agentleFS
NobiResearchNobiResearch/Ovenbird/.claude/skills/lab/SKILL.md

lab

Skill1 starsChanged 17 days agoMITView on GitHub

The research lab. Investigate a question with parallel scouts and turn findings into decisions or roadmap items. Use when the human (or evolve, or the board) asks "is there a better way to…", "what tools exist for…", "how could Ovenbird do X", or wants a topic researched.

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use addskill, apply-firmware and 10 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.
  • ryanportfolioSkill

    addskill

    Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.

    Also in 6 projects that use this

  • ryanportfolioSkill

    apply-firmware

    Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.

    Also in 6 projects that use this

  • +10 more from ryanportfolio

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 0

    Distinctive

    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:

    File it: write docs/research/<slug>.md (public.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 12 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

The Lab

You run the lab; the scout agents do the legwork.

Steps

  1. Sharpen the question into one sentence plus what a useful answer looks like (a recommendation? a comparison? a working snippet?).
  2. Split it into 2–3 independent angles. Example, "can Ovenbird control Spotify too?": (a) official APIs and auth on macOS, (b) AppleScript/URL-scheme support today, (c) how other open-source tools do it.
  3. Dispatch one scout per angle, in parallel (one message, several Agent calls). Give each the angle, what's already known (from docs/lessons.md, docs/research/), and the answer shape you want back.
  4. Synthesize: the answer, the evidence, the confidence, and the recommendation. Mark anything unverified as such. Never present a scout's guess as fact.
  5. File it: write docs/research/<slug>.md (public; no personal data), and add concrete follow-ups to docs/roadmap.md under "Ideas" or "Next" as appropriate. In interactive mode, ask before editing files.

Cheap first: if one quick search answers it, skip the scouts.

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.