跳到主要内容
知仓学习社ZHICANG

session-finder

Index and search Claude Code sessions using semantic embeddings (Gemini). Find past sessions by topic, relaunch the best match. Triggers on "find se…

执行命令读文件严重 0 · 高危 1glebis/claude-skills

它会碰到什么

扫了多少3 个文本文件,18 KB
它会碰到什么执行命令读文件
命中总数2 处
命中统计严重 0 · 高 1 · 中 1 · 低 0
逐条看命中(1 条严重或高危)
  • scripts/session_finder.py:218exec-spawn
    result = subprocess.run(

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

Session Finder

Semantic search across Claude Code sessions using Gemini embeddings.

Commands

Index sessions

python3 ~/.claude/skills/session-finder/scripts/session_finder.py index [--max-age-days 90]

Search

python3 ~/.claude/skills/session-finder/scripts/session_finder.py search "query" [--top 5]

Open best match directly

python3 ~/.claude/skills/session-finder/scripts/session_finder.py open "query"

Stats

python3 ~/.claude/skills/session-finder/scripts/session_finder.py stats

How it works

  1. Document extraction — deterministic, no LLM. Each session JSONL is parsed into a structured document:
  • away_summary events (pre-existing Claude recaps) if available
  • First user message (task description)
  • Follow-up user messages (condensed)
  • First assistant response
  • Tools used
  • Project name
  1. Embedding — documents are embedded with gemini-embedding-exp-03-07 via llm CLI
  2. Storage — SQLite at ~/.claude/session-finder.db
  3. Search — query is embedded, cosine similarity ranks all sessions, top match is the default to open

Workflow

When user asks to find a session:

  1. Run search with their query
  2. Present results with confidence scores
  3. Offer to resume the top match via claude --resume <id>

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。