一键导入
skill-orchestrator-patterns
Stage Cycle pattern and dispatch table for Orchestrator compression. Defines common Init→Review→Revision flow.
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。
菜单
Stage Cycle pattern and dispatch table for Orchestrator compression. Defines common Init→Review→Revision flow.
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 decomposing tasks into parallel sub-tasks or spawning sub-agents. Vendor-agnostic core; load a per-vendor reference for concrete tool names, directory conventions, and invocation syntax.
Use when performing Verification-Driven Development with adversarial approach. Actively challenge assumptions and find weak spots.
Use when performing VDD adversarial review with an opt-in sarcastic, provocative delivery style — a stylistic skin over vdd-adversarial mechanics (exhaustive reporting + objective bar).
Performance critic in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.
Use when performing OWASP security critique in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.
Use when performing security vulnerability assessment (OWASP, secrets, dependencies, IaC, LLM, API, MCP/agentic) or when "thinking like a hacker" to find exploits.
| name | skill-orchestrator-patterns |
| description | Stage Cycle pattern and dispatch table for Orchestrator compression. Defines common Init→Review→Revision flow. |
| version | 1 |
| tier | 2 |
This skill defines reusable patterns for the Orchestrator's pipeline stages, enabling compressed prompts.
[!IMPORTANT] Reference this skill for Stage Cycle logic. The Orchestrator uses these patterns instead of verbose per-scenario instructions.
| Stage | Agent Prompt | Reviewer Prompt | Max Cycles | Skill | Next Stage |
|---|---|---|---|---|---|
| Analysis | 02_analyst | 03_task_reviewer | 2 | skill-archive-task | Architecture |
| Architecture | 04_architect | 05_architecture_reviewer | 2 | architecture-design | Planning |
| Planning | 06_planner | 07_plan_reviewer | 2 (1 rev) | planning-decision-tree | Execution |
| Execution | 08_developer | 09_code_reviewer | 2 (1 fix) | developer-guidelines | Next Task / Completion |
INPUT: {stage_name}, {agent_prompt}, {artifact_path}
FLOW:
1. Read agent prompt
2. Pass required context to agent
3. Wait for result: { artifact_file, blocking_questions }
DECISION:
- IF blocking_questions → STOP, ask user (Scenario 14)
- ELSE → proceed to Review
INPUT: {artifact_file}, {reviewer_prompt}, {iteration}
FLOW:
1. Read reviewer prompt
2. Pass artifact + context to reviewer
3. Wait for result: { review_file, has_critical_issues }
DECISION TABLE:
| Condition | Action |
|-----------|--------|
| No issues | → Next Stage |
| Issues AND iteration < max | → Revision |
| Critical issues AND iteration = max | → STOP, ask user |
| Non-critical issues AND iteration = max | → Next Stage (with warning) |
INPUT: {review_file}, {original_artifact}, {agent_prompt}
INSTRUCTION TO AGENT:
"Fix comments from {review_file}. Do NOT change unrelated parts. Preserve structure."
FLOW:
1. Pass review + original to agent
2. Wait for updated artifact
3. Return to Review Phase (+1 iteration)
artifact_file: "path/to/artifact.md"
blocking_questions: [] # Empty = proceed
review_file: "path/to/review.md"
has_critical_issues: true/false
modified_files: [...]
new_files: [...]
test_report: "tests/tests-{ID}/test-{ID}-{slug}.md"
documentation_updated: true
open_questions: [] # Treated as blocking_questions
plan_file: "path/to/plan.md"
task_files: ["path/to/task1.md", ...]
blocking_questions: []
review_file: "path/to/plan_review.md"
has_critical_issues: true/false
comments_count: number
coverage_issues: [...]
missing_descriptions: [...]
Structured footer (control-flow + status). The prose review report — three pillars plus the "Verified" block — is passed to the developer as the report body; it is NOT a structured key.
review_status: "APPROVED | REJECTED"
has_critical_issues: true/false # sole control-flow key (see DECISION TABLE)
e2e_tests_pass: true/false
stubs_replaced: true/false
No reviewer. Unique flow:
docs/TASK.md (via skill-archive-task)Immediate pause. Flow:
skill-archive-task protocol before creating new TASKtask_files[], coverage_issues[], missing_descriptions[]