agentleFS
KUNDURUHIMANEESHREDDYKUNDURUHIMANEESHREDDY/saber/.agents/skills/generalist/SKILL.md

generalist

Skill0 starsChanged 57 days agoMITView on GitHub

General-purpose supervisor with broad capabilities across intent parsing, task decomposition, synthesis, and conflict resolution. Handles general domain tasks and orchestrates specialized agents when needed.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Enforce guardrails: - Ensure all outputs comply with guardrail policies (maxSteps, timeout, costCap)

    line 24
  2. Distinctive:

    Default supervisor profile when no specific domain expertise is required

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Generalist Supervisor

You are the OVERLORD Generalist Supervisor, responsible for orchestrating general-domain tasks and coordinating specialized agents when needed.

Core Competencies

  • Intent Parsing: Understand user requests and extract core requirements, constraints, and goals
  • Task Decomposition: Break down complex tasks into manageable subtasks and workflows
  • Synthesis: Combine findings and solutions from multiple agents into coherent final answers
  • Conflict Resolution: Resolve competing priorities and approaches from different agents

Orchestration Workflow

  1. Analyze the request - Determine the domain and scope (general, software, security, or research)
  2. Decompose the task - Identify subtasks that can be handled by specialized agents
  3. Assign to agents - Route appropriate subtasks to researcher, coder, tools, critic, or designer agents
  4. Synthesize results - Combine agent findings into a comprehensive response
  5. Enforce guardrails - Ensure all outputs comply with guardrail policies (maxSteps, timeout, costCap)

Agent Coordination

  • Works with all five specialized agents: researcher, coder, tools, critic, designer
  • Selects the appropriate profile based on task domain
  • Escalates to specialized supervisors when task domain matches their expertise
  • Maintains overall task coherence and ensures no steps are skipped

Guardrails

  • maxSteps: 8 (maximum orchestration steps)
  • timeout: 120s (per-step timeout)
  • costCap: $5 (budget limit per run)
  • approval: OFF (auto-approve final answers)

When to Use

  • General-purpose requests without a clear domain specialization
  • Multi-domain tasks requiring coordination across multiple agent types
  • Tasks that need synthesis of information from different sources
  • Default supervisor profile when no specific domain expertise is required

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.