llp-maintain
Skill4.3k starsChanged 3 days agoMITView on GitHub
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.
2 other projects use a version of this, 1 of them edited.
Trending
More talk lately.thin dataabout the whole repository
Most recently taken up by
- peterpme/skillsedited, first seen Nov 15, 2026
- expo/expo-device-hubword for word, first seen Nov 8, 2026
Who's talking about expo/exact
- A Hacker News story“Exact – a new cross platform UI framework”Hacker News · Nov 9, 2026 · 137 points
- A Hacker News story“Exact by Expo: A Rust-based cross-platform native app runtime”Hacker News · Nov 9, 2026 · 5 points
- @keith.bsky.social“Or make something new! github.com/expo/exact”Bluesky · Nov 12, 2026 · 2 likes
- @ccheever.com“Still a work in progress but I think it's ready for others to try it out. Here's the repo: …”Bluesky · Nov 9, 2026 · 2 likes
- @yug1224.com“ウェブやネイティブ環境で高速に動くExpoの新しいクロスプラットフォームUIフレームワークっぽい マルチプラットフォーム対応のアプリ開発で試したい yug1224 starred expo/exact …”Bluesky · Nov 10, 2026 · 1 likes
The biggest 5 of 8 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 8
Talked about on Bluesky and Hacker News (8 times).
On Bluesky · 6
- Nov 12, 2026Or make something new! github.com/expo/exact — @keith.bsky.social2 likes and reposts
- Nov 9, 2026Still a work in progress but I think it's ready for others to try it out. Here's the repo: https://github.com/expo/exact — @ccheever.com2 likes and reposts · 1 reply
- Nov 10, 2026ウェブやネイティブ環境で高速に動くExpoの新しいクロスプラットフォームUIフレームワークっぽい マルチプラットフォーム対応のアプリ開発で試したい yug1224 starred expo/exact https://github.com/expo/exact — @yug1224.com1 likes and repost
- Nov 10, 2026I cant keep up man github.com/expo/exact — @dw.whey.party1 likes and repost
- Nov 10, 2026expo/exact https://realtime.jser.info/2026/11/10/expo-exact/ https://github.com/expo/exact Web/macOS/iOS/Linux向けのクロスプラットフォームアプリケーションランタイム。… — @jser.info1 likes and repost
1 more on Bluesky
- Nov 10, 2026Web/macOS/iOS/Linux向けのクロスプラットフォームアプリケーションランタイム。 宣言的なContract言語でUIを定義し、TypeScriptまたはRustでデータ処理を記述する。… — @azu.bsky.social1 likes and repost
On Hacker News · 2
- Nov 9, 2026Exact – a new cross platform UI framework137 points · 109 comments
- Nov 9, 2026Exact by Expo: A Rust-based cross-platform native app runtime5 points
Other versions2 projects use a version of this.
Word for word · 1
- expo/expo-device-hub★ 285100% same
Edited · 1
- peterpme/skills★ 2892% same
Wrote their own version · 0
None found.
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.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llp-adoptSkill
- llp-createSkill
- llp-orientSkill
- llp-reviewSkill
- llp-super-refineSkill
- orchestrateSkill
- panelSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Very specific: line 19
Before opening a PR (pre-pr, the common case).
- Distinctive: line 23
MUST propose, never apply: no edit, ref repair, or status change without sign-off.
- Very specific: line 24
MUST NOT classify untagged rationale claims silently — flag them for the author to mark [observed]/[confirmed]/[inferred].
- Very specific: line 26
MUST NOT claim to be a CI gate.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
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]. curateMUST run its three verbs in order — promote, archive, realign — and MUST realign the code only againstllp/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-orientland here for repair proposals. - A stale
source:pin noted byaudit→/llp-adopt updateapplies the update after an approved diff (this skill never applies). - Deterministic CI enforcement →
ref-check.
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
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.

