orchestrator
Skill1 starsChanged 40 days agoMITView on GitHub
Orchestrates implementation, review, and user-path verification of phase plans via subagents. Use when given a phase MD file to complete.
80 other projects use a version of this.
Adopted by
Most recently taken up by
- BrightGold70/skillstheir own version, first seen Nov 8, 2026
- Veeiy/agent-skillstheir own version, first seen Nov 8, 2026
- Mehul72/skillstheir own version, first seen Nov 8, 2026
- pietz/skillstheir own version, first seen Nov 8, 2026
- kcns008/cluster-skillstheir own version, first seen Nov 8, 2026
- soilmass/motion-design-agenttheir own version, first seen Nov 8, 2026
Used with
Projects with it also use worker, reviewer and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
stotihvSkillworker
Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.
Also in 3 projects that use this
MicrosoftSkillreviewer
ASP.NET Core ハンドブックの記事をレビューする。Use when: 記事をレビューする、ドキュメントを校正する、コードレビューする、PRをレビューする。技術ドキュメントのレビュー、品質チェック、校正。
Also in 4 projects that use this
am-willSkillplanner
Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.
Also in 4 projects that use this
yakatotechSkilladvisor
Provide improvement suggestions and advice on work content. Use for document review, efficiency suggestions, and best practices
Also in 3 projects that use this
AWSSkillplanning
Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.
Also in 3 projects that use this
OpenAISkillobservability
Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.
Also in 3 projects that use this
Other versions80 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 80
- nubjs/nub★ 4.4ksame name
- SirAllap/agentglass★ 347same name
- DylXBT/claude-orchestrator-skills★ 114same name
- nwiizo/claudelytics★ 88same name
- nahisaho/MUSUBI★ 74same name
- olivieropinotti/orchestrator-skill★ 70same name
- sanky369/vibe-building-skills★ 30same name
- felvieira/claude-skills-fv★ 27same name
- robertbstillwell/marketing-skills★ 26same name
- kcns008/cluster-agent-swarm-skills★ 25same name
70 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository38 other files it gives its agents.
- agent-conductSkill
- bugfixSkill
- code-smellsSkill
- deliverSkill
- final-responseSkill
- frontend-designSkill
- go-conventionsSkill
- go-implementorSkill
- go-reviewerSkill
- go-test-strengthSkill
- implementation-principlesSkill
- nextflow-conventionsSkill
- nextflow-implementorSkill
- nextflow-reviewerSkill
- nextjs-fastapi-conventionsSkill
- nextjs-fastapi-implementorSkill
- nextjs-fastapi-reviewerSkill
- phase-creatorSkill
- phase-reviewerSkill
- prose-principlesSkill
- pr-resolverSkill
- pr-reviewerSkill
- python-conventionsSkill
- python-implementorSkill
- python-reviewerSkill
- spec-authorSkill
- spec-proofreaderSkill
- spec-reviewerSkill
- spec-writerSkill
- subagentsSkill
- swift-conventionsSkill
- swift-implementorSkill
- swift-reviewerSkill
- testing-principlesSkill
- tightenSkill
- unslopSkill
- verificationSkill
- writing-for-agentsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 10 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 66 edited versions we read keep these.
10
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Read and follow agent-conduct, testing-principles, and subagents before starting.
- Distinctive: line 16
Use skills named in the phase file's Instructions section if specified.
- Distinctive: line 45
testing-principles: Run tests and linters."
- Very specific: line 73
When every checkbox is checked and every required drive is VERIFIED, commit with Implement phase <N>.
- Distinctive: line 90
Follow fix-and-commit cycle.
- Distinctive: line 100
After all requested phases and required reviews succeed, apply queue completion.
- Very specific: line 109
File removal: delete normally. If deletion fails (e.g.
- Distinctive: line 114
Do NOT relaunch the implementor to "find a way".
- Very specific: line 116
Write blocker-phase<N>-<item-id>.md next to the phase file, containing: the item, the impossibility (what was tried, what failed and why), …
- Distinctive: line 127
Follow the rules in subagents (no direct implementation, no read-only agents for writing work, etc.).
- Distinctive: line 129
NEVER check a checkbox until the subagent confirms success.
- Distinctive: line 130
NEVER skip or reorder items unless the phase file allows parallel execution.
- Distinctive: line 131
Follow agent-conduct Git Safety for push authorization, rebasing feature branches on the resolved base, and force-pushing with a lease.
“Common” is measured: kept by at least 6 in 10 of the 66 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Orchestrator Skill
Read and follow agent-conduct, testing-principles, and subagents before starting. subagents owns delegation: agent choice, briefing, skill discovery, and error handling. This skill covers only the orchestrator procedure. Establish the outermost queue owner using bugfix routing before starting; inherit a caller's owner when nested. Route incidental findings returned by implementation, review, and verification before resuming phase work.
Use skills named in the phase file's Instructions section if specified; otherwise follow the skill-discovery procedure in subagents.
Input
A phase MD file containing items with - [ ] implemented and
- [ ] reviewed checkboxes, possibly grouped into ordered batches.
Procedure
1. Read the phase file. Note which items are already checked (skip those).
2. Process items in order
- Sequential items: one at a time.
- Parallel batch: apply shared concurrency limits.
- Complete and review each batch before starting the next.
3. For each item (or batch)
a. Implementation
Launch an implementor subagent with:
- Conventions, testing-principles, and implementor skill names + file paths (to read).
- Item description, spec.md section reference, phase instructions.
- "Read spec.md for acceptance tests. Follow TDD cycle and testing-principles. Run tests and linters."
On success, check - [x] implemented.
b. Review
Launch a reviewer subagent with:
- Conventions, testing-principles, and reviewer skill names + file paths (to read).
- Item(s) description, spec.md section reference(s), phase instructions.
- "You have clean context. Read spec.md, source and test files, run tests and linter, return PASS or FAIL with specific feedback."
PASS: check - [x] reviewed.
FAIL: launch new implementor with feedback, then fresh reviewer. Repeat
until PASS.
4. Verify user-visible behaviour
Apply
user-path verification.
Delegate required drives with the verification skill path and affected
features. Keep affected reviewed markers unchecked until VERIFIED; follow
verification's failure handling before resuming.
5. Phase completion
When every checkbox is checked and every required drive is VERIFIED, commit
with Implement phase <N>. Use targeted git add <path> for every changed
path that belongs to the phase, including the phase file. Inspect the staged
diff before committing to confirm it contains the complete phase and no
unrelated changes.
Cite the retained verification evidence in your report.
6. Spec-aware PR review (after all phases)
Launch a pr-reviewer subagent with:
- pr-reviewer skill name + file path.
- Path to spec document.
- "Review all changes on this branch vs base. Check code quality, bugs, usability, and spec conformance. Fix via implementor subagents."
Follow fix-and-commit cycle. Repeat with fresh context until 2 consecutive clean passes.
7. Spec-free PR review
Same as step 6 but without the spec document (focus on code quality and usability only). Repeat until 2 consecutive clean passes.
8. Complete or return to caller
After all requested phases and required reviews succeed, apply queue completion. Nested workflows return pending references without processing them. Only the outermost owner drains deferred branches. Report pending references with any blocker or stopped phase.
Error Handling
- Transient failures: see subagents.
- File removal: delete normally. If deletion fails (e.g. NFS refusing
the unlink), move the file to
.tmp/trash/in the repo instead; clean up after all phases. - Blocker reported by subagent (per agent-conduct § Honesty About
Blockers - e.g. an external API cannot do what the spec requires):
- Do NOT relaunch the implementor to "find a way". Do NOT check the item.
- Write
blocker-phase<N>-<item-id>.mdnext to the phase file, containing: the item, the impossibility (what was tried, what failed and why), and 1-3 proposed alternatives or clarifications needed from the user. - Abort the current phase and any later phases that depend on the blocked item. Continue only with independent phases.
- At the end, report all blocker files and which phases were skipped.
Rules
- Follow the rules in subagents (no direct implementation, no read-only agents for writing work, etc.).
- NEVER check a checkbox until the subagent confirms success.
- NEVER skip or reorder items unless the phase file allows parallel execution.
- Follow agent-conduct Git Safety for push authorization, rebasing feature branches on the resolved base, and force-pushing with a lease.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

