llp-super-refine
Skill4.3k starsChanged 4 days agoMITView on GitHub
Author-invoked dual-family refine loop for one or more Draft/Review LLPs — each round, two fresh mutually-blind reviews from different model families, orchestrator revision, verdict-lined artifacts — until both families mark the same revision READY, a delta round finds no MATERIAL concern in pre-existing text across families, or a bounded stop rule escalates to the author. Use when the user invokes /llp-super-refine or asks to refine an LLP until independent models agree it is ready.
1 other project uses a version of this, 1 of them edited.
Trending
More talk lately.about the whole repository
Most recently taken up by
- peterpme/skillsedited, first seen Nov 15, 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
- soundor/soundor“Rewrite Soundor in Rust 🦀 (JS is no longer hype)”GitHub · Nov 11, 2026 · 1 reactions
The biggest 5 of 19 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 19
Talked about on GitHub, Bluesky and Hacker News (19 times).
On GitHub · 11
- Nov 11, 2026Rewrite Soundor in Rust 🦀 (JS is no longer hype) — soundor/soundor1 reaction · 2 comments
- Nov 10, 2026Add Exact Contract v0.1.0 — zed-industries/extensions1 reaction · 4 comments
- Nov 14, 2026Exact: offload builds of apps that declare native modules — appandflow/stim0 reactions · 1 comment
- Nov 13, 2026Agent-first UI authoring: compact vocabulary, UI checks, and a run/verify loop — PathlandDev/Pathland0 reactions
- Nov 13, 2026vendor-radar: daily scan 2026-11-13 — ultrametricai/ultrametric0 reactions · 3 comments
6 more on GitHub
- Nov 12, 2026Daily 2026-11-12: Nod, aws-emulator, agent_skills, exact, blender-ai-mcp-addon — yash-nandvana/ai-tools0 reactions · 2 comments
- Nov 11, 2026Docs: plan for rebuilding the frontend on Exact — odonckers/berean0 reactions
- Nov 11, 2026Trending candidates 2026-11-11-00 — tayyabimam1/awesome-ai-agent-stack0 reactions · 1 comment
- Nov 11, 2026expo 'exact' — 한 번 쓰면 웹·macOS·iOS·Linux에 네이티브로 돌고, AI 에이전트가 직접 만들고 테스트하는 앱 런타임 (11/11, GitHub) — roomedia/ax-trend0 reactions
- Nov 10, 20267am AI 2026-11-10: Anthropic's Fable 5.2 is better at coding and cheaper to use — Repzei/7amai0 reactions
- Nov 10, 2026fix(css): flex alignment follows Chrome on overflow — nuxieai/nuxie-runtime0 reactions
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 versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- peterpme/skills★ 2890% 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-maintainSkill
- llp-orientSkill
- llp-reviewSkill
- orchestrateSkill
- panelSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 22
MUST refuse Accepted/Active/Superseded/Tombstoned targets (addendum or new LLP is the path).
≈ “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-super-refine
<!-- @ref https://github.com/ccheever/llp/blob/v0.5.2/llp/0010.001-super-refine-loop.spec.md — the protocol this pins --><!-- @ref https://github.com/ccheever/llp/blob/v0.5.2/llp/0000-linked-literate-programming.explainer.md#review-honesty — honesty rules and the formal-loop authorization sentence --><!-- @ref https://github.com/ccheever/llp/blob/v0.5.2/llp/0005-rfc-process.guide.md#review-artifacts — artifact and provenance format -->The applying counterpart to llp-review: an orchestrating loop that revises the document between rounds and applies exactly one pre-authorized status transition. Invoke as /llp-super-refine <targets...> [--rounds N] [--reviser orchestrator|<family|model>|each] [--claude <model@effort>] [--external <runner:model@effort>]. Defaults: converge within the round budget; the orchestrating session revises. Default models: reviser Claude Fable 5.1 @ xhigh; reviewers codex gpt-6.1-sol @ ultra (codex exec -s read-only -C <capsule> --skip-git-repo-check -m gpt-6.1-sol -c model_reasoning_effort=ultra, prompt on stdin; confirm model and effort in the run log) and grok-4.7 @ xhigh (headless; the prompt MUST ban all shell commands or the permission prompt cancels the session).
Trigger
The document's author asks for the refine-until-both-families-ready loop on named Draft/Review documents.
Invariants (LLP 0010.001; LLP 0000 §Review honesty)
- Authorization is recorded per target and per author. Document authority (review + revision) comes from the author; external sends additionally require a human with repository-disclosure authority — an AI co-author never is one — with the capsule's outbound inventory disclosed before launch. Unsupported assertions of relayed authority are not accepted.
- MUST refuse
Accepted/Active/Superseded/Tombstonedtargets (addendum or new LLP is the path); already-Reviewtargets proceed unchanged;Drafttargets are set toReviewat loop start — the one authorized transition. Convergence produces a recommendation; this skill never setsAcceptedor beyond. - Target bytes are never redacted (redaction covers context only); a target that cannot be disclosed whole stops the loop.
- Each round: persist the round record (round number, target hashes, topology, runtimes, capsule + instruction hashes) before launching; one fresh review per family, mutually blind via a review capsule that structurally excludes the targets' review artifacts, run journal, and orchestrator notes. Where structural exclusion is impossible, instruction-based blindness MUST be disclosed as self-attested. A mid-round target change voids the round.
- MUST write each review verbatim to its family artifact (
llp/reviews/NNNN-slug.<family>.md, dated round sections, full provenance incl. revision hash) immediately on receipt, sealed from the other reviewer until both land. Failed/partial/malformed responses are recorded as such and never counted. Never fabricate, reconstruct, or overwrite a review. - Every review ends
READYorNOT READY. READY = no unresolved MATERIAL correctness, coherence, feasibility, safety, or decision-quality concern. Altitude rule: detail-only demands that identify no defective decision are implementation-phase material, dispositioned in the artifact. Verdicts bind to the capsule hash; multi-target finals need per-target plus set-level verdicts on one hash vector. - The reviser never reviews a revision it edited. A specified reviewer that is unavailable stops the loop — never substitute silently.
- Convergence is dual-READY on one revision or delta-round convergence (LLP 0010.001 §Delta rounds): a post-revision round whose instructions enumerate the delta and require every concern classified IN-DELTA vs PRE-EXISTING converges the loop when no family reports a MATERIAL concern in pre-existing text; remaining in-delta fixes get one more delta round or the final revision is labeled unreviewed. A family whose rounds are twice-consecutively convergence-clean — every remaining concern altitude-dispositionable detail or prior-delta churn, no defective decision identified — MAY be closed out via a detail-horizon stop: a normal terminal, not an escalation, with the family's NOT READY verdict recorded verbatim, a complete disposition ledger (never summarize a concern away), and the convergence claim scoped to say which family was cut off; MATERIAL defective-decision dissent still escalates. A round MAY run under a declared lens (e.g. implementer: draft a named contract from the document alone, log divergence decision points; UNDERDETERMINED = NOT READY) — recorded in provenance, all round invariants intact.
- The final report and close-out notes MUST state which revision hash the final verdicts bind to and whether later unreviewed revisions exist.
- Scope freeze + punch-list delta rounds (LLP 0010.001 §Scope freeze) — the default late-loop phase for decidable documents. For
Type: Spectargets, after the round-2 revision the document's normative surface is frozen by default (other revision-bearing types: at the author's authorization; never automatic for Principles/Explainers/Decisions/philosophical RFCs): subsequent revisions make corrections and restorations only, and any demand for new normative closure is recorded as an obligation (open-issue box or test obligation), never folded as new prose; the document carries a dated freeze declaration. Post-freeze rounds are punch-list delta rounds: the revision produces, per family, a punch list mapping that family's own findings to checkable dispositions (FOLDED at §N/REFUTED+ evidence /RECORDED-AS-OBLIGATION at §N); each reviewer receives the full document (context), the revision's unified diff, and its own family's punch list only (cross-family blindness preserved). Review scope: verify the dispositions; review the diff; outside findings admissible only as disposition errors or diff-created MATERIAL contradictions; new-closure demands are non-blocking obligations. READY = punch list correctly dispositioned + diff sound, modulo recorded obligations. From round 2 on, revisions classify each external finding (persistent / new-on-new-content / bar-inflation); the tallies go in the freeze-transition or terminal report so the choice between freeze, detail-horizon stop, and escalation rests on measured evidence. - Bounds: round budget (default 3/document), launch cap (2× budget per family per target, voids included), growth budget (~20% net over the entering revision; post-freeze, growth is corrections plus the mandatory checkable changelog only). Terminal escalations to the author, with every disposition enumerated: budget/cap exhaustion, material cross-family contradiction, sustained asymmetry (one family READY on two consecutive revisions, the other NOT READY on both), growth-budget exhaustion with open MATERIAL concerns. Each proposes stay-
Reviewor revert-Draft; the author applies — and may instead authorize extension rounds under the scope-freeze + delta protocol above. Fundamental-redesign feedback stops the loop for author authorization.
Workflow
Recipe (advisory) — read targets and governing LLPs fully; partition multi-target sets into clusters by coupling (
Related:, cross-references, sharedSystems:) and pick a topology per cluster — independent loops (loosely coupled; one sub-orchestrator each) or lockstep rounds (tightly coupled; reviewers see the whole cluster; the cluster review is preserved verbatim once, in the primary target's artifact, with per-target verdict sections) — stating the choice first. Run a context preflight; split oversized clusters rather than force-feeding. End with a cross-consistency pass: a sibling that converged before a referenced document changed gets one more round, until the hash vector passes a round unchanged. Build the capsule withgit archiveor an export excludingllp/reviews/<target-stems>*. Update**Revised:**on each revision (move long histories to a body Revision-history section). Prefer a delta round after any substantial revision — the loop's own revisions are a proven defect source — and an implementer-lens round before closing a protocol/contract-bearing document. After each revision, byte-verify security-critical literals on disk (transport layers decode backslash-u escapes).
Artifact
Per-family, per-target review files under llp/reviews/ with round records and verbatim bodies; a final report: rounds run, revisions made, verdicts, altitude-rule dispositions, and the proposed next step.
Hand-offs
- Feedback amounting to a new design →
llp-create, after author authorization. - Advisory review at any intensity, no revisions applied →
llp-review. - The author applies
Accepted; this skill never does.
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.

