agentleFS
steepy-itsteepy-it/steepy-formula/.agents/skills/steepy-formula-bootstrap/SKILL.md

steepy-formula-bootstrap

Skill5 starsChanged 22 days agoApache-2.0View on GitHub

Project entry point for steepy-formula. Loads the root instructions and routes work through the Stable Knowledge Graph.

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
  1. Distinctive:

    Use this skill before working on the project.

    line 10
  2. Distinctive:

    Read AGENTS.md in full for the project overview, development commands, and confirmed surfaces.

    line 14
  3. Very specific:

    When a steepy-formula workflow is needed, invoke it by its semantic skill name — one of the eleven canonical skills: inception, init, …

    line 18
  4. Very specific:

    Run the owning surface's test command and steepy-formula graph validate before reporting completion.

    line 19
  5. Very specific:

    Do not ordinarily enumerate, search, or read under .formula/work/.

    line 23

≈ “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
<!-- steepy:generated:steepy-formula-bootstrap:v1 -->

steepy-formula bootstrap

Use this skill before working on the project.

Procedure

  1. Read AGENTS.md in full for the project overview, development commands, and confirmed surfaces.
  2. Declare the hub mode: run steepy-formula hub-mode and quote the mode: line. If it reports migrate, stop and tell the user to run the graph-migrate skill; if it reports none, stop and tell the user to run the init skill.
  3. Resolve the task context: run steepy-formula context resolve --path <task-path> for the paths the task will touch (fallback --target apex:<projectId>:surface:<slug>) and load exactly the layers the resolve returns (context.json + context.md).
  4. State the owning surface and specialist agent before changing files.
  5. When a steepy-formula workflow is needed, invoke it by its semantic skill name — one of the eleven canonical skills: inception, init, check, new-surface, discovery, brainstorm, plan, implement, review, loop-engineer, graph-migrate.
  6. Run the owning surface's test command and steepy-formula graph validate before reporting completion.

Work-artifact boundary

Do not ordinarily enumerate, search, or read under .formula/work/**.

A workflow phase may consume only the exact work inputs named by an accepted handoff. A pathless workflow invocation may perform only bounded workflow-header recovery discovery. Exact paths or a broader work-area scope are permitted only when the user explicitly delimits them. This applies transitively to child agents: only the phase orchestrator interprets a handoff.

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.