agentleFS
Sign inStart free
KemetraKemetra/Seshat-BI/.claude/skills/capabilities/SKILL.md

capabilities

Skill2 starsChanged 4 months agoApache-2.0View on GitHub

Show the read-only capability inventory for this kit -- each capability by lifecycle state, authority, requirements and provenance. Use when someone asks what the kit can do or what works without a database. Writes nothing and emits no score.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the module directly from the repo root:

    line 26
  2. Very specific:

    Not a scoring surface: No maturity/confidence/completeness/health value is ever emitted, and nothing is ranked by a computed number.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 3 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

capabilities

The read-only capability inventory: one truthful, categorical read of everything Seshat BI can do, derived from committed, reviewable metadata (never from a file's mere existence).

What it does

Reads the committed capability manifest (docs/capabilities/capabilities.yaml) and reconciles it against the feeders that already own each fact -- the _DISPATCH command table, .claude/skills/*/SKILL.md frontmatter, .seshat/kit-source.yaml verbs, docs/roadmap/roadmap.md F-numbered ship status, and docs/quality/status-claims.yaml -- then renders:

  • a grouped human-readable read (the default), or
  • a stable, deterministic JSON machine form (--format json).

How to invoke it

Run the module directly from the repo root:

python -m seshat.capability_inventory
python -m seshat.capability_inventory --format json

There is no retail capabilities / seshat capabilities CLI verb -- this is a deliberate, ratified choice (docs/roadmap/decisions/cli-verbs-vs-skill-driven.md, Option B). Do not add one; do not touch src/seshat/cli/parser.py or _DISPATCH to "wire this up". Simply run the module command above and relay its output.

What it is NOT

  • Not a gate. It adds no seshat check rule; its presence/absence never blocks anything.
  • Not a readiness surface. It reads no readiness-status.yaml, moves no stage, grants no approval. For per-table readiness use seshat status; for the next allowed action use seshat next; for repo drift use seshat doctor; for the governance gate use seshat check.
  • Not a scoring surface. No maturity/confidence/completeness/health value is ever emitted, and nothing is ranked by a computed number.
  • Not a writer. It writes nothing, connects to no database, runs no Power BI.

See also

  • docs/capabilities/README.md -- the fail-closed truthfulness contract and how this differs from status/next/doctor/check.
  • docs/capabilities/capabilities.yaml -- the manifest this skill renders.

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