agentleFS
Sign inStart free
sunnysxgsunnysxg/claude_skills/session-search/SKILL.md

session-search

Skill0 starsChanged 3 months agoMITView on GitHub

检索已归档的历史 agent session 摘要（关键词、项目、时间、未竟事项）。 用户指向上次/最近的 agent 工作（最近的 session、上次那个 chat、接着上次、哪次改过）， 且 CLAUDE.md、README、_sxg/ 等项目文档不足以回答时，先查归档再答。 仓库文档或源码能直接回答的问题、与历史 session 无关的新任务、handoff 交接待办，不用本 skill。

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ml-training-recipe, replication and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • getcompanion-aiSkill

    ml-training-recipe

    Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, train, reproduce, or choose a practical ML method, dataset, hyperparameter setup, or benchmark recipe.

    Also in 3 projects that use this

  • getcompanion-aiSkill

    replication

    Plan a replication of a paper, claim, or benchmark, and execute only after an explicit environment choice. Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package.

    Also in 3 projects that use this

  • brainbytes-devSkill

    alpha-research

    Also in 3 projects that use this

  • JaimeParkerSkill

    paper-code-audit

    Perform three-way cross-validation of a research paper by comparing the original paper text (via Zotero), official code implementation (via Git), and personal Obsidian notes. Use this skill whenever the user wants to "audit a paper", "verify paper claims against code", "cross-check notes with implementation", "triangulate paper + code + notes", "find discrepancies between paper and code", or mentions wanting a deep, structured comparison of a paper's claims against its implementation and their own notes. Also trigger when the user asks to "analyze this paper thoroughly" with code available, or when they want to systematically reconcile what the paper says, what the code does, and what their notes claim.

    Also in 3 projects that use this

  • JimLiuSkill

    pdf-explore

    Use this skill when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, or find/list/extract every instance of something across the whole document (datasets, benchmarks, citations, figures, table rows, accession numbers — including appendices). Skip it only for a single lookup of 1–4 pages quoted in your very next response — `read_file(pages=[...])` attaches pages as images that are dropped from context after one turn, so multi-section answers end up re-reading the same ranges repeatedly. Parses the PDF once in the Python kernel: `pdf_pages` (pages as persistent text), `pdf_outline` (TOC), `pdf_scan` (rank pages by relevance), `pdf_map`/`pdf_extract` (per-page summary / structured fields via parallel haiku calls). For PDF creation/manipulation, use reportlab/pypdf directly.

    Also in 3 projects that use this

  • composio-communitySkill

    weekly-digest

    Generate a weekly support digest and post it to [Slack](https://composio.dev/toolkits/slack)

    Also in 3 projects that use this

  • +1 more from getcompanion-ai

The file

Create a free account to mount
Files
SKILL.md

Session Search — 检索历史 session 摘要

续接上次 agent 工作或找「哪次 chat 做过 X」，但项目文档说不清时用。归档目录与文件格式见 references/archive-layout.md。

归档按机器独立（~ 各自解析），本 skill 只搜本机归档。

0. 何时用 / 何时不用（先判断再搜）

用 — 同时满足：

  • 用户话里指向历史 agent 行为（最近的 session、上次改的那个、之前 agent 做的、接着上次、哪次改过 X）
  • 快速扫过 CLAUDE.md、README、_sxg/ 后，仍缺「谁什么时候做了什么、还有什么未竟」

不用：

  • 代码/配置怎么用，文档或源码里能直接找到
  • 纯新需求，与历史 session 无关
  • 要 handoff 给下个 agent → 用 /handoff

流程：文档不够 → 执行下面检索 → 简短交代「查了 session 归档」再答；无命中则直说，并建议 /session-log 补记录。

1. 解析查询

从用户话里提取（缺省则不过滤）：

维度示例用法
关键词mlflow、gitlab、lineagegrep 正文 + frontmatter
项目quantalpha、factor_infra文件名中的 {project} 段或 project: 字段
时间上周、260629、6 月文件名时间戳前缀或 index 日期列
意图「上次」「最近」「哪次」多命中时按时间新→旧；「最近/上次」默认取最新 1 条

项目名不确定时：从 cwd / 用户 @ 路径推断默认项目；隐式触发时优先筛当前项目，无命中再扩全局。

2. 检索顺序（先广后窄）

Step A — index 快扫

读 ~/_sxg/llm_session_log/index.md，按摘要 / Session 标题 / 项目列做第一轮匹配。

Step B — 文件名过滤

LOG=~/_sxg/llm_session_log
ls "$LOG"/*_{project}_*.md 2>/dev/null       # 新格式，按项目筛
ls "$LOG"/\[{project}\]*.md 2>/dev/null      # 旧格式（存量文件，主要在集群）
ls "$LOG"/*.md

文件名两代格式都可能存在，见 archive-layout.md；内容 grep 不受格式影响。

Step C — 内容 grep

rg -i -l '关键词1|关键词2' "$LOG" --glob '*.md' --glob '!index.md' --glob '!INDEX.md'
rg -i '关键词' "$LOG" --glob '*.md' -n -C 0

同时搜 frontmatter 字段：keywords、summary、session_title、suggested_chat_title、git_commits。

Step D — 读命中文件

对每个候选（通常 ≤5 个）读 YAML frontmatter + 「完成事项」「未竟 / 下次继续」节。不要编造未读内容。

3. 回复格式

用简体中文，结构如下：

## 检索：{用户原问简述}

找到 N 条相关 session（按时间新→旧）：

### 1. {session_title} — {date} {time}
- **项目**：{project}
- **文件**：`~/_sxg/llm_session_log/{filename}`
- **Chat 标题建议**：`{suggested_chat_title}`（客户端已成功应用时可在 chat 历史按此名查找；归档检索不依赖改名）
- **匹配原因**：{为何命中，1 句}
- **要点**：{2–4 条 bullet，来自摘要}

### 2. …

---
未找到时：说明搜了哪些词/项目；建议换关键词或 `/session-log` 补归档。

规则：

  • 最多详述 5 条；更多只列 index 一行
  • 给出可点击的完整路径
  • 若用户问「上次/最近」，默认只展开最新 1 条并简述其余
  • 隐式触发时：先 1 句交代「查了 session 归档」，再答用户原问题；不必每次贴完整模板
  • 不要继续写无关代码，除非用户接着提新任务

4. 与 session-log / handoff 的边界

工具用途
session-search（本 skill）找已归档的历史 session
session-log关 chat 前写入新摘要
handoff给下一个 agent 的待办（不是检索）

归档为空或太旧时，告知用户用 /session-log 养成关 session 前记录的习惯。

5. 参考

文件名与 frontmatter 标准见 references/archive-layout.md（与 session-log 共用约定）。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free