coordinate
Skill189 starsChanged 7 months agoMITView on GitHub
Coordinate focused Luna helpers for bounded work and Astra advisers for difficult design questions while doing the main work yourself.
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Do the main work yourself, using Luna for scouting or bounded tasks and Astra for advice.
- Very specific: line 20
Start helpers with collaboration.spawn_agent, fork_turns: "none", the chosen model, and reasoning_effort: "high".
- Distinctive: line 22
Ask helpers to report only to you, with updates that unblock work or change the plan.
- Distinctive: line 26
When the user adds follow-up guidance, keep a compact worklog file of the goal, current instructions, assignments, decisions, and completed …
“Common” is measured: kept by at least 6 in 10 of the 11 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
Coordinate
Do the main work yourself, using Luna for scouting or bounded tasks and Astra for advice. Keep small tasks and narrow lookups local. Delegate only when a concrete assignment saves enough time to justify coordination and you can continue useful independent work.
Luna: gpt-6-luna, high
Use Luna for well-defined work or substantial investigations that require synthesizing information across sources. For scouting, give it a concrete question and sources; ask for concise findings with evidence. Use the findings directly and send gaps back to Luna instead of repeating its reads or searches. For changes, specify the owned files, expected behavior, and relevant checks; have Luna implement and verify them. Tell Luna not to spawn agents.
Astra: gpt-6-astra, high
Consult Astra when the approach is unclear, repeated attempts fail, or the task needs cross-cutting design or aesthetic judgment. Share the question, relevant findings, constraints, and what you have tried. Request advice, then use its guidance to continue implementation. Tell Astra not to spawn agents.
Coordinate
Start helpers with collaboration.spawn_agent, fork_turns: "none", the chosen model, and reasoning_effort: "high". Give them their assignment and the context needed to complete it, including scope and permitted side effects. Assign disjoint files when helpers make changes concurrently.
Ask helpers to report only to you, with updates that unblock work or change the plan; otherwise report on completion. Relay dependencies between helpers. Continue independent work while they run.
When blocked on helper results, use collaboration.wait_agent with timeout_ms: 60000. Answer questions or resolve blockers they raise, then resume waiting as needed. After a quiet timeout, wait again without status pings or transcript polling. Keep the user informed at the cadence required by the session. Review helpers' evidence and changes before integrating their work.
When the user adds follow-up guidance, keep a compact worklog file of the goal, current instructions, assignments, decisions, and completed work. Update entries in place; consult it after compaction or handoff.
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- first-fluke/fullstack-starter★ 223same name
- jsboige/CoursIA★ 17same name
- bftelman/skills★ 2same name
- gao-xh/multi-agent-protocol★ 2same name
- leosimini/keelokit★ 2same name
- revealui-studio/revskills★ 2same name
- RevealUIStudio/revskills★ 2same name
- combinaut/ai-agent-orchestration★ 1same name
- ryanportfolio/Harness-Firmware★ 1same name
- wilanis/wilanis-js★ 1same name
2 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 repository101 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accelevents-apiSkill
- accelevents-speaker-syncSkill
- agents-sdkSkill
- ai-devblogSkill
- ai-engineeringSkill
- ai-readmeSkill
- align-meSkill
- annotated-video-productionSkill
- antislop-codebaseSkill
- app-ux-paradigmsSkill
- autoreviewSkill
- babysit-runsSkill
- blog-system-designSkill
- cassandra-creatorSkill
- ceo-creatorSkill
- claude-session-introspectSkill
- cli-uxSkill
- cloudflare-do-turn-based-multiplayerSkill
- cloudflare-email-serviceSkill
- cloudflare-one-migrationsSkill
- cloudflare-oneSkill
- cloudflare-production-builderSkill
- cloudflareSkill
- conference-developer-endpointsSkill
- conference-transcribeSkill
- data-chatbotsSkill
- data-visualization-qualitySkill
- deep-trajectory-analysisSkill
- design-apps-with-imagegenSkill
- design-preferencesSkill
- diy-netlifySkill
- download-videoSkill
- download-x-videoSkill
- durable-objectsSkill
- europe-developer-apiSkill
- face-matchingSkill
- forgeSkill
- future-onlySkill
- generalizeSkill
- gsuite-setupSkill
- keep-it-simpleSkill
- latent-space-thumbnail-directorSkill
- live-ai-pipelinesSkill
- location-inputSkill
- long-running-operation-uxSkill
- media-heavy-workflowsSkill
- media-to-wiki-pipelineSkill
- media-transformSkill
- mobile-nativeSkill
- mobile-webapp-uxSkill
- multimodal-extractionSkill
- new-mac-setupSkill
- next-stepsSkill
- observability-hardeningSkill
- person-profile-writingSkill
- podcast-publishing-assistantSkill
- productionize-app-with-servicesSkill
- programmatic-agentsSkill
- provision-model-keysSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

