agentleFS
sevenschultesevenschulte/agentic-harness/.claude/skills/wrap-up/SKILL.md

wrap-up

Skill2 starsChanged 7 months agoMITView on GitHub

Update memory/ACTIVE.md with the state of the current session — what was worked on, what's done, what's next, what's blocked — so the next session can pick up without re-learning context. Run at session end or when switching to an unrelated task.

61 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use refine, doctor and 10 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.
  • AlexPEClubSkill

    refine

    Always use when the user wants to discuss an exsiting feature or specification. Open an existing feature spec to improve, extend, or fundamentally challenge it. Pass the feature ID as argument (e.g. /refine PROJ-2).

    Also in 3 projects that use this

  • MicrosoftSkill

    doctor

    Diagnose an Amplifier CLI environment through the CLI doctor agent. USE WHEN a user requests CLI runtime, settings or missing-capability inspection. DO NOT USE for project bugs or other hosts.

    Also in 4 projects that use this

  • MicrosoftSkill

    sync

    Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase onto upstream, push current branch, publish branch, or set upstream.

    Also in 3 projects that use this

  • austintgriffithSkill

    orchestration

    Use when a Scaffold-ETH 2 build leaves localhost: planning the launch order, deploying and verifying contracts on a live network, standing up a fork of a real chain to rehearse a deploy, or fixing a contract bug that is already onchain. Not for running the app or a demo against that fork (`/frontend-playbook`).

    Also in 3 projects that use this

  • SentrySkill

    spec

    Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.

    Also in 5 projects that use this

  • nicolasestremSkill

    brainstorm

    Structured idea generation and solution exploration with systematic analysis.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 56 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Don't inline long descriptions.

    line 81
  2. Very specific:

    After adding the new entry, count entries under "Session Notes".

    line 88
  3. Very specific:

    If this session produced decisions about a specific project, update that project's memory/projects/<name>/context.md.

    line 94
  4. Distinctive:

    Update project context files if decisions were made

    line 130

“Common” is measured: kept by at least 6 in 10 of the 56 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

Wrap Up

You are closing a work session. Your job is to update memory/ACTIVE.md so the next session has everything it needs to continue: where we were, what got done, what's still in flight, what's next.

Without this step, ACTIVE.md stagnates and the next session starts cold even though the codebase hasn't.

When to wrap up

  • User says "wrap up" / "let's stop" / "end session" / "that's it for today"
  • About to stop responding after meaningful work (a deliverable shipped, a decision made, an investigation concluded, a PR opened)
  • Switching to a completely different topic or project

Skip for purely conversational sessions with no deliverables.

Step 1 — Read the current ACTIVE.md

You are updating, not rewriting.

memory/ACTIVE.md

Expected shape (create if missing):

# Active Work

## Current Focus
<what we're working on right now>

## In Progress
- [ ] <task with a checkbox>
- [x] <completed task>

## Next Up
- <upcoming task>

## Parking Lot
- <idea to revisit>

## Completed
- **<title>** (<date>) — <one line>. Details: <pointer to memory/projects/...>

## Session Notes
*<date>:* <one-paragraph session summary>

Step 2 — Analyse this session

Identify:

  1. Focus — what was the main thing we worked on?
  2. Done — what got finished? (mark [x])
  3. In flight — what's started but not finished? ([ ])
  4. Next — what's the immediate next step for whoever continues?
  5. Blockers — what's waiting on something external?
  6. Discovered — new tasks that came up but aren't urgent? (parking lot)

Step 3 — Update ACTIVE.md

  • Current Focus: rewrite to reflect today's work, including status if relevant (blocked, in review, waiting on X)
  • In Progress: mark completed items [x], add any new in-flight items
  • Next Up: move items in/out as priorities shift
  • Parking Lot: append anything worth remembering later
  • Completed: one-line index entry pointing at the fuller write-up elsewhere. Don't inline long descriptions; details live in memory/projects/<...> or memory/research/<...>
  • Session Notes: prepend one short paragraph (date in YYYY-MM-DD, one paragraph summarising what happened and why)

Step 4 — Auto-archive old session notes

After adding the new entry, count entries under "Session Notes". If more than 3, move the oldest ones into memory/session-history.md (create if missing). Stops ACTIVE.md growing unbounded while preserving history.

Step 5 — Update project context (if applicable)

If this session produced decisions about a specific project, update that project's memory/projects/<name>/context.md. Don't move the decision from ACTIVE.md to the project file; link between them.

Step 6 — Report

## Session wrapped

**ACTIVE.md updated:**
- <summary of changes>

**Project files updated:** <list or "none">

**Archived session notes:** <count, or "none">

Next session's first file to read: memory/ACTIVE.md

What this skill will not do

  • Will not save durable facts or preferences. That's the save-memory skill. Two different jobs: wrap-up captures state, save-memory captures knowledge.
  • Will not delete or overwrite existing tasks without marking them first. If a task is no longer relevant, move it to "Completed" with a (skipped — reason) note, don't disappear it.
  • Will not inline long descriptions in ACTIVE.md. Keep it scannable; pointers to fuller detail elsewhere.

Now execute:

  1. Read current memory/ACTIVE.md
  2. Analyse this session
  3. Update each section
  4. Auto-archive session notes if more than 3
  5. Update project context files if decisions were made
  6. 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.