agentleFS
JsnnmscJsnnmsc/10000x-engineer/skills/catchup/SKILL.md

catchup

Skill2 starsChanged 2 months agoMITView on GitHub

Quick status brief so the user can pick up where things left off — what changed, what state it's in, what's next.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use wrapup, explain and 5 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.
  • Skeln-ioSkill

    wrapup

    End-of-session closeout — commit, push, and optionally post a Slack summary. Use when you say "wrap up", "done for now", "save everything", or similar.

    Also in 3 projects that use this

  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 4 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 3 projects that use this

  • MicrosoftSkill

    pr-review

    Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode. Use when reviewing a docs PR for factual correctness: setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.

    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 4 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 5

    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:

    If there's no git repo or no meaningful history, say so directly rather than padding the response.

    line 24
  2. Distinctive:

    Don't summarize commits into a theme ("various skill improvements").

    line 58
  3. Distinctive:

    Don't report "Current state: clean" when there's untracked work sitting there.

    line 61
  4. Distinctive:

    Don't turn the next step into a roadmap.

    line 64
  5. Distinctive:

    If a branch, date, or "since <commit>" was supplied, scope the git history to that instead of just recent commits.

    line 67

“Common” is measured: kept by at least 6 in 10 of the 21 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

Catch Up

Goal: user reads this once and knows exactly what happened, what state things are in, and what to do next — no need to dig through git log themselves.

Rules

  • Respond in the same language the user wrote in. If they write in Chinese, reply in Chinese. Technical terms (JWT, Redis, API…) stay in English.
  • Max 12 lines. Hard limit.
  • Ground every line in evidence: check git status, git log (recent commits, last ~5-10 or from any supplied branch/date/commit), and git diff for uncommitted work before writing anything. Never guess at what changed.
  • "Since last time" = what actually landed: commits (with short hash), files changed, uncommitted work in progress. Cite specifics, not "some fixes were made".
  • "Current state" = is it clean, mid-change, broken, blocked? Uncommitted changes, failing state, or half-finished work goes here explicitly — don't bury it.
  • "Next step" is the closing line and takes the inline form **Next step:** … — one obvious action, not a plan. If a blocker is in the way (merge conflict, failing test, unresolved decision), that's the next step instead.
  • If there's no git repo or no meaningful history, say so directly rather than padding the response.
  • No emoji.

Output format

**Since last time**
- `[hash]` [commit subject]
- Uncommitted: [file] ([new / +N lines / deleted])

**Current state**
[clean / mid-change / blocked — one line, concrete]

**Next step:** [the one obvious action, or the blocker in the way]

Example

/catchup

**Since last time**
- `6efbe87` Add clear-view and doubt skills, reviewer agent
- `e6fd00f` Bump version to 1.4.0
- Uncommitted: `skills/one-line/SKILL.md` (new, untracked), `README.md` (+12 lines)

**Current state**
Mid-change — new skill written and documented, nothing committed yet; no tests in this repo to run

**Next step:** commit the one-line skill plus the README and version bump as one change

Anti-examples

Don't summarize commits into a theme ("various skill improvements"). The subject lines are already short — quote them.

Don't report "Current state: clean" when there's untracked work sitting there. Untracked counts.

Don't turn the next step into a roadmap. One action. If the user needs the plan, they'll ask for it.

If a branch, date, or "since <commit>" was supplied, scope the git history to that instead of just recent commits.

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.