luabaggluabagg/agent-skills/skills/agentfolio-operator/SKILL.md

agentfolio-operator

Skill3 starsChanged 3 months agoMITView on GitHub

Use when configuring this Agentfolio collection, selecting Pi/Cursor/OpenCode harness workflows, changing model policy, or choosing plan/apply commands.

In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- branch-portSkill
- code-commentsSkill
- code-namingSkill
- cognitive-refactorSkill
- memory-palaceSkill
- natural-copy-editingSkill
- testing-business-rulesSkill
- thorough-pr-reviewSkill

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Run these commands from the collection checkout (or set AGENTFOLIO_COLLECTION):
line 12
Very specific:
Use agentfolio list harnesses, plan, doctor, and verify for inspection.
line 58
Very specific:
Treat direct agent-skills setup|install commands as adapter implementations or debugging surfaces.
line 59
Distinctive:
Keep credentials outside the collection.
line 60
Distinctive:
Stop on the first failed action and preserve unmanaged user configuration.
line 62

≈ “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

Agentfolio Operator

Agentfolio orchestrates collection.yaml. This repository's adapter owns harness behavior. Do not hand-edit live harness configuration when a declared action exists.

Start with the collection

Run these commands from the collection checkout (or set AGENTFOLIO_COLLECTION):

agentfolio doctor --collection .
agentfolio list harnesses --collection .
agentfolio plan --collection .

Agentfolio also discovers the nearest collection.yaml or uses AGENTFOLIO_COLLECTION.

Profiles

Intent	Profile
Personal + curated skills and global instructions	`default`
Personal skills only	`skills`
Personal skills plus Pi configuration	`pi`
Committed Pi model lock and Scope only	`pi-catalog`
Personal skills plus Cursor agents	`cursor`
Personal skills plus OpenCode plugins and agents	`opencode`
Personal skills plus global, Pi, Cursor, and OpenCode	`all`

Preview before applying:

agentfolio plan --profile pi
agentfolio apply --profile pi --dry-run
agentfolio apply --profile pi-catalog --dry-run
agentfolio apply --profile pi

Collection-owned model commands

agent-skills implements model discovery and generated catalog files, not Agentfolio core:

agent-skills models check
agent-skills models diff
agent-skills models refresh

Edit harnesses/catalog.yaml. The generated model lock is an output. Run models check, then preview with models diff. Use models refresh only when the policy and discovery results are ready to commit. Apply Pi changes through agentfolio apply --profile pi --dry-run.

Decision rules

Change workflow intent in collection.yaml. Change execution semantics in scripts/agentfolio-adapter.mjs or the relevant setup script.
Use agentfolio list harnesses, plan, doctor, and verify for inspection.
Treat direct agent-skills setup|install commands as adapter implementations or debugging surfaces.
Keep credentials outside the collection. Never copy OAuth tokens, API keys, or login state.
Dry-run first unless the user explicitly requests an immediate apply.
Stop on the first failed action and preserve unmanaged user configuration.
Restart a harness when its extensions or providers changed.

Canonical onboarding and safety

Clone this collection and run npm ci. Install or verify Agentfolio from its canonical repository. Before apply, run:

agentfolio doctor --collection .
agentfolio plan --profile pi --collection .
agentfolio apply --profile pi --dry-run --collection .

The adapter is generic. This collection owns setup policy. Use native keychain or login authentication first. Keep fallback environment keys ephemeral. Rely on dry-run and rollback safeguards. Pi uses direct providers and its native model picker.

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