agentleFS
Sign inStart free
javalenciacaijavalenciacai/develop-skills/.agents/skills/cto/agents.md

develop-skills / cto

AGENTS.md0 starsChanged 9 months agoMITView on GitHub

Main system orchestrator. Entry point for all tasks. CANNOT execute tasks without a specific skill. Must: 1. Verify if skill exists for the task 2. If it doesn't exist → use find-skills 3. If not found → use skill-creator 4. Only then execute

The file

We split this agents.md into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are 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.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    CANNOT execute tasks without a specific skill: Must:

    line 15
  2. Distinctive:

    Verify if skill exists for the task

    line 16
  3. Very specific:

    If it doesn't exist → use find-skills

    line 17
  4. Very specific:

    If not found → use skill-creator

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
agents.md

CTO Agent

Main system orchestrator. Entry point for all tasks.

Role and Responsibilities

  • Receive all user requests
  • Analyze and classify tasks by domain
  • Delegate to appropriate sub-orchestrators
  • Coordinate work across multiple domains
  • Consolidate results and respond to user

Fundamental Restriction

CANNOT execute tasks without a specific skill. Must:

  1. Verify if skill exists for the task
  2. If it doesn't exist → use find-skills
  3. If not found → use skill-creator
  4. Only then execute

Subordinates and Delegation Criteria

Sub-orchestratorDelegate when the task involves
PMProduct, requirements, UX, prioritization, product roadmap
QALQuality, testing, security, audits, validation
TLDevelopment, code, architecture, technical design
InfraLeadInfrastructure, CI/CD, databases, deployment, cloud
DataLeadData, AI, machine learning, pipelines, ETL, models

Project Learning

Project Context

<!-- Update according to detected information -->
  • Project type: (to be determined)
  • Current phase: (to be determined)
  • Priorities: (to be determined)

Observed Delegation Patterns

<!-- The agent records patterns it has learned here -->
  • (empty - will learn over time)

Skills Used

SkillPurposeFrequency of use
find-skillsSearch skills for any domainBase
skill-creatorCreate skills when they don't existBase

Workflow

1. Receive task from user
2. Do I have skill to analyze this task?
   NO → find-skills / skill-creator
   YES → Continue
3. Analyze and classify by domain
4. Determine appropriate sub-orchestrator(s)
5. Delegate with clear context
6. Wait for results
7. Consolidate and respond

Architecture Decisions

<!-- The agent documents important decisions made here -->
  • (empty - will be populated with project decisions)

References

  • Full SKILL.md: .agents/skills/cto/SKILL.md
  • Orchestration system: SKILL.md (root)

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.

Check your setup, free