agentleFS
Sign inStart free
andyridsandyrids/icm-spec/skills/spec/SKILL.md

spec

Skill2 starsChanged 3 months agoApache-2.0View on GitHub

How to author and change files under specs/ - the state side of the state/motion split

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 130 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Every spec carries ## Out of scope: the adjacent capability a reader would assume is included, and where it went.

    line 19
  2. Very specific:

    Every spec opens with the context-hierarchy / context-hierarchy-role / immutable / tags frontmatter block in specs/README.md.

    line 28
  3. Very specific:

    After amending a spec, run the ripple check: grep -l '<spec path>' plans/*.md, then flag the plans chasing the old desired state.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 130 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

Working under specs/

specs/ declares what MUST be true - permanent desired state, changed only by review. The full protocol is specs/README.md; the authoring bar and templates are ICM/_config/reference-standard-spec.md. Read both before writing.

The rules that bite most often:

  • Specs state behaviour observable from outside the implementation - invocation, outputs, failure modes, errors. Never function names, module paths or test cases; those rot on the first refactor.
  • Every spec carries ## Out of scope: the adjacent capability a reader would assume is included, and where it went. Edge cases stay in the spec too, as If <trigger>, then criteria.
  • Behaviour is stated in EARS (ICM/_config/reference-standard-validation.md). The prose about authoring a spec stays in modal form; the requirements inside one do not.
  • The level-of-detail test: could two implementers read it and disagree about whether the code conforms? If yes, it is too vague.
  • A new spec on the default branch needs an owning plan unless the behaviour already exists - named in that plan's specs: if code changes to conform, its authors: if the plan only writes the spec. Invariant 1 in specs/README.md.
  • Every spec opens with the context-hierarchy / context-hierarchy-role / immutable / tags frontmatter block in specs/README.md. Without it the spec is not routable by layer.
  • After amending a spec, run the ripple check: grep -l '<spec path>' plans/*.md, then flag the plans chasing the old desired state.
  • Spec/code divergence is a bug, not debt. Fix the code or amend the spec - never work around a spec in code.

Spec authorship belongs to ICM stage 01 (/icm:specify). Editing a spec mid-implementation is a re-entry decision, not a quiet patch.

Download now (ZIP)

  • Other versions151 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 151

    1. garrytan/gstack★ 139ksame name
    2. getsentry/sentry-react-native★ 1.8ksame name
    3. JuliusBrussee/cavekit★ 1.1ksame name
    4. kdlbs/kandev★ 1ksame name
    5. getsentry/sentry-dart★ 877same name
    6. poshan0126/dotclaude★ 871same name
    7. SparkDevNetwork/Rock★ 692same name
    8. hyperlink-academy/leaflet★ 525same name
    9. strands-agents/box★ 471same name
    10. menkesu/awesome-pm-skills★ 441same name

    141 more not listed

    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.

  • Used alongsideProjects with it also use backprop, ios-clean 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.
    • 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

    • Saqlain-811Skill

      ios-clean

      Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

      Also in 5 projects that use this

    • Saqlain-811Skill

      ios-fix

      Autonomous iOS bug fixer. (gstack)

      Also in 5 projects that use this

    • bastosSkill

      ios-design-review

      Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".

      Also in 5 projects that use this

    • ShreyRaviSkill

      benchmark-models

      Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".

      Also in 5 projects that use this

    • ShreyRaviSkill

      plan-tune

      Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.

      Also in 6 projects that use this

    • +3 more from Saqlain-811
    • +3 more from ShreyRavi
  • 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.

Check your setup, free