Agent Skills
› szw321127/repowise
› pk-auto-crystallize
pk-auto-crystallize
GitHub用于任务结束时自动提炼项目知识,通过脚本分析任务上下文、文件变更及推荐匹配,生成实践节点并更新知识库。
Trigger Scenarios
用户希望自动总结任务经验
需要更新项目知识库实践
Install
npx skills add szw321127/repowise --skill pk-auto-crystallize -g -y
SKILL.md
Frontmatter
{
"name": "pk-auto-crystallize",
"description": "Use when the user wants task-end project knowledge crystallization to be inferred from the current task, touched files, and existing recommendation matches."
}
PK Auto Crystallize
Treat this skill as the preferred task-end entrypoint when the user wants the project knowledge loop to update with minimal manual JSON authoring.
Required Behavior
- Determine the target project root from an explicit path; otherwise use the current working directory.
- Resolve
../../scripts/pk-auto-crystallize.mjsrelative to thisSKILL.mdfile. - The wrapper delegates to
auto-crystallize-session.mjs. - If
.project-knowledge/project-profile.mdis missing, returnmode: no-knowledgeand skip crystallization entirely; do not scan touched files, create sessions, or create.project-knowledge/. - Prefer passing a JSON input file after the project path when the task summary, touched files, or session id are known.
- If
adoptedNodeIdsis omitted, allow the script to infer adopted recommended options frompk-preflightmatches. - Prefer explicit
touchedFiles;allowGitStatusFallbackmust be true before dirty git status is used as low-confidence evidence. - Accept
taskIdortaskDirfor generic task/process context. Prefer.tasks/<taskId>ortasks/<taskId>; compatible external workflow layouts such as.trellis/tasks/<taskId>are fallback inputs only. Treat process files as process sources and task text, not durable source evidence unless the project evidence policy explicitly allows them. - If
incubatingNodesis omitted and no practice matches, allow the script to create an incubating practice plus candidate option fromtaskTextandtouchedFiles. - Report the result in Chinese and include
mode, inferred adopted nodes, generated incubating nodes, touched files, task/process sources when present, and the next suggested skillpk-lint; when skipped because knowledge is uninitialized, suggestpk-initinstead.
JSON Input Shape
{
"sessionId": "session-YYYY-MM-DD-topic",
"title": "本轮任务标题",
"topic": "本轮任务主题",
"taskText": "用于匹配已有实践的任务描述",
"taskId": "",
"taskDir": "",
"decisionSummary": "一句话总结本轮关键决策。",
"touchedFiles": [],
"allowGitStatusFallback": false,
"adoptedNodeIds": [],
"rejectedNodeIds": [],
"incubatingNodes": [],
"stableUpdates": []
}
Version History
- fa4164e Current 2026-07-24 16:07


