agentleFS
Sign inStart free
Co4anCo4an/claude-auto/skills/pick/SKILL.md

pick

Skill0 starsChanged 6 months agoMITView on GitHub

Picks the best 3-5 agents for a given task and shows reasoning, WITHOUT launching them. Use when Roman wants to see options before committing, or to compare candidates for a task.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. cyrilichti/agent-workflows★ 3same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the user's task from $ARGUMENTS.

    line 16
  2. Distinctive:

    Do not launch any worker agent: Only show recommendations.

    line 49

≈ “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

PICK — Show agent candidates without launching

You receive a task description and return the best 3-5 candidate agents with reasoning. You DO NOT launch them.

Process

  1. Read the user's task from $ARGUMENTS.
  2. Invoke Agent with subagent_type: "Meta Task Classifier" to get the type/complexity/domain.
  3. Invoke Agent with subagent_type: "Meta Agent Picker" to get the candidate list.
  4. Format and present to user.

Output format

## Recommended agents for: "[task]"

**Classification:** [type, complexity, domain, deliverable]

| # | Agent | Why this one | Model |
|---|---|---|---|
| 1 | `slug` | [reason] | haiku/sonnet/opus |
| 2 | ... | ... | ... |

**Execution suggestion:** [parallel/sequential]
**Synthesis:** [which agent or main session synthesizes]
**Token estimate:** low / medium / high

**Alternatives considered but rejected:**
- `slug` — [why not]
- `slug` — [why not]

---

To run this plan: `/auto <model> <task>` (or just `/auto <task>` for adaptive model)
To run a single agent: just say "use <agent slug>" or "use the X agent"

Hard rules

  1. Do not launch any worker agent. Only show recommendations.
  2. Maximum 5 candidates in the main table. Rejected alternatives go below.
  3. Be specific about why each agent fits THIS task — not generic descriptions.
  4. Suggest the right next command at the bottom — /auto for full pipeline, single agent for simple task.

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