agentleFS
Sign inStart free
ulises-jeremiasulises-jeremias/agent-toolkit/skills/tooling/inventory/SKILL.md

inventory

Skill19 starsChanged 2 months agoMITView on GitHub

Discover installed skills, agents, loops, and platform capabilities via agent-toolkit inventory,

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Before starting delivery: check which workflow (delivery/*), forge (github-cli-workflow), or ops (swarm) skills apply.

    line 23
  2. Very specific:

    After agent-toolkit install — verify what was deployed and what needs mcp setup.

    line 24
  3. Very specific:

    Before running build or plugin — understand target support via matrix.

    line 25
  4. Very specific:

    Host / installed toolkit (consumers): use the CLI only — do not expect repo-root scripts/ (it is not installed to XDG/wheel):

    line 63

“Common” is measured: kept by at least 6 in 10 of the 3 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

Inventory

Discover what the toolkit can do before you build — skills, agents, loops, MCP, and platform support — via agent-toolkit inventory, matrix, build --check, and skills list.

When to use

  • User asks "what can agent-toolkit do?", "what skills are available?", or "is there a skill for X".
  • Before starting delivery: check which workflow (delivery/*), forge (github-cli-workflow), or ops (swarm) skills apply.
  • After agent-toolkit install — verify what was deployed and what needs mcp setup.
  • Before running build or plugin — understand target support via matrix.

Workflow

1. List everything

agent-toolkit inventory              # skills (61), agents (16), loops (10), products
agent-toolkit matrix                 # platform capability matrix (claude-code, cursor, opencode, etc.)
agent-toolkit skills list            # grouped by domain (core, ops, forge, etc.)
agent-toolkit skills list --domain ops  # filter
agent-toolkit loops --help 2>&1 | head

inventory now shows 61 skills across 9 domains including the new swarm family:

  • ops/swarm, ops/swarm-observer, ops/swarm-handoff, tooling/herdr, forge/worktree, core/workspace, core/project, integrations/mcp, tooling/inventory.

2. Inspect a skill or agent

agent-toolkit skills validate        # all 61 should be ✓
muse skills validate ~/.ai-workspace/.agents/skills/swarm --json | jq .valid
cat skills/ops/swarm/SKILL.md | head -n 20
cat agents/code-reviewer/AGENT.md | head -n 20
ls plugins/  # agent-toolkit-core, agent-toolkit-forge, etc. — each maps skills+agents to targets

3. Check readiness before delivery

agent-toolkit doctor
agent-toolkit mcp doctor
agent-toolkit swarm doctor           # herdr/tmux + runner model profiles
agent-toolkit build --check          # validate compilation without writing plugins/

4. After adding skills (host vs checkout)

Host / installed toolkit (consumers): use the CLI only — do not expect repo-root scripts/ (it is not installed to XDG/wheel):

agent-toolkit skills validate
agent-toolkit skills list --domain ops
agent-toolkit inventory
agent-toolkit install --dry-run

Maintainer / repo checkout only (CI or local clone of agent-toolkit): regenerate catalogs and package data from the monorepo root:

./scripts/generate-catalogs.vsh          # regenerate catalogs/*.yaml
./scripts/prepare-package-data.vsh         # sync skills/catalogs into packages/pypi/.../data/
agent-toolkit skills validate

Delegates to

NeedSkill
Use a discovered skillassistant (discovery), swarm (orchestration), workspace (context)
Install or sync to a toolmcp (providers), herdr (UI)
Build error after inventorybuild-error-resolver agent

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