agentleFS
Sign inStart free
blair-keckblair-keck/claude-skills/session-recap/SKILL.md

session-recap

Skill0 starsChanged 4 months agoMITView on GitHub

Use when someone asks to recap what we worked on, summarize this session, write up what we got done, or turn our work so far into a shareable summary.

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. sonichi/sutando★ 396same name
    2. hideki5123/agent-skill-set★ 2same name
    3. RouanetClement/claude-skills★ 0same name
    4. thistleknot/skills★ 0same name
    5. topness-msft/crowdhum-plugin★ 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 repository3 other files it gives its agents.

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 4 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:

    Before writing, read and apply the shared writing principles in ../_shared/human-voice.md (sound human, preserve voice, don't invent, stay …

    line 11
  2. Very specific:

    If a focus was passed as arguments, narrow the recap to that (e.g.

    line 16
  3. Distinctive:

    Follow with the substance.

    line 25
  4. Distinctive:

    Omit empty sections: No open items means no "Open / next" section.

    line 53

“Common” is measured: kept by at least 6 in 10 of the 4 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

What This Skill Does

Summarizes the work done so far in the current session into a clear, natural-sounding recap: what we set out to do, what actually got done, and anything left open. Produces the summary as text in chat. Unlike humanize-notes and email-drafter, the source material is the conversation itself, not text the user pastes in.

Before writing, read and apply the shared writing principles in ../_shared/human-voice.md (sound human, preserve voice, don't invent, stay proportional, plain punctuation).

Steps

  1. Determine the scope.
    • If a focus was passed as arguments, narrow the recap to that (e.g. just the bug fixes, the API work). Otherwise recap the whole session.
    • The source is the current conversation: the tasks worked on, decisions made, files changed, commands run, and anything explicitly left open.
  2. Gather what actually happened.
    • Pull concrete facts from the session: what was built, changed, tested, decided, or blocked.
    • Ground every claim in something real from the conversation. If you're unsure whether something was finished versus just discussed, say "discussed" or flag it rather than claiming it was done.
  3. Structure the recap.
    • Lead with a one-line summary of the overall goal or theme of the session.
    • Follow with the substance. Default to a few short paragraphs. Use a compact bulleted list of concrete changes or decisions when the work has several distinct pieces (that's usually clearer than prose for a change log).
    • End with an Open / next note only if there is genuinely something unfinished. Don't manufacture next steps to look thorough.
  4. Keep it honest and human. Apply the shared human-voice principles. Use "we" for collaborative work. Report outcomes faithfully: if something failed or was skipped, say so; don't inflate a half-done thing into a finished one.
  5. Present the result in a clearly delimited block so it's easy to copy or paste elsewhere. Then offer to adjust (shorter, more formal, standup format, group by topic, etc.).

Output Template

**Session recap: [one-line theme]**

[One or two short paragraphs on what we did and why.]

What got done:
- [concrete change or decision]
- [concrete change or decision]

Open / next:
- [anything genuinely unfinished, or omit this section entirely]

Notes

The shared human-voice principles above already cover not inventing content, staying proportional, and plain punctuation. These are specific to recapping:

  • Summarize, don't fabricate. The single biggest risk here is claiming work that didn't happen. Only include what the session actually shows. When in doubt, leave it out or flag it.
  • Proportional to the work. A short session gets a short recap. Don't pad a two-step session into a page.
  • Omit empty sections. No open items means no "Open / next" section. Don't include a heading just to fill the template.

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