agentleFS
Sign inStart free
JamaalxJamaalx/claude-chat-namer/skills/find/SKILL.md

find

Skill5 starsChanged 12 days agoMITView on GitHub

Find, list or get back to an earlier conversation with Claude. Use whenever the user refers to a past chat or session in any language, e.g. "where did we talk about X", "that chat about X", "find the conversation where...", "open/resume the X chat", "what were my recent chats", "unde am vorbit despre X", "găsește chat-ul cu X". Not for searching code or files.

6 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions6 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 6

    1. fakechris/obsidian_vault_pipeline★ 165same name
    2. tonydzi/second-brain-starter-kit★ 6same name
    3. bibryam/universal-skill-finder★ 5same name
    4. replybr/plugadvpl★ 1same name
    5. statzhero/zotero-fulltext★ 0same name
    6. ZeeshanSultan/DocGov★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search everything the user typed, in every project (all words must match, any order):

    line 10
  2. Distinctive:

    If the command says no Claude Code transcripts were found, use path B.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Find the earlier conversation the user means and help them get back to it. Use the first path that works.

A. Claude Code (you can run shell commands)

Search everything the user typed, in every project (all words must match, any order):

node "${CLAUDE_PLUGIN_ROOT}/scripts/cli.js" search "<keywords>" --all --json --limit 8

With no topic ("my recent chats"), list instead:

node "${CLAUDE_PLUGIN_ROOT}/scripts/cli.js" list --all --json --limit 10

Pick 2–4 short keywords from the user's words; if nothing matches, retry once with fewer or synonym keywords.

Reply with a short numbered list: title, date, directory, and for content matches the snippet. When one result clearly fits, give its resume field as the command to run in a new terminal, exactly as printed (it starts with cd, because claude --resume only works from the session's directory). If they would rather continue here, offer to recap it (the recap skill).

If the command says no Claude Code transcripts were found, use path B.

B. Claude.ai and other Claude apps

If you have tools for searching or listing the user's past chats (such as conversation_search or recent_chats), use them with the user's keywords. Reply with a short numbered list: a clear title of a few words for each chat (write one if the chat has none), when it happened, one line on what it was about, and its link.

C. Neither is available

Say plainly that you can't see past conversations here. In Claude.ai that needs the setting that lets Claude search and reference past chats (Settings > Capabilities, on plans that include it); in Claude Code it works out of the box.

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