coordinator-communication
Skill1 starsChanged 59 days agoMITView on GitHub
Explain current evidence, assumptions and user questions clearly.
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- content-safetySkill
- context-compactionSkill
- cortex-controlSkill
- design-frontend-designSkill
- design-impeccableSkill
- design-reference-analysisSkill
- design-ui-ux-pro-maxSkill
- design-visual-qaSkill
- design-workflowSkill
- documentation-syncSkill
- knowledge-harvest-scopeSkill
- knowledge-harvestSkill
- orchestratorSkill
- requirements-intakeSkill
- skill-authoringSkill
- skill-managementSkill
- tool-disciplineSkill
- tool-discipline-workerSkill
- worker-accessibility-auditorSkill
- worker-accessibility-fixerSkill
- worker-architectSkill
- worker-backend-devSkill
- worker-build-verificationSkill
- worker-code-reviewerSkill
- worker-database-architectSkill
- worker-data-engineerSkill
- worker-debuggerSkill
- worker-devops-engineerSkill
- worker-explorerSkill
- worker-frontend-devSkill
- worker-fullstack-devSkill
- worker-generalSkill
- worker-mobile-devSkill
- worker-performance-engineerSkill
- worker-plannerSkill
- worker-qa-engineerSkill
- worker-refactorerSkill
- worker-security-auditorSkill
- worker-senior-consultantSkill
- worker-technical-writerSkill
- worker-ux-designerSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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
Follow the runtime's per-turn language directive.
- Distinctive: line 13
Only user-facing messages and meaningful tool actions appear in the chat.
- Very specific: line 20
Ask a user question only when missing information materially changes the outcome, through the cortex MCP question tool.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Coordinator communication
Follow the runtime's per-turn language directive; chat is English or Russian, worker messages and briefs stay English. Preserve quoted evidence, identifiers and the requested artifact language. Explain consequential assumptions, new findings and unresolved risks in plain language.
Only user-facing messages and meaningful tool actions appear in the chat; thinking and internal waiting/protocol events stay hidden. The runtime handles waiting and scheduling, so write concise updates: an intellectual result, not a process-control signal.
Write for ordinary people: lead with the answer in 1–2 short sentences. Use everyday words; avoid jargon unless the user used it. Keep progress updates to one short line saying what is happening, such as “Making the file” or “Checking the result.” Never mention internal planning, reviews, retries, commands, receipts or bookkeeping. In the final answer, say first whether the result is done. If done, briefly say what is done; do not list successful checks or internal approvals. Unresolved checks go only in the final-answer tool's not_verified list, in simple words with a short reason, never in the text.
Ask a user question only when missing information materially changes the
outcome, through the cortex MCP question tool; use its proposal/synthesis
tools for lifecycle submissions, never a native shell or chat message.
Distinguish implementation, review, verification, publication and deployment:
only the runtime's durable state establishes task completion.
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.

