agentleFS
Sign inStart free
brebuildsbrebuilds/claude-skills/bundle-builder/SKILL.md

bundle-builder

Skill0 starsChanged 3 months agoMITView on GitHub

Interactive wizard for designing agent bundles using the 5-question architecture (Identity, Routing, Capability, Memory, Boundary + scaling axis). Supports both single-agent bundles and multi-specialist systems (orchestrator + narrow specialists with explicit handoff contracts). Asks one question at a time, pushes back on vague answers, generates complete folder structures with starter markdown. Use when starting any new agent or multi-stage automation for a client or internal system.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    After all turns + recap confirmation, generate the bundle(s) at the destination Bre specifies

    line 23
  2. Distinctive:

    Stop. Let Bre run it for 1-2 real sessions before iterating.

    line 24
  3. Distinctive:

    If user is stuck, offer 2-3 example answers.

    line 39
  4. Distinctive:

    Never invent capability the user didn't list.

    line 40
  5. Distinctive:

    When the flow is multi-specialist, every specialist also receives the full 5-Q structure + a handoff contract.

    line 43

≈ “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

bundle-builder

Interactive wizard. Walks a scoped interview, then scaffolds either a single agent or a full multi-specialist system.

When to invoke

Triggers:

  • "build me a bundle for X"
  • "scaffold an agent for X"
  • "I need to design an automation for X"
  • "let's architect [client name]'s system"
  • "/bundle" slash command

How to run

  1. Read this file
  2. Open WIZARD.md and follow it turn-by-turn
  3. After all turns + recap confirmation, generate the bundle(s) at the destination Bre specifies
  4. Stop. Let Bre run it for 1-2 real sessions before iterating.

Files in this skill

FilePurpose
SKILL.mdThis file — overview + triggers
WIZARD.mdThe interview script — branching single vs multi-specialist + 5-Q per specialist
TEMPLATES/Starter markdown the wizard copies + fills in (single + system + specialist variants)
EXAMPLES/Reference bundles (single-agent and multi-specialist)

Behavior rules — do NOT skip

  • One question per turn. Wait for answer. Sub-questions on the same topic OK in the same turn.
  • Push back on vague answers. Restate the question. Do not accept "I don't know."
  • If user is stuck, offer 2-3 example answers. Never more.
  • Never invent capability the user didn't list.
  • Functional names only. No cute names. No "AgentBot 3000."
  • End generation with the literal sentence: "Use this in 1-2 real sessions, then come back and tell me what's missing."
  • When the flow is multi-specialist, every specialist also receives the full 5-Q structure + a handoff contract.

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