orchestration
Skill20 starsChanged 44 days agoMITView on GitHub
Orchestrate a workflow with subagents
47 other projects use a version of this.
Adopted by
Most recently taken up by
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
- Hive-Academy/PtahCodetheir own version, first seen Nov 8, 2026
- delorenj/skillstheir own version, first seen Nov 7, 2026
- Hive-Academy/ptah-extensiontheir own version, first seen Nov 3, 2026
- webdevarif/claude-skillstheir own version, first seen Nov 1, 2026
- jgeofil/agent-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use orca-cli, orca-per-workspace-env and 8 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.
HK-hubSkillorca-cli
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
Also in 5 projects that use this
stablyaiSkillorca-per-workspace-env
Set up, review, debug, or validate an Orca per-workspace environment recipe: the on-demand, disposable runtime (cloud sandbox, VM, SSH host, or local container) Orca creates fresh for each workspace. Use to stand up a new recipe end to end, fix an `environmentRecipes` entry in `orca.yaml`, scaffold provider lifecycle scripts, or resolve an `orca vm recipe doctor` failure. Use `orca-cli` for ordinary worktree and workspace creation with no recipe involved.
Also in 3 projects that use this
- HK-hubSkill
computer-use
Use Orca's computer-use CLI to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions. Use for desktop app interaction: list apps/windows, get app state, read visible UI, click controls, type, press keys, scroll, drag, set values, or perform accessibility actions. Also use for browser windows, webviews, Orca app UI, or other desktop UI. Triggers include "computer use", "orca computer", "read Spotify", "read Slack", "control/click/read in a desktop app", and "get app state".
Also in 6 projects that use this
kongyo2Skillprompt-engineering
Comprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. This skill should be used when users request prompt creation, optimization, or improvement for any LLM task, or when users need help translating vague requirements into effective prompts through collaborative dialogue and iterative refinement.
Also in 3 projects that use this
GoogleSkillcodebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Also in 4 projects that use this
MicrosoftSkillpr-review
Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode. Use when reviewing a docs PR for factual correctness: setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.
Also in 3 projects that use this
Other versions47 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 47
- stablyai/orca★ 119ksame name
- BankrBot/openclaw-skills★ 1.2ksame name
- BankrBot/skills★ 1.2ksame name
- AThevon/genjutsu★ 758same name
- moasq/production-saas-starter★ 532same name
- bam-bam-2/solo-skills★ 366same name
- austintgriffith/ethskills★ 303same name
- PaulRBerg/agent-skills★ 104same name
- geekatron/jerry★ 37same name
- Hive-Academy/ptah-extension★ 34same name
37 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 repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- breakdownSkill
- bug-investigationSkill
- code-review-adversarialSkill
- code-review-multiSkill
- code-review-with-followupSkill
- document-changesSkill
- grillingSkill
- type-test-codeSkill
- explain-changesSkill
- github-actions-ciSkill
- github-appSkill
- github-ticketsSkill
- implementation-planSkill
- implement-simpleSkill
- implementSkill
- implement-ttcSkill
- pull-requestSkill
- review-and-wrap-upSkill
- verusSkill
- specSkill
- ticketsSkill
- update-working-copySkill
- verifySkill
- wrap-upSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 42 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Do not perform the subagent duties inline or spend time develop your own detailed understanding.
- Distinctive: line 25
Start every delegation without inherited conversation history using the mpty-context option on the platform.
- Distinctive: line 27
Do not paste the conversation transcript into the delegation prompt.
- Distinctive: line 29
Always run subagents without blocking- this makes it possible to monitor them.
- Distinctive: line 40
If a specific agent (and any listed fallabacks) are unavailable for delegation, stop and ask the user how to proceed.
“Common” is measured: kept by at least 6 in 10 of the 42 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
Orchestration
Your job is to orchestrate subagents through implementation according to this skill. Do not perform the subagent duties inline or spend time develop your own detailed understanding. You may need to do checks/verifications of agent handoffs.
Artifacts should be passed between sub-agents so they start with a summary of all useful information from other sub-agents: this minimizes re-exploration. Create a task-scoped temporary directory outside the repository. Do not commit its contents. Pass absolute artifact paths between agents.
Instruct agents to edit artifacts incrementally- that way if an agent's session ends prematurely more information is persisted.
Start every delegation without inherited conversation history using the mpty-context option on the platform. Give the sub-agent only its requested action and the artifact or source paths it needs. Do not paste the conversation transcript into the delegation prompt.
Always run subagents without blocking- this makes it possible to monitor them. Reconcile every subagent to see if they are stuck, completed, or running and also to check on their token usage. File mtime is the most reliable liveness signal. Ask agents to update an artifact file at least every 15 minutes. Investigate for additional liveness signals (mtime of non-artifact files, e2e tests running, etc) before assuming the agent is not running. Reconcile at least every 15 minutes- don't wait for a notification without a deadline. Arm ONE recurring timer BEFORE the first delegation, and keep it armed until the last subagent is reconciled to completion.
A subagent should compact after 200k tokens regardless of its total limit. Compaction is accomplished by restarting the agent. When the subagent gets over 150k tokens, tell it to find a convenient stopping point and checkpoint information in the standard artifact files and to write out any additional files that will be helpful to re-read on restart. Restart the agent with instructions to read these files and continue its work.
If a specific agent (and any listed fallabacks) are unavailable for delegation, stop and ask the user how to proceed.
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.