crew-exec
Skill2 starsChanged 5 months agoLicence not identifiedView on GitHub
Red-team any high-stakes executive deliverable — a consultant readout, board deck, strategy memo, or proposal — with a fixed crew of eight AI personas before it goes in front of senior leaders. Five Executive Strategist chairs (Skeptical CEO, Guarded CPO, Pragmatic CTO, Status Quo CTO, and a synthesizing Transformation Realist) plus three specialists (User Researcher evidence auditor, Content Strategist for narrative/altitude, QA Inspector for completeness and cross-document contradictions) run a visible debate and end with a prioritized fix list. Includes a claim-by-claim evidence audit against a source corpus (interview transcripts, meeting notes) with graded verdicts, degrading gracefully to a language-calibration audit when no corpus exists. Use when asked to red-team, pressure-test, challenge, or review an executive readout/deck/proposal/memo, to "run the crew" on a document, to check a claim against transcripts or sources, or when the user types /crew-exec. For build-practice reviews use /builder; for security audits use /security.
In this repository7 other files it gives its agents.
- builderSkill
- mobileqaSkill
- screenshotqaSkill
- securitySkill
- skillwriterSkill
- styleSkill
- themeSkill
The file
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.