /goal condition from AA-MA plan artifacts. Produces a falsifiable condition referencing observable artifacts (provenance.log, tasks.md, git tags, test exit codes) plus a turn cap derived from plan effort. Owns the canonical verdict-token enum, observable-artifact list, hashing contract, and turn-cap formula. Used by /execute-aa-ma-full §2.5 and /verify-plan --iterate.
Use when executing tasks from AA-MA artifacts - handles step/milestone/full execution with proper context injection, validation, and provenance logging. Proactively use when detecting .claude/dev/active/ directories or when user asks to continue/resume work.
Use when planning complex multi-step tasks, creating AA-MA artifacts, or transitioning from ad-hoc to structured development - transforms rough ideas into executable plans through 5-phase workflow with integrated skills and validation gates
Post-impl adversarial review symmetric to /verify-plan. Dispatches up to 5 parallel audit agents (code-reviewer, security-auditor, tdd-sequence-auditor, context7-evidence-auditor, future-proofing-auditor) based on the milestone's plan-declared Audit-Profile. CRITICAL findings surface via AskUserQuestion accept/dispute/defer panel before §7.3 user authorization. Introduced in v0.8.0 per ADR-0005. Invoked by Phase 6.8 of /execute-aa-ma-milestone.
| name | complexity-router |
| description | Estimate task complexity and route high-complexity tasks (>=80%) to deep architectural review - use before plan generation |
Estimates task complexity using a weighted factor algorithm and routes high-complexity tasks (≥80%) to deep architectural review (human review, ultrathinking, or a dedicated architecture skill if available).
| Factor | Weight | Description |
|---|---|---|
| Scope | 25% | Number of files/components affected |
| Architectural Impact | 25% | Level of system changes |
| Technical Risk | 20% | Unknowns and technical uncertainty |
| Dependencies | 15% | External service/library count |
| Uncertainty | 15% | Requirements ambiguity |
1-3 files: 0-20
4-10 files: 21-40
11-20 files: 41-60
21-50 files: 61-80
50+ files: 81-100
No architecture changes: 0-20
Single component changes: 21-40
Multiple component changes: 41-60
Cross-service changes: 61-80
System-wide changes: 81-100
Well-understood domain: 0-20
Minor unknowns: 21-40
Moderate unknowns: 41-60
Significant unknowns: 61-80
High uncertainty/new tech: 81-100
No external dependencies: 0-20
1-2 dependencies: 21-40
3-5 dependencies: 41-60
6-10 dependencies: 61-80
10+ dependencies: 81-100
Clear requirements: 0-20
Minor ambiguity: 21-40
Moderate ambiguity: 41-60
Significant ambiguity: 61-80
High ambiguity: 81-100
Complexity = (Scope × 0.25) + (ArchImpact × 0.25) +
(TechRisk × 0.20) + (Deps × 0.15) +
(Uncertainty × 0.15)
| Complexity | Category | Routing Action |
|---|---|---|
| 0-29% | Low | Standard workflow, minimal review |
| 30-59% | Medium | Standard workflow with validation |
| 60-79% | High | Enhanced validation, flag in plan |
| 80-100% | Critical | Deep architectural review (human or dedicated skill) |
The following automatically set complexity ≥80%:
From Phase 2-3 outputs:
Rate each factor on 0-100 scale:
Scope: [__]/100
Arch Impact: [__]/100
Tech Risk: [__]/100
Dependencies: [__]/100
Uncertainty: [__]/100
Scan for automatic high-complexity indicators:
Auto-Triggers Found:
- [ ] [Trigger 1]
- [ ] [Trigger 2]
If any trigger found: Complexity = max(calculated, 80)
Calculated Complexity: [X]%
Auto-Trigger Override: [Yes/No]
Final Complexity: [X]%
Routing Decision: [Standard / Enhanced / Senior-Architect]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
COMPLEXITY ASSESSMENT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Task: [task-name]
Date: [YYYY-MM-DD]
FACTOR SCORES:
Scope: [XX]/100 (weight: 25%)
Architectural: [XX]/100 (weight: 25%)
Technical Risk: [XX]/100 (weight: 20%)
Dependencies: [XX]/100 (weight: 15%)
Uncertainty: [XX]/100 (weight: 15%)
──────────────────────────────────
WEIGHTED TOTAL: [XX]%
AUTO-TRIGGERS:
[✓/✗] [Trigger description]
[✓/✗] [Trigger description]
FINAL COMPLEXITY: [XX]% ([Low/Medium/High/Critical])
ROUTING DECISION: [Action]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
This skill is invoked at the start of Phase 4:
When using this skill: