agentleFS
epechuzalepechuzal/claude-skill-recall/tldr/SKILL.md

tldr

Skill1 starsChanged 7 months agoMITView on GitHub

Use when the user explicitly invokes /tldr to summarize the current conversation into a session note saved to a configured directory. For ambient surfacing of past sessions, use the session-recall skill instead.

39 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use explain, handoff and 2 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.
  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 6 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 34 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the full conversation.

    line 30
  2. Very specific:

    If multiple /tldr calls land on the same day, the slug differentiates them.

    line 78
  3. Distinctive:

    Keep reverse chronological (newest first).

    line 89
  4. Distinctive:

    If the conversation is clearly:

    line 96

“Common” is measured: kept by at least 6 in 10 of the 34 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

TLDR — Session Note Saver

Summarize the current conversation as a session note and save it to disk.

Argument ($ARGUMENTS): optional freeform annotation that focuses the summary (e.g. "important — financial strategy change", "for partner's birthday").


Setup

Configure these paths in your project's CLAUDE.md (or set them inline in conversation):

  • Sessions directory — where session notes live (default: sessions/ at the project root)
  • Index file — one row per saved session (default: <sessions-dir>/INDEX.md)
  • Tags file — canonical tag registry, optional (default: <sessions-dir>/TAGS.md)

Companion: the session-recall skill reads from the same directory + index. Pair them.


What to Capture

Read the full conversation. Identify:

  1. Title — short, descriptive, opinionated. "RAV4 PHEV — Trim Analysis and Purchase Plan", not "Car Discussion". Lead with the conclusion or the topic's real name.
  2. Summary — 2–3 sentences capturing the conclusion, not the process. "X turned out to be Y because Z" not "We discussed X."
  3. Tags — freeform but consistent. Check <tags-file> before inventing new tags. Multiple tags expected — think "who would want to find this later?"
  4. Sections — only include sections that are relevant:
    • ## Key Decisions — if choices were made
    • ## Findings — if research produced conclusions
    • ## Recommendations — if products / tools / media were evaluated (name, price, where to get). This is the #1 thing the user tries to recall from past conversations.
    • ## Open Threads — anything left unfinished that a future session should know about
  5. Source — if the conversation was triggered by a URL (article, video, post), capture it in frontmatter.

Format

---
date: YYYY-MM-DD
tags: [tag1, tag2, tag3]
source: "https://..."  # only if the conversation had a trigger URL
---
# Title

2–3 sentence summary.

## Key Decisions
- ...

## Findings
- ...

## Recommendations
- Product — $price at [vendor](url)

## Open Threads
- ...

File Naming

<sessions-dir>/YYYY-MM-DD-slug.md

Slug: lowercase, hyphenated, 3–5 words max. Derived from the title. Examples: 2026-03-12-rav4-purchase-research.md, 2026-03-28-postgres-tuning-checklist.md

If multiple /tldr calls land on the same day, the slug differentiates them.


After Writing

  1. Update the tags file — add any new tags to <tags-file>, alphabetical.
  2. Update the index file — add one line to <index-file>:
    YYYY-MM-DD | [Title](YYYY-MM-DD-slug) | tag1, tag2, tag3
    Keep reverse chronological (newest first).
  3. Confirm — show the user the title, tags, and file path. Don't dump the full content back at them.

When NOT to /tldr

If the conversation is clearly:

  • A one-shot lookup ("what is prime reading")
  • An automated workflow whose artifacts already exist elsewhere

…flag it and ask if they still want a session note. Don't refuse — just check.


Companion Skill

The session-recall skill handles ambient surfacing of saved session notes during normal conversation. This skill writes new ones; that one reads them. Both touch the same index file.

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.