agentleFS
opum-aiopum-ai/proof-skills/.claude/skills/lore/SKILL.md

lore

Skill27 starsChanged 52 days agoMITView on GitHub

Author, retrieve, and maintain OKF documentation with the lore CLI, including explicit multi-repository workspaces. Use whenever reading, writing, linking, moving, querying, or checking docs, so Story/Task coupling, managed blocks, provenance, and cross-links stay coherent. Run `lore instructions` for the canonical agent loop and `lore instructions <topic>` for just-in-time detail.

13 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

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

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 1

    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:

    Before the canonical workflow below, treat lore link, lore unlink, lore rename, and lore sync as self-committing commands: they can create …

    line 20
  2. Very specific:

    Run lore instructions for the canonical agent loop and the topic index, then pull just-in-time detail with lore instructions <topic>:

    line 31
  3. Very specific:

    Every command supports --json (the {schemaVersion, kind, data} envelope) and --plain (ANSI-free, auto-selected off a TTY).

    line 76
  4. Distinctive:

    When native Claude Code instructions name a committed Lore profile, use this stable opt-in line:

    line 82

“Common” is measured: kept by at least 6 in 10 of the 11 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

lore — OKF documentation CLI

lore is this repo's documentation engine: a deterministic, CLI-first tool (no LLM dependency) for authoring and maintaining the OKF bundle under docs/. This skill is a thin pointer — lore instructions is the source of truth for how to drive lore.

When to use it

Reach for lore — not a plain editor — whenever you read, write, link, move, retrieve, or verify docs in this repo or an explicitly selected workspace, so Story <-> Task coupling, managed blocks, provenance, and cross-links stay coherent.

Commit-side-effect preflight

Before the canonical workflow below, treat lore link, lore unlink, lore rename, and lore sync as self-committing commands: they can create commits under backlog/. Read the applicable repository instructions and verify explicit commit authority before invoking them. When the repository supplies .codex/skills/backlog-handover/scripts/lore-authority-preflight.mjs, dispatch those commands only through that gate with the exact Git worktree and in-repository scope. Without applicable authority, stop before Lore runs and request permission or record a deferred stage. This preserves the repository's Lore sole-committer contract.

Start here

Run lore instructions for the canonical agent loop and the topic index, then pull just-in-time detail with lore instructions <topic>:

  • linking Story <-> Task coupling (lore link / lore unlink)
  • sync reconcile status + managed blocks (lore sync)
  • check the CI gate: drift, links, anchors, portability (lore check)
  • validation per-file OKF/schema conformance (lore validate)
  • workspace multi-repository projection and bounded retrieval (--workspace)

Commands

  • backlog Adopt Backlog knowledge records through a digest-guarded migration lifecycle
  • init Scaffold an OKF bundle; a bare TTY run also wizards the agent bridge/scaffolds/backlog check
  • new Scaffold a typed concept from a template (rejects an unknown type under strict_types)
  • validate Check concept files against OKF + the lore profile (per-file); strict_types escalates an unknown type
  • check Validate links/anchors + reconciliation/committed-schema drift across the bundle (CI gate); strict_types escalates an unknown type
  • replace Find-and-replace across the bundle, skipping managed regions
  • rename Move a concept and repoint every inbound link + ref
  • supersede Mark a concept superseded by another, wiring both ways
  • link Add task ids to a concept's tasks: + the doc: back-ref
  • unlink Remove task ids from a concept's tasks: + the doc: back-ref
  • sync Reconcile status + managed task blocks, regen index/log, commit backlog/
  • tasks Show the live status rollup for a concept's linked tasks
  • orphans Report tasks with no owning doc + docs whose linked task vanished
  • schema Export the profile's editor JSON Schemas to .lore/schemas/ (the fix for lore check's schema-drift)
  • types Print the active profile's declared type vocabulary — fields, requiredness, sections
  • scaffold Generate a downstream docs consumer's config additively, rewriting nothing
  • graph Emit the bundle's cross-link graph as json or dot
  • path Find bounded paths across exact authored concept and task edges
  • impact Expand bounded impact across exact authored concept and task edges
  • snapshot Explicitly retain, list, or delete bounded projection snapshots
  • changed Compare two retained snapshots with bounded authored-fact deltas
  • provenance Trace one retained concept, task, or edge to exact source evidence
  • explorer Build a deterministic self-contained local graph explorer
  • export Emit a deterministic, consumer-neutral OKF projection as JSONL
  • query Full-text search the bundle with frontmatter filters
  • context Assemble a concept + neighbor summaries within a token budget
  • read Read one concept exactly as authored, with no budget and no assembly
  • agent List context profiles or compile bounded task-scoped evidence
  • instructions Print task-scoped agent guidance on demand
  • agents Regenerate the agent bridges (SKILL.md + the CLAUDE.md/AGENTS.md nudge)
  • help Show help, or the machine-readable command manifest under --json

Machine contract

Every command supports --json (the {schemaVersion, kind, data} envelope) and --plain (ANSI-free, auto-selected off a TTY). Branch on the semantic exit code, never on prose: 0 ok · 2 usage · 3 not_found · 4 denied · 5 conflict · 6 validation/drift.

Optional task-scoped context

When native Claude Code instructions name a committed Lore profile, use this stable opt-in line:

Lore profile: <name>. Before working, run lore agent context <name> --task "<assigned task>" and ground decisions in the returned source IDs.

Lore supplies evidence only. It does not create or patch native agents, prompts, tools, models, permissions, or execution settings.

<!-- Generated by `lore agents`; do not hand-edit. Re-run `lore agents --force` to refresh. -->

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.