agentleFS
bestes206bestes206/claude-whereami/skills/whereami/SKILL.md

whereami

Skill0 starsChanged 5 months agoMITView on GitHub

Read-only in-session reorientation. Use when you (the user) have lost track of a long or resumed session and want a quick rich summary of what's going on — what you last said, the original goal vs. now, the open loop, drift, and whether to split the session. Tip: after reading, press Esc Esc to rewind this skill out of the conversation so it leaves no artifact.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. rikilamadrid/lorekeeper★ 1same name
    2. rikilamadrid/pathfinder★ 1same 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 repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Keep the whole thing tight — this is a glance, not a report.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

/whereami — Where am I in this session?

You are producing a read-only reorientation snapshot. Do NOT edit, write, or create any files. Do NOT run commands with side effects. The user will likely Esc Esc to rewind this output away afterward, so it must leave nothing behind.

Using the conversation already in your context (and, only if useful for exact timestamps, reading the current session's transcript file), output these five sections, concise and skimmable:

1. Last thing you said

Quote the user's most recent genuine message verbatim (not tool results).

2. Original goal vs. now

One line on what this session set out to do (from the first real user message), and one line on what it's actually doing now.

3. Open loop / your turn

What is the agent currently waiting on or what did the last response ask of the user? What is the next concrete action?

4. Drift

State whether the conversation has stayed on its original path or wandered, and how far. If an orientation cache exists at ~/.claude/whereami/<session-id>.json, you may read its score, gist, open_loop, and goal fields, but do not write to it.

5. Split recommendation

A clear call: keep going in this session, or start a fresh one — with a one-sentence reason (e.g. context is full, topic has fully changed, original task is done).

Keep the whole thing tight — this is a glance, not a report.

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.