agentleFS
emiljuchnikowskiemiljuchnikowski/ai-os-template/.claude/skills/level-up/SKILL.md

level-up

Skill0 starsChanged 3 months agoMITView on GitHub

Weekly 3M interview (Mindset → Method → Machine) ending in ONE shipped automation or skill. Use once a week, after /audit.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use explain, build and 1 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.
  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 3 projects that use this

  • Microsoft AzureSkill

    build

    Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 5 projects that use this

The file

Files
SKILL.md

Level-up — one lever per week

/audit asks "is the OS well built?" (form). /level-up asks "what lever am I missing?" (function). The result = ONE shipped artifact, not a list of ideas.

Interview (one question at a time)

  1. Mindset: what did you do by hand this week while feeling "AI could probably do this"? Where did you reflexively open the browser instead of the OS?
  2. Method: which process did you repeat ≥2 times? Which prompt did you type ≥2 times? (skill candidate — see /skill-builder)
  3. Machine: what couldn't the OS touch, so you got stuck? (candidate for a new connection in connections.md)

Selection and delivery

  • Collect candidates — fresh from the interview, backlog from context/growth/level-up-backlog.md, and section "(d) cadence candidates" of the latest report in archives/audits/.
  • Judge against the north star (context/north-star.md): does it move the goal or save real hours? If not — reject (productivity ≠ hour count). Update the backlog: chosen → remove; permanently rejected → a "Rejected" section with the reason.
  • Eliminate before you automate: first check whether the step should exist at all. Automating a worthless step entrenches the waste. Sometimes the cheaper fix is deleting the step, a template, or a changed entry condition.
  • Estimate with the outside view: "how long did similar things actually take", not "how long do I feel this will take" — the planning fallacy is the default.
  • Pick ONE. Build it in this session (skill → /skill-builder; connection → entry + live test in connections.md; automation → make the workflow work manually first; cadence comes only after that).
  • One per week is not bureaucracy — shipping several changes in parallel is the most common reason none of them stick.
  • Record in decisions/log.md what was chosen and what was rejected (with reasons).
  • Commit: feat: level-up — <artifact name>.

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.