catchup
Skill199 starsChanged 2 months agoMITView on GitHub
Comprehensive onboarding for new or returning contributors. Scans repository artifacts (git history, .claude/STATE.md, project rules, skill catalog, DESIGN.md, research & library notes, checkpoints, agent-team logs) and synthesizes a GUIDE.md at the repository root summarizing what has been worked on, why, and how to resume work.
26 other projects use a version of this.
Adopted by
Most recently taken up by
- LilMGenius/paperthintheir own version, first seen Nov 15, 2026
- shortcuts/dotfilestheir own version, first seen Nov 8, 2026
- blamechris/chroxytheir own version, first seen Nov 8, 2026
- saksham10arora-dotcom/everything-claude-codextheir own version, first seen Nov 1, 2026
- Avijit07x/claude-dbtheir own version, first seen Oct 13, 2026
- poshan0126/dotclaudetheir own version, first seen Oct 8, 2026
Used with
Projects with it also use wrapup, explain and 3 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-ioSkillwrapup
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
sunnyclinches44Skillexplain
Explains code using real-world analogies and ASCII diagrams
Also in 3 projects that use this
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 4 projects that use this
MicrosoftSkillpr-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
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 4 projects that use this
Other versions26 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 26
- LilMGenius/paperthin★ 1.4ksame name
- poshan0126/dotclaude★ 871same name
- getsentry/sentry-wizard★ 297same name
- Avijit07x/claude-db★ 233same name
- saksham10arora-dotcom/everything-claude-codex★ 96same name
- wilbeibi/catchup★ 81same name
- shortcuts/dotfiles★ 18same name
- blamechris/chroxy★ 8same name
- iopsystems/skills-mcp★ 6same name
- Code-Shock/claude-skills★ 5same name
16 more not listed
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 repository17 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- checkpointingSkill
- codex-systemSkill
- context-loaderSkill
- design-trackerSkill
- featureSkill
- initSkill
- planSkill
- research-libSkill
- simplifySkill
- spikeSkill
- tddSkill
- team-executeSkill
- troubleshootSkill
- update-lib-docsSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
0
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
- Very specific: line 109
Write the bodies to a JSON file keyed by the section ids in references/guide-template.md:
“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.
Files
Catchup
Onboarding skill that produces a GUIDE.md at the repository root so a new or returning contributor can understand the project's history, current state, and how to resume work.
When to Use
- A contributor joins the repository for the first time
- A contributor returns after a long absence
- You want a single human-readable snapshot of "what has been happening here"
When NOT to Use
- You need a single focused answer (use
/featureplanning phases or direct research instead) - You want to capture the current session for later (use
/checkpointing) - You want running design history (use
/design-trackeror readDESIGN.mddirectly)
Full skill routing: AGENTS.md section "Routing Policy".
Workflow
Phase 1: COLLECT (collect_repo_state.py)
Run the collector script -> single JSON of every dataset the template needs
|
Phase 2: SYNTHESIZE (Claude Lead)
Turn that JSON into per-section prose — the judgment step
|
Phase 3: ASSEMBLE (write_guide.py)
Stamp, order, validate, and write GUIDE.md under the Writer Safety ContractPhase 1: COLLECT (via collect_repo_state.py)
python3 .claude/skills/catchup/collect_repo_state.pyOptional flags: --since "30 days ago" (recent-work window, passed to git),
--max-commits 100, --claude-home DIR (Agent Teams data root),
--project-root DIR.
Exit codes: 0 ok · 1 bad arguments · 2 not a git repository, or a
SKILL.md/agent frontmatter that yields neither a name nor a description ·
3 a git subcommand failed inside a real repository. The payload always carries
top-level ok and errors; check those rather than assuming exit 0.
Degradation is named, never silent: an absent file is {"present": false}, an
unreadable one carries an error, and a failed git subcommand is null plus an
entry in git.errors — distinct from [], which means genuinely empty.
Top-level JSON keys:
git—log,branches,status,stash,diffstat,recent_stat,current_branch,errors.identity—README.md,AGENTS.md,pyproject.tomlpresence + first line, plusidentity.statewithmain_agent,current_project,current_feature,current_bug_fixread from.claude/STATE.md.rules—{present, items[{file, first_line}]}.skills—{present, items[{name, short_description, file}], frontmatter_errors}.agents—{present, items[{name, specialization, model, file}], frontmatter_errors}.docs—design{present, placeholder, key_decisions[]},research,libraries.env—manifests,scripts(frompyproject.toml),commands(each with thesourcefile it was quoted from),errors.checkpoints— newest 5 (file +first_line: the frontmattersummary, else itsslug, else the first non-empty body line — never the---fence).agent_teams—sessions[{name, members, tasks_total, tasks_completed}]and in-repowork_logs.cli_tools— recent consultations for every tool, each tagged withtool, plusskipped_lines.
Feed the emitted JSON to Phase 2 as its sole input. For very large repos hand it
to general-purpose-opus for the thematic grouping.
Phase 2: SYNTHESIZE (Claude Lead)
Turn the collected JSON into one markdown body per section of
references/guide-template.md. Do not re-read the source files; the collector
now gathers every dataset the template asks for, so re-reading only costs
context.
This phase is judgment and stays here: grouping commits into 3–7 themes, ranking
the top design decisions, and deciding which optional sections are worth a
reader's time have more than one defensible answer. write_guide.py deliberately
takes the prose as input rather than generating it.
Omit a section entirely when its source data is absent. Never leave a
{placeholder} — Phase 3 rejects them.
Write the bodies to a JSON file keyed by the section ids in
references/guide-template.md:
{
"what_is_this_project": "- **Purpose**: ...",
"recent_work": "- ...",
"capabilities": "### Slash commands\n\n| Command | Purpose |\n|---|---|\n...",
"resume_work": "- **Environment setup**: `uv sync`"
}Phase 3: ASSEMBLE (via write_guide.py)
python3 .claude/skills/catchup/write_guide.py --input body.json
python3 .claude/skills/catchup/write_guide.py --input body.json --applyThe first call previews to .claude/logs/guide-preview-*.md; the second writes
GUIDE.md atomically, refuses if GUIDE.md changed since it was read, and
validates the composed document (validate_doc.py --contract guide) before
replacing it. --now ISO8601 injects the date stamp; --project-root DIR
relocates the root.
The script owns the title, the _Generated by /catchup on YYYY-MM-DD_ line, the
section order and fixed numbering, and the _Sources:_ footer — do not supply
them in --input.
Payload: {ok, guide_path, preview_path, sections_written, sections_omitted,
line_count, residual_placeholders, applied, result, artifacts}. Exit codes:
0 preview/applied · 1 bad args or unreadable --input · 2 unknown section
id, a missing required section (what_is_this_project, recent_work,
capabilities, resume_work), a residual {placeholder}, or a composed
document the guide contract rejects · 3 write failure or concurrent
modification.
Report guide_path, line_count, sections_written, and sections_omitted
from the payload rather than restating them from memory.
GUIDE.md Structure
references/guide-template.md is the contract: it maps each section id to its
numbered heading, marks which four are required, and lists the collector fields
each one draws on. Section numbers never shift when an optional section is
omitted.
Tips
- Context discipline: Phase 1 is a single script run, not a subagent scan — the orchestrator never loads raw logs or long docs. Only hand the JSON to a subagent when the synthesis itself is large.
- Not byte-stable:
GUIDE.mdis regenerated from sources each run, but its prose is LLM-authored, so two runs over identical sources produce different text and a noisy diff on a tracked root file. Do not edit it by hand — update the underlying sources (.claude/STATE.md,DESIGN.md, rules) and re-run. .gitignoreawareness:.claude/checkpoints/and.claude/logs/are gitignored. On a fresh clone they will be absent; the collector reports that aspresent: falserather than failing.- Language:
GUIDE.mdis user-facing prose, so it follows.claude/rules/language.mdrather than the English technical-document rule, while code identifiers and command names stay in English.
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
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.

