persistent-role-promotion
Skill2 starsChanged 33 days agoMITView on GitHub
Proposes persistent specialist agent roles from proficiency evidence (staging + PR only)
In this repository52 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/00-core-operating-model.mdcCursor rule
- .cursor/rules/01-plan-approval-gate.mdcCursor rule
- .cursor/rules/02-git-worktree-policy.mdcCursor rule
- .cursor/rules/03-validation-definition-of-done.mdcCursor rule
- .cursor/rules/04-documentation-memory.mdcCursor rule
- accessibility-reviewSkill
- agent-skills-packagingSkill
- autonomy-budgetSkill
- bounded-autonomySkill
- candidate-promotionSkill
- capability-planningSkill
- code-reviewerSkill
- code-structure-cleanupSkill
- compass-evaluatorSkill
- context-inodesSkill
- dependency-supply-chainSkill
- docker-cloudSkill
- embedding-providersSkill
- execution-telemetrySkill
- experience-routingSkill
- experience-skill-trainingSkill
- external-knowledge-ingestSkill
- github-integrationSkill
- goose-agent-orchestrationSkill
- harness-gcSkill
- hosted-vector-dbSkill
- implementation-planningSkill
- ios-engineeringSkill
- knowledge-stewardSkill
- linear-integrationSkill
- node-engineeringSkill
- northstar-connected-routineSkill
- notion-integrationSkill
- package-registry-tiSkill
- playwright-browser-validationSkill
- postgres-prismaSkill
- procedure-playbooksSkill
- project-overseerSkill
- pull-request-preparationSkill
- python-mlSkill
- react-engineeringSkill
- repository-discoverySkill
- review-fix-loopSkill
- security-audit-proceduresSkill
- security-reviewSkill
- skill-learning-loopSkill
- skill-lifecycleSkill
- source-code-contextSkill
- technology-intelligence-liveSkill
- testing-validationSkill
- worktree-orchestrationSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 32
After merge, optionally record the role in .agent/agents/promotions/registry.json so the assembler can prefer it.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Persistent Role Promotion
Use this Skill when
A subagent has Captain-approved proficiency at proficient or expert with
enough Experience evidence, and the Captain wants a persistent specialist
role draft prepared for a PR into .cursor/agents/.
Inputs
- Agent id with proficiency under
.agent/agents/proficiency/ - Optional notes
Procedure
- Confirm proficiency gates (Captain-approved, level ≥ proficient, ≥1 Experience id).
Propose staging drafts only:
./scripts/propose-persistent-role.sh --agent-id compass-evaluator- Review proposal under
.agent/agents/promotions/proposals/and drafts under.agent/agents/promotions/staging/<agent-id>/. - Open a Captain-reviewed PR to copy drafts into
.cursor/agents/andorchestrator/reference-profiles/. Never auto-merge. - After merge, optionally record the role in
.agent/agents/promotions/registry.jsonso the assembler can prefer it.
NorthStar bridge
From a NorthStar run that has reached REVIEW_READY:
./scripts/run-northstar-routine.sh --demo --approve --advance-to-review --propose-rolesThis only stages drafts via orchestrator/integrations/m4_bridge.py. It does
not write .cursor/agents/ or auto-merge.
Output
- Promotion proposal JSON
- Staging
agent.md+reference-profile.json
Prohibited actions
- Writing directly to
.cursor/agents/from this Skill - Auto-merging persistent-role PRs
- Treating staging drafts as live agents
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.

