agentleFS
electrohireelectrohire/spec-kit-evaluator/.github/skills/speckit-aee-gaps/SKILL.md

speckit-aee-gaps

Skill3 starsChanged 27 days agoMITView on GitHub

Generate or update the gap register from a verification matrix and test

  • Installs packages

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Only close gaps when evidence explicitly shows a passing test.

    line 53
  2. Distinctive:

    Do not modify the verification matrix during gap generation.

    line 55

≈ “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

Aee Gaps Skill

AEE Gaps

Generate or update the project gap register (GAPS.md) by cross-referencing the verification matrix against available test evidence.

User input

$ARGUMENTS

Accept matrix=<path>, evidence=<dir>, and optional output=<path>, close=<GAP-ID>, existing=<path>. Infer the verification matrix at .specify/extensions/aee/docs/verification-matrix.md and the evidence directory at evidence/ when omitted.

Prerequisites

  1. Do not install the engine yourself. The runner uses an aee engine in the range >=1.5.0,<2 from the active Python; otherwise its first run installs applied-epistemic-engineering>=1.5.0,<2 into .specify/extensions/aee/.runtime (this needs network access once). If the runner refuses (exit 2) because that install is disabled (SPECKIT_AEE_AUTO_INSTALL=0) or failed, stop and relay its message, which names the manual python -m pip install "applied-epistemic-engineering>=1.5.0,<2" command.
  2. Confirm the verification matrix file exists. If absent, stop and recommend creating .specify/extensions/aee/docs/verification-matrix.md first.
  3. Resolve the project root. Never follow symlinks or read outside the project root.

Execution

Run:

python .specify/extensions/aee/scripts/python/run_aee.py gaps --matrix "<matrix>" --evidence "<evidence>" --output "<output>"

Manual closure does not validate evidence automatically. Inspect passing evidence first; then use the existing register as --output to close a specific gap:

python .specify/extensions/aee/scripts/python/run_aee.py gaps --matrix "<matrix>" --evidence "<evidence>" --output "<output>" --close GAP-XXX

The adapter writes the gap register only when output=<path> is supplied; otherwise the engine prints it to stdout. Choose an explicit in-project path such as GAPS.md. Pass --existing "<prior-register>" when regenerating if you intend to preserve prior closed gaps. The adapter does not read the YAML reference configuration.

Evidence confinement is a runner-side pre-flight: before the engine runs, the adapter walks the evidence tree and refuses (exit 2, naming the offenders) any symlink and any entry resolving outside the project root, so out-of-root data can never close a gap. Keep evidence as real files inside the project.

Report the open/closed counts and list any open gaps. Do not describe the register as proof of correctness — it tracks verification coverage only.

Guardrails

  • Only close gaps when evidence explicitly shows a passing test.
  • Pass --existing to preserve previously closed gaps across regenerations; review whether the old evidence still applies.
  • Do not modify the verification matrix during gap generation.
  • The gap register is a tracking artifact, not a certification.

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.