Create or maintain a source-grounded kpopper knowledge model as a versioned plugin. Use when a reusable domain model should ship independently of any one project.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Use this skill for a reusable, source-backed model that people should install and query across projects. An ordinary project record, a one-off answer, or a case adapter alone is a different task.
The generated plugin and packaging workflow are currently qualified for local Codex on macOS ARM64. This skill's presence in another host does not establish support there. The companion is an unreleased source candidate; use a maintainer-supplied qualified prebuilt toolchain.
Read the authoring guide. The complete example is a separate packaging walkthrough; do not copy its record or history over a model you have authored. Define the scope, source closure, unknowns, independently expected questions and plugin descriptor before packaging.
Author records with the native kpop commands. Do not hand-edit generated GROUNDING.yaml or history. Preserve a person's case in a disposable workspace, never in the reusable model. Use the release-qualified prebuilt kpop-model build tool and bundled engine when they are available; model authors should not compile Rust or install another language runtime. If either artifact is missing, save the authored model and report the missing packaging prerequisite.
Before native authoring, set XDG_CACHE_HOME to a private writable directory outside the model, within the task's existing allowed paths. The engine needs its runtime cache even with --no-cache; do not rely on a writable home directory or broaden host permissions. Keep this transient cache out of the committed model and package.
A read model needs only the standard native reader. Recorded rules run through the native engine too. A domain application that adds case-specific input binding or output projection must supply a separately tested native adapter and maintainer-owned build. Keep that obligation separate from model authoring.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Annotated Documents: optional experimental application for standalone HTML with evidence. Use when the user explicitly requests Annotated Documents or a kpopper HTML document with evidence, refreshes an existing kpopper document, or has a standing preference for this application. Generic HTML requests do not select it. Install the HTML runtime before use. Not for the record's own page or an ordinary website. Requests come in any language.
中文简介正在准备中。当前显示原文说明。
Test, fold or refute hypotheses beside the knowledge record, and reconcile records across branches. Use when open or check say hypotheses wait or an id is CONTESTED, when a write was refused into a hypothesis, before merging a branch whose record changed, and when a pull request's dry run or remeasure is red. Covers consolidate --dry-run, the fold, --refute, --from, same and distinct at the fold, and remeasure.
中文简介正在准备中。当前显示原文说明。
Compatibility alias for Annotated Documents. Use when explicitly invoked as $document or /kpopper:document. Follow the canonical annotated-doc skill; do not select this alias for ordinary requests.
中文简介正在准备中。当前显示原文说明。
Read the project's knowledge record before answering from memory or from the files. Use before answering about the project's state, a number, a date, a decision, a source, a deadline or what was agreed - even a casual 'what's the situation with X' or 'is that quote still current'; before changing a recorded value; and whenever the opener or a grounding line names entries. After finding relevant IDs, prefer kpop context to read them with their declared dependencies and checks. Uses pull for concise readings or when the checked reader is unavailable, affects for changed inputs, and search when no ID is known. A missing id is not absence. Not for showing the record's page (the hub skill). Requests come in any language.
中文简介正在准备中。当前显示原文说明。
kpopper Hub: optional experimental application for exploring the project record. Use when the user explicitly requests kpopper Hub or its record page, its graph, layout or verification, or has a standing preference for this application. Do not render automatically after mapping or recording. Install the HTML runtime before use. Not for ordinary HTML documents or a text answer from the record. Requests come in any language.
中文简介正在准备中。当前显示原文说明。
The kpopper method: a knowledge record (GROUNDING.yaml) for work that gets revisited - what is known, where each piece came from, and what would make each conclusion wrong. Use when asked what kpopper is or how to keep a record, when choosing which kpopper skill fits a moment, or when no narrower one does. The occasions have their own skills: ground (read the record before answering), record (write what the work found), map (map existing materials), annotated-doc (a standalone HTML document with evidence), hub (the record's visual home), consolidate (hypotheses and merges), watch (background checks).
中文简介正在准备中。当前显示原文说明。