agentleFS
DeL-TaiseiOzakiDeL-TaiseiOzaki/claude-code-orchestra/.claude/skills/catchup/SKILL.md

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

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-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

  • 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

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
  1. Very specific:

    Write the bodies to a JSON file keyed by the section ids in references/guide-template.md:

    line 109

“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

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 /feature planning phases or direct research instead)
  • You want to capture the current session for later (use /checkpointing)
  • You want running design history (use /design-tracker or read DESIGN.md directly)

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 Contract

Phase 1: COLLECT (via collect_repo_state.py)

python3 .claude/skills/catchup/collect_repo_state.py

Optional 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.toml presence + first line, plus identity.state with main_agent, current_project, current_feature, current_bug_fix read 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 (from pyproject.toml), commands (each with the source file it was quoted from), errors.
  • checkpoints — newest 5 (file + first_line: the frontmatter summary, else its slug, else the first non-empty body line — never the --- fence).
  • agent_teams — sessions[{name, members, tasks_total, tasks_completed}] and in-repo work_logs.
  • cli_tools — recent consultations for every tool, each tagged with tool, plus skipped_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 --apply

The 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.md is 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.
  • .gitignore awareness: .claude/checkpoints/ and .claude/logs/ are gitignored. On a fresh clone they will be absent; the collector reports that as present: false rather than failing.
  • Language: GUIDE.md is user-facing prose, so it follows .claude/rules/language.md rather than the English technical-document rule, while code identifiers and command names stay in English.

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.