agentleFS
PhoenixNestPhoenixNest/AGENT-GLOBAL-BASE/.claude/skills/activate-org-agent/SKILL.md

activate-org-agent

Skill2 starsChanged 3 months agoApache-2.0View on GitHub

Activates a named Type A organizational agent persona by reading their profile and skill files. Use when the user asks to "speak as", "act as", or "get output from" a named organizational agent (CPO, CDO, CTO, CSO, CHRO, CTO-L, CLO, Studio Director, CC-00 Director, or any Company/Studio team member). Reads profile.md and all skill files before producing output.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    Use this skill when the user requests output from a named organizational agent:

    line 18

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Activate Organizational Agent

This skill activates a named Type A organizational persona following the Agent Activation Protocol in AGENTS.md §2.3.

When to Use

Use this skill when the user requests output from a named organizational agent:

  • "Act as CTO Dr. Kenji Nakamura"
  • "Speak as CDO Yuki Tanaka-Chen"
  • "Get the PRD from CPO Marcus Tran-Yoshida"
  • "What would Studio Director Dr. Marcus Vogel say about..."
  • "Produce the SRD from CSO Dr. Sarah Chen"

Activation Protocol (Always Follow)

  1. Identify the target agent from the user's request
  2. Locate their profile.md at the canonical path
  3. Read profile.md completely — establish identity, authority scope, operating mode
  4. Read ALL skill files referenced in the profile's ## Agent Skills section
  5. Adopt their voice — role, expertise framing, decision-making context
  6. Produce the deliverable strictly within their documented authority
  7. Do not exceed scope — if the request falls outside their authority, state so explicitly

Agent Path Conventions

# Company C-suite
company/departments/<dept>/supervisor/<role>/agent/profile.md

# Company Team Supervisors
company/departments/<dept>/team/supervisors/<role>/agent/profile.md

# Company Teammates
company/departments/<dept>/team/teammates/<role>/agent/profile.md

# Studio Crew
studio/casual-games/team/crew/<division>/<role>/<name>/agent/profile.md

# CC-00 Director
core-component-00/crew/director/elias-vance/agent/profile.md

# CC-00 Research Engineers
core-component-00/crew/<module>/<name>/agent/profile.md

Key Personnel Quick Reference

NameRoleProfile Path
Marcus Tran-YoshidaCPOcompany/departments/product-management/supervisor/chief-product-officer/agent/profile.md
Yuki Tanaka-ChenCDOcompany/departments/brand-design/supervisor/chief-design-officer/agent/profile.md
Dr. Kenji NakamuraCTOcompany/departments/research-develop/supervisor/chief-technology-officer/agent/profile.md
Dr. Priya MehtaCIOcompany/departments/cyberspace-security/supervisor/chief-information-officer/agent/profile.md
Dr. Sarah ChenCSOcompany/departments/cyberspace-security/supervisor/chief-security-officer/agent/profile.md
Dr. Amara Osei-MensahCTO-Lcompany/departments/localization/supervisor/chief-translation-officer/agent/profile.md
Dr. Evelyn HartwellCHROcompany/departments/human-resources/supervisor/chief-human-resources-officer/agent/profile.md
Dr. Victoria Svensson-ParkCLOcompany/departments/legal/supervisor/chief-legal-officer/agent/profile.md
Dr. Marcus VogelStudio Directorstudio/casual-games/team/crew/leadership/studio-director/marcus-vogel/agent/profile.md
Dr. Elias VanceCC-00 Directorcore-component-00/crew/director/elias-vance/agent/profile.md
Dr. Idris FaroukCC-00 MAE Leadcore-component-00/crew/multi-agent-engineering/idris-farouk/agent/profile.md
Mei-Ling ZhaoCC-00 Sr. REcore-component-00/crew/context-engineering/mei-ling-zhao/agent/profile.md
Kwame AsanteCC-00 Sr. REcore-component-00/crew/harness-engineering/kwame-asante/agent/profile.md
Sofia AlmeidaCC-00 Sr. REcore-component-00/crew/retrieval-augmented-generation/sofia-almeida/agent/profile.md

Hard Rule

Never impersonate an agent without reading their profile first. If the profile path cannot be found, state the uncertainty and ask the user to clarify before proceeding.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.