agentleFS
andyridsandyrids/icm-spec/skills/express/SKILL.md

express

Skill2 starsChanged 3 months agoApache-2.0View on GitHub

Run the ICM express-change pipeline - a small change no spec has to move for, with the plan record left intact

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    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:

    Read CONTEXT.md at the repository root, then ICM/express-change/CONTEXT.md, then ICM/express-change/stages/01-change/CONTEXT.md.

    line 13
  2. Very specific:

    Test eligibility before writing anything, and state the verdict with its reason in the visible response.

    line 16
  3. Distinctive:

    Stop at the single review gate: present the plan, the diff and the test result for explicit user acceptance.

    line 20

“Common” is measured: kept by at least 6 in 10 of the 4 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

ICM express-change

The argument is the change request. If it is empty, ask for one before doing anything else.

  1. Read CONTEXT.md at the repository root, then ICM/express-change/CONTEXT.md, then ICM/express-change/stages/01-change/CONTEXT.md. If any of these is missing, stop and suggest /icm:init.
  2. Test eligibility before writing anything, and state the verdict with its reason in the visible response. If the work needs a specs/** change, stop and hand off to /icm:specify. Do not amend a spec here - that is the one thing this pipeline exists not to do.
  3. Execute the stage contract exactly as written - it defines the inputs, process and outputs.
  4. Stop at the single review gate: present the plan, the diff and the test result for explicit user acceptance. The run ends there; the frozen plan is the durable record.

$ARGUMENTS

Download now (ZIP)

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. G1Joshi/Agent-Skills★ 15same name
    2. Spardutti/claude-skills★ 3same name
    3. authdog/agent-skills★ 0same name
    4. conjure-3301/skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository10 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.