agentleFS
Sign inStart free
steepy-itsteepy-it/steepy-formula/skills/check/SKILL.md

check

Skill5 starsChanged 19 days agoApache-2.0View on GitHub

Run `steepy-formula graph validate` on the canonical Stable Knowledge Graph and report any violations.

80 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval 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.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • JuliusBrusseeSkill

    backprop

    Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 69 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Declare the hub mode first: Run steepy-formula hub-mode and quote its mode: line — graph, migrate, or none, each printed with one evidence: …

    line 18
  2. Very specific:

    If the user asked about a specific area, optionally spot-check the resolver too — target-based: steepy-formula context resolve --target …

    line 55

“Common” is measured: kept by at least 6 in 10 of the 69 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

check

Declare the repo's hub mode, validate the canonical Stable Knowledge Graph from the repo root, and report any violations.

Engine root: this skill's base directory is <engine-root>/skills/check/; engine scripts live two levels up, at <engine-root>/scripts/. Resolve them relative to the base directory your harness reports for this skill.

Procedure

  1. Declare the hub mode first. Run steepy-formula hub-mode and quote its mode: line — graph, migrate, or none, each printed with one evidence: line. The command always exits 0: it is a declaration, not a gate, and this prose never re-implements its detection — the command is the single authority. The declared mode picks the gate:

    Declared modeCoherence gate
    graphsteepy-formula graph validate (step 2)
    migrateStop and tell the user to run the graph-migrate skill (invoke it the way your harness invokes skills) before any other workflow.
    noneNo hub — nothing to validate. Stop and tell the user to run the init skill (invoke it the way your harness invokes skills) to create one, instead of reporting a coherent hub.

  2. Validate the graph

    First run the model-mapping freshness verifier (before the coherence gate):

    node <engine-root>/scripts/verify-model-mappings.mjs
    • Include the per-row verdicts (OK | STALE | UNKNOWN) in the check report.
    • STALE means the live source shows drift: a human-ratified table patch is needed — the script prints the prepared patch, so surface it in the report as a finding for a human to ratify and apply.
    • UNKNOWN is informational (source unreachable — offline degradation): report it as declared, never as a failure.

    Then validate the canonical graph:

    steepy-formula graph validate
    • Exit 0 (violations: 0, chain clean): report that the canonical graph is coherent — the portable graph invariants and the revision-chain replay both came back clean.
    • Exit non-zero: list each printed [CODE] message violation clearly and suggest how to fix it (broken structural invariants, nodes unreachable from the Project root, replay findings such as out-of-band writes).
    • If the user asked about a specific area, optionally spot-check the resolver too — target-based: steepy-formula context resolve --target apex:<projectId>:surface:<slug(name)> should still answer for the area's owning surface (surface names from .claude/agents/<name>-agent.md, with CLAUDE.md's Surfaces section as the fallback listing; the project id from the hub-mode declaration's hub-mode '<projectId>' echo; slug(name) lowercase with non-alphanumeric runs collapsed to -). steepy-formula context resolve --path <p> answers only where a topology bridge exists (e.g. a hub migrated through graph-migrate); on a freshly graph-first-initialized repo it exits 10 UNRESOLVED — expected, not a violation.
  3. Report — name the declared hub mode, confirm steepy-formula graph validate ran, and whether it is green.

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