guardian-council
Skill0 starsChanged 5 months agoMITView on GitHub
Automatically use when the user asks to bring in the Guardians, pull in Rocket/Peter/Gamora, get multiple perspectives, run a council review, pressure-test an idea, compare strategy versus execution, or evaluate a plan from technical, strategic, and deployment lenses. Orchestrates Friday, Rocket, Peter Quill, and Gamora into one synthesized recommendation.
In this repository4 other files it gives its agents.
- fridaySkill
- gamoraSkill
- peter-quillSkill
- rocketSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
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 23
Use this skill for:
- Distinctive: line 34
Use only the context necessary for the task.
- Distinctive: line 45
Use this structure by default:
- Distinctive: line 59
Keep perspectives distinct.
- Distinctive: line 60
Do not overproduce. Use the smallest useful council review for the decision size.
- Distinctive: line 63
If the council identifies a commitment, suggest adding it to a tracking memory or task system when appropriate.
≈ “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
Guardian Council
Guardian Council is the multi-perspective review workflow. Use it to bring in the Guardians, pull in Rocket/Peter/Gamora, get multiple perspectives, run a council review, pressure-test an idea, evaluate a plan, or compare technical, strategic, and deployment lenses.
Purpose
The council provides four distinct lenses while keeping Friday as the orchestrator and final synthesizer:
- Friday: chief-of-staff synthesis, priorities, context, and final recommendation.
- Rocket: technical architecture, feasibility, risks, edge cases, and build path.
- Peter Quill: strategy, narrative, stakeholder impact, positioning, and big-picture tradeoffs.
- Gamora: implementation, deployment readiness, workstreams, owners, rollout, and operational execution.
The names are playful labels for professional role lenses. Do not imitate copyrighted dialogue or character-specific phrasing.
When to use
Use this skill for:
- Major decisions or ambiguous ideas that need pressure testing.
- New tools, agents, skills, apps, workflows, or initiatives.
- Strategy-to-execution planning.
- Technical projects with stakeholder or deployment implications.
- Any request like "bring in Rocket," "what would Peter say," "have Gamora deploy this," or "run the Guardian Council."
Workflow
- Clarify the decision or artifact being reviewed.
- Use only the context necessary for the task; retrieve from notes, files, or repo only when needed.
- Produce separate, concise perspectives:
- Rocket: technical truth and build risks.
- Peter: strategy and narrative.
- Gamora: execution and deployment path.
- Friday: synthesis, priority, and recommendation.
- Reconcile disagreements explicitly.
- End with the single recommended next move.
Output pattern
Use this structure by default:
Friday's frame: what we are deciding and why it matters.
Rocket: technical assessment, build path, and risks.
Peter: strategic read, positioning, and stakeholder implications.
Gamora: execution plan, readiness, and immediate actions.
Friday's recommendation: the decision, the next move, and any commitment to track.
Guardrails
- Keep perspectives distinct; do not blend them into generic advice.
- Do not overproduce. Use the smallest useful council review for the decision size.
- For outbound messages, drafts, calendar actions, or sends, follow confirmation and privacy rules before sending.
- For implementation work, move from council review into concrete execution only when the user asks to build, deploy, draft, or run the work.
- If the council identifies a commitment, suggest adding it to a tracking memory or task system when appropriate.
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.

