agentleFS
Sign inStart free
matheus-rib1108matheus-rib1108/meu-kit-claude-code/skills/criar-skills/agent-builder/SKILL.md

agent-builder

Skill0 starsChanged 26 days agoMITView on GitHub

Creates the user's own personal AI agents (Claude Code subagents) for any recurring task — e.g. a study assistant, a social-media assistant, a client-site builder, an Obsidian librarian — and registers them so Claude picks them automatically. Use when the user asks to "criar um agente", "minha IA para…", "um assistente que…", or wants a repeatable specialist.

57 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use workflow-builder, pdf and 5 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Hussain-ElfalahSkill

    workflow-builder

    Also in 3 projects that use this

  • AnthropicSkill

    pdf

    Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

    Also in 30 projects that use this

  • dragonflydbSkill

    benchmark

    Benchmark Dragonfly (and compare against Valkey/Redis) on local or remote cloud instances, then produce a performance + memory report with charts and a raw-data appendix. Use this whenever the user runs /benchmark, or asks to benchmark / load-test / measure throughput, QPS, latency, or memory efficiency of Dragonfly or another Redis-compatible server, to compare Dragonfly vs Valkey or Redis, or to generate a benchmark report. Trigger it even when the user just describes the goal ("see how fast Dragonfly is on this box", "compare memory per key vs Valkey") without saying the word "benchmark".

    Also in 3 projects that use this

  • SentrySkill

    onboard

    Onboard a service to sentry-options. Use when integrating a new service, creating schemas, or setting up the multi-repo sentry-options workflow.

    Also in 3 projects that use this

  • OpenAISkill

    audit

    Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Add a row to the team table in CLAUDE.md ("Pedido do usuário → quem faz").

    line 41
  2. Distinctive:

    Test it with one realistic request.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 51 edited versions of this file we could read. “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

Agent builder

An agent is a Markdown file in .claude/agents/<name>.md (this project) or ~/.claude/agents/<name>.md (all projects on the user's computer).

1. Interview (max 4 short questions, skip what's already clear)

  • What should it do, with an example request?
  • What must it never do? (e.g. never send messages or publish without confirmation)
  • Which tools/places does it use? (web search, files, Obsidian, Notion, Vercel, browser)
  • Style of the answer (short? Portuguese? table?).

2. Write the file

---
name: kebab-case-name
description: "Use this agent when <concrete triggers, in the user's words too>. <What it delivers>."
tools: Read, Write, Edit, Glob, Grep, WebSearch, WebFetch   # only what it needs
model: sonnet            # sonnet = fast/cheap; opus = hardest reasoning
---

You are <role> for <user>. <Goal in one sentence>.

## How you work
1. ...
## Rules
- Never <hard limits>.
- Answer in Portuguese, <style>.
## Output
<exact format>

Rules: the description decides when it's used — make it specific. Give the fewest tools possible (security + fewer tokens). MCP tools are listed by name (e.g. mcp__notion__*) only if that server is configured. Reuse existing skills by naming them in the body.

3. Register and test

  • Add a row to the team table in CLAUDE.md ("Pedido do usuário → quem faz").
  • Test it with one realistic request; fix the prompt if it went off-track.
  • Tell the user how to call it: just ask normally, or "usa o agente <name>".

Ideas to offer

estudos (resume vídeos/PDFs into Obsidian notes) · social-media (scripts for Reels/TikTok, content calendar in Notion) · site-cliente (runs the full site pipeline + site-fortress + cost-estimator) · pesquisa-precos · organizador-obsidian.

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