harrylee0412/review-gen/review-orchestrator
Claude Code and agent skill by harrylee0412/review-gen
- community
Checking that the SKILL.md file is still in the repository.
Coordinate long-running literature review projects across the search, planning, and writing subagents. Use when the user wants the system to decide the next stage, enforce plan approval before drafting, or manage the review workflow over time.
Install
npx vskill@latest install harrylee0412/review-gen/review-orchestratorSKILL.md
The same SKILL.md was published earlier as chanw-research/claude-code-paper-writing/review-orchestrator.
Review Orchestrator
Use this skill when the user wants the literature-review system to behave like a coordinated multi-agent workflow rather than a set of manually switched skills.
This skill acts as the controller for three subagents:
openalex-ajg-insightsfor literature collection and evidence preparationmanagement-review-plannerfor framework design and iterative plan refinementmanagement-review-writerfor prose drafting inside the approved framework
Core Principle
Keep the workflow file-based and transparent, but let the controller decide which subagent should act next.
Gatekeeping Rules
- Do not send the project to the writer until the user has explicitly approved the review plan in the conversation.
- After the user says the plan is approved, update the plan status through the orchestration script. Do not ask the user to manually edit the file.
- When the plan is approved or reopened, record that state and create a timestamped archive snapshot under
07_plan/history/. - When new literature is added after plan approval, preserve the existing framework by default.
- Only reopen the plan if the user explicitly asks to revise the framework.
Workflow
- Inspect the workspace state with
scripts/review_state_manager.py status. - Route to the correct subagent.
- If the user explicitly approves the plan, run
approve-plan. - If the user explicitly wants to revise the framework, run
reopen-planand return to the planner. - Keep all handoffs grounded in workspace files rather than ephemeral chat memory.
What To Ask The User
When a draft plan is ready, ask directly whether the framework should be frozen.
If the user says yes, run the approval command yourself.
Platform-Agnostic Quick Start
Use these placeholders on any operating system:
<workflow-python>: the Python interpreter that can run the orchestration script<review-gen-home>: the folder containing thereview-genpackage or its installed skills<review-workspace>: the target review workspace
After the user explicitly approves the framework:
References
Read only what is needed:
references/orchestration-rules.md
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/review-orchestrator/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/harrylee0412/review-gen/review-orchestrator)