agentleFS
Sign inStart free
ai-erp-collabai-erp-collab/deterministic-context-routing-plugin/skills/check/SKILL.md

check

Skill0 starsChanged 4 days agoMITView on GitHub

Use when the user asks for a workspace health check, audit, or check report, or asks to fix numbered issues from that report, for example "fix issue 3". Runs the workspace integrity tool, which applies only fixes with one correct answer (journaled, undoable) and lists everything else as numbered issues.

80 other projects use a version of this.

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

5 rules. 0 are common, 0 are distinctive, and 5 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.

  • 5

    Very specific

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

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

    If tools/kb/kb.py is missing but AGENTS.md and modules.md exist, the workspace was built before the integrity tool.

    line 14
  2. Very specific:

    Every edit is journaled; python tools/kb/kb.py undo <run-id> reverts that run if the files have not changed since.

    line 22
  3. Very specific:

    Run the full check: python tools/kb/kb.py check.

    line 24
  4. Very specific:

    When the user names ids ("fix #3, #5"), run python tools/kb/kb.py fix --ids 3 5.

    line 41
  5. Very specific:

    Run python tools/kb/kb.py check again and report what is still open.

    line 47

“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

The workspace's integrity tool does the checking; this skill runs it and reports. Run commands from the workspace root. Use python3 or py -3 where python is missing or older than 3.9.

Before you start

If tools/kb/kb.py is missing but AGENTS.md and modules.md exist, the workspace was built before the integrity tool. Tell the user to run the init skill, which upgrades it, and stop.

Run

  1. Apply the fixes that have exactly one correct answer: python tools/kb/kb.py fix --safe. It prints each edit and a run id. Every edit is journaled; python tools/kb/kb.py undo <run-id> reverts that run if the files have not changed since.
  2. Run the full check: python tools/kb/kb.py check. It writes a dated report in docs/checks/, rewrites docs/checks/OPEN.md (numbered open issues), and updates the health line in known_issues.md.
  3. Report to the user: the summary line, the edits from step 1 with their run id, and the open issues from docs/checks/OPEN.md by id, blocking ones first. Blocking means routing or evidence tracking would give an agent wrong context.

The tool covers module registry paths, links that must open by path (in the wiki, in the root and module AGENTS.md, and in the newest part of each session log), legacy [[...]] links, index coverage, session stop markers, confidence lines, required sections per page type, duplicate pages, evidence tracking and freshness, recipe drift, encoding, unknown source extensions, and the lookup index.

Fix

  1. When the user names ids ("fix #3, #5"), run python tools/kb/kb.py fix --ids 3 5. It applies the automatic fixes and prints one line per id it could not fix (no automatic fix, unknown issue id; exit 1). Work each of those through the kb skill (its issue-queue procedure), asking the user where the answer is a judgment call.
  2. Run python tools/kb/kb.py check again and report what is still open.

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