菜单
Before editing a subsystem, file, or starting a task, assemble the governing LLP context — read the root LLP, follow the @ref annotations on the code in scope, and find the LLPs covering the relevant systems. Produces a compact context pack of the constraints a change must respect. Read-only.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
| name | llp-orient |
| description | Before editing a subsystem, file, or starting a task, assemble the governing LLP context — read the root LLP, follow the @ref annotations on the code in scope, and find the LLPs covering the relevant systems. Produces a compact context pack of the constraints a change must respect. Read-only. |
| source | ccheever/llp@v0.3.0 |
Load the design rationale governing the area you're about to touch, before touching it. This is the consumption side of LLP — orienting first is what turns @ref from a possibility into a habit.
Invoke as /llp-orient <path-or-task> (file, directory, subsystem, or task description). With no argument, use the current change scope (git diff --name-only).
Start of a coding task that touches an area with documented design. The orient-first rule lives in the repo's always-loaded AGENTS.md; this skill is the detailed form that rule routes to for non-trivial work — don't rely on ambient description-match alone.
LLP NNNN#anchor rather than paraphrasing sections.@ref — report it and hand off to llp-maintain.Recipe (advisory) — read the root LLP first (systems vocabulary, where things live).
Grep '@ref'over the files in scope andReadeach target — these are the highest-signal context.Grepthe**Systems:**headers acrossllp/for LLPs governing the subsystems touched; read the governing ones (Spec, Decision, Principles, relevant RFCs). FollowRelated:and nearby@reftargets one hop out; stop there unless something is clearly load-bearing.
A context pack with these sections, faster to read than the documents it points at:
LLP NNNN#anchornone | llp-adopt | llp-create | llp-review | llp-maintainllp/ missing or stub) → llp-adopt.llp-create (or llp-review if proposal-shaped).@ref target or anchor doesn't resolve → llp-maintain.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.
Create a new LLP document with the next available number, the NNNN-slug.type.md filename convention, and a scaffolded metadata header — or extend an existing LLP when one already covers the topic.
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, and status changes. Modes — pre-pr, audit, reconcile, retire-proposal. Proposes; never applies.
Run the LLP 0005 review loop for an LLP document — orchestrate reviews from other model families, write one provenance-tracked artifact per review actually received under llp/reviews/, and never fabricate a review or accept on the author's behalf. Review intensity scales with stakes; the author decides when it's enough.
Take one or more tasks (Linear tickets, ticket files, accepted LLPs, free text) end to end — plan lanes, implement in run-namespaced worktrees, integrate on a run branch, verify and review the exact integrated commit, deliver per repo policy (direct push by default), and clean up without destroying recoverable work. Use when the user invokes /llp-ship or hands over tasks to be implemented and shipped.
Bring LLP to a repository and keep its installed skills current — the single entry point for "set up LLP here" and "update the LLP skills". Scaffold mode (fresh structure), retrofit mode (survey the codebase, draft a provenance-tagged root LLP, propose an adoption plan), install step (copy skills from a tagged release with a receipt), and update mode (verified, diff-approved skill updates).