Index of every page on this site: llms.txt
All skills
expo avatar

/llp-maintain

@f428a37
by expoexpo/exact4.7k stars
132
Run it yourself

Keep an LLP corpus in sync with its code. Detects code/doc drift, validates @ref annotations interactively, checks provenance tags, and proposes reconciliations, ref repairs, status changes, and overlay changes. Modes — pre-pr, audit, reconcile, retire-proposal, curate (the promote → archive → realign pass). Proposes; never applies.

  • 1 file
  • 4 KB
  • Updated 2 weeks ago
  • GitHub
Use this Skill: https://skilld.dev/gh/expo/exact/llp-maintain

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈89 tokens for metadata: the name and description. ≈932 when used: this file.

Description uses 4.4% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈349 characters, or 4.4%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

llp-maintain

<!-- @ref https://github.com/ccheever/llp/blob/v0.5.2/llp/0004-design-principles.principles.md — co-evolution and living documents, the model this operationalizes --> <!-- @ref https://github.com/ccheever/llp/blob/v0.5.2/llp/0000-linked-literate-programming.explainer.md#6-validation-ref-check — the deterministic subset lives in ref-check, not here --> <!-- @ref https://github.com/ccheever/llp/blob/v0.5.2/llp/0011.000-curation-pass.guide.md — the curate intent follows this procedure -->

The upkeep engine. Living documents rot into misleading guidance unless code and docs co-evolve; this skill finds the drift and proposes fixes. The propose-only line is what lets one skill cover four maintenance moments without becoming a mega-skill.

Invoke as /llp-maintain --intent <pre-pr | audit | reconcile | retire-proposal | curate> (each has a sensible default scope).

Trigger

Before opening a PR (pre-pr, the common case); periodically or on suspicion (audit); after a pull or against a branch (reconcile); "this doc looks done/stale" (retire-proposal); after design work lands, before a release, or on cadence (curate).

Invariants

  • MUST propose, never apply: no edit, ref repair, or status change without sign-off. Output is a reviewable checklist or diff, never a mass rewrite.
  • MUST NOT classify untagged rationale claims silently — flag them for the author to mark [observed]/[confirmed]/[inferred].
  • curate MUST run its three verbs in order — promote, archive, realign — and MUST realign the code only against llp/foundation/, never against the whole corpus. Promotion proposals MUST apply LLP 0000's admission test (design recreatable from the set; set-level; too-small fails), not importance.
  • MUST NOT claim to be a CI gate. The deterministic, merge-blocking checks are ref-check's job; this skill is the interactive, judgment-bearing complement.

Checks

For @refs in scope: broken target/anchor (error — list the anchors that do exist); tombstoned/superseded target (warning, note the replacement); stale gloss (hint); orphaned annotation whose attached construct is gone (warning). For provenance-tagged docs: [inferred] in Accepted/Active (error); [observed] without a stated location, or [confirmed] without name+date (flag for the author). For installed skills: a source: pin that lags upstream releases (note, when network allows). Beyond the mechanical: code whose behavior no longer matches the section it references; new files implementing a documented LLP with no @ref; LLP sections the diff contradicts.

Modes

Intent Default scope Artifact
pre-pr working tree co-evolution checklist ("update doc or code" / "repair ref" / "consider annotating") + proposed status changes, not applied
audit corpus findings list: drift, broken refs, stale statuses
reconcile diff range / branch per-doc reconciliation proposals (or "the code drifted, not the doc")
retire-proposal one named doc a drafted Superseded/Tombstoned proposal with rationale (a status change in the header — files never move)
curate overlays + foundation vs. code the PROMOTE / ARCHIVE / REALIGN checklist of LLP 0011.000: links to add or remove, folds, status fixes, and code changes foundation now demands

Hand-offs

  • A reconciliation that is really a new design decision → llp-review.
  • Broken refs surfaced by llp-orient land here for repair proposals.
  • A stale source: pin noted by audit → /llp-adopt update applies the update after an approved diff (this skill never applies).
  • Deterministic CI enforcement → ref-check.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at f428a37. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago
source
ccheever/llp@v0.5.2

README badge

README badge for expo/exact/llp-maintain