计划执行与检查节点
executing-plans
按既定实施计划完成工作,保持过程检查和反馈。
lov-search-project【效率与协作】分层定位本机项目/源码目录:项目根优先,其次当前文件夹、AI 聊天记录,最后全盘 兜底,返回候选路径与证据。Use when locating a project on this machine: "找到 xxx 项目"、"这个项目在哪"、"where is the X project"、"find the source for X".
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
用户给出项目名、关键词或特征描述,Skill 在四层递进范围中定位候选目录, 每一层都标注命中来源与证据,供用户确认或继续深入。全程不修改任何文件。
lov-memory-search / lov-search-chatlov-finder-actionlov-find-logoEvery generated Skill is connected to the shared user-profile/v1 contract in
skill.yaml. Read the shared user, brand, workspace, preferences, and this
Skill's skills.<skill_id> namespace at the start of every run. Keep the source
portable: resolved personal values belong in the shared profile, never here.
workspace.projects(项目根目录列表)会追加到 CLI 的默认搜索根中,无需
硬编码路径。当用户直接说出「我常把项目放在 /xxx」这类长期事实,通过
scripts/profile_store.py 写入 workspace.projects 并报告保存路径。
When the user directly states a durable preference or brand fact, persist it
through scripts/profile_store.py and report the saved profile path. Put
Skill-specific values under records.<field>; use brand.<field> or
user.<field> for shared values. Do not persist inferred secrets or credentials.
See references/user-profile.md for the complete contract.
Read references/skill-composition.md before deciding whether to invoke or
extend any adjacent capability. The record distinguishes optional upstream and
downstream handoffs from embedded Kit modules. Do not silently depend on a
sibling Skill that is not shipped with this source.
You MUST follow these steps in order.
SKILL_DIR if the environment provides it.scripts/find_project.py(分层搜索 CLI,必需)scripts/profile_store.py(Profile 读写,必需)When running scripts manually:
export SKILL_DIR="/path/to/lov-search-project"
Resolve context.profile on every invocation. The precedence is current request,
project context, Skill-specific profile records, shared preferences, shared
brand/user profile, then safe defaults. A direct user statement about a durable
preference or brand fact should be saved with scripts/profile_store.py record
using --confirm, followed by a concise saved-path report.
claude code)。references/skill-composition.md 记录:与本 Skill 相邻的
lov-find-logo、lov-memory-search、lov-search-chat、lov-finder-action
均为不同能力,无重叠;lov-repo-takeover 是其下游可选交接(拿到路径后可
让用户决定是否接手仓库)。本 Skill 是 Single Skill,无需 Kit。--scope auto,roots 命中即停):python3 "$SKILL_DIR/scripts/find_project.py" "<查询词>" --json
按命中层解读结果(结果 JSON 中每条 hits[] 有 layer / path /
score / evidence):
roots:项目根目录集合内的直接子目录(最可靠)cwd:当前目录向下 4 层内的名字匹配chat:AI 聊天记录中提及过的路径(evidence 标注提及来源文件)full:Spotlight/全盘慢扫(噪声大,需要人工甄别)缩小范围或扩大范围:
--scope chat(从聊天记录找)或 --scope full(全盘兜底)。--scope full,仍未命中则如实说「本机未找到」,不要
编造路径。给出结论:列出 top 候选(默认 10 条内),每条标注命中层与证据。若 唯一性高(score 显著领先且语义吻合),明确指出推荐路径;否则请用户挑选。
可选后续:用户需要时,用打开的路径继续(查看结构、打开 Finder、
或询问是否需要 lov-repo-takeover 处理仓库)。
ls 验证)。full 层命中即使路径存在也可能是同名无关目录。profile_store.py 写入并报告保存路径。cases/cases.json。mdfind(可选,full 层使用;缺失时回退 find)