Skip to content
cccskills
FreePublished on GitHub

catchup

Restore context after /clear by summarizing recent work and project state

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.0 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Context catchup

Restore context after /clear - summarize recent work and project state.

Purpose

After clearing context with /clear, use this command to quickly rebuild understanding of:

  • What was recently modified
  • Current project state
  • Outstanding TODOs and issues
  • Where to resume work

Instructions

Step 1: Git history analysis

# Recent commits (last 10)
git log --oneline -10

# Files modified in last 5 commits
git diff --stat HEAD~5 2>/dev/null || git diff --stat $(git rev-list --max-parents=0 HEAD)

# Current branch and status
git branch --show-current
git status --short

Step 2: Recent changes summary

# What changed today
git log --oneline --since="midnight" --author="$(git config user.name)" 2>/dev/null

# Uncommitted work
git diff --name-only
git diff --cached --name-only

Step 3: TODO/FIXME scan

# Find outstanding work markers in recently modified files
git diff --name-only HEAD~5 2>/dev/null | head -20 | xargs grep -n "TODO\|FIXME\|XXX\|HACK" 2>/dev/null | head -30

Step 4: Project state check

# Check for common state indicators
[ -f "package.json" ] && echo "📦 Node project: $(jq -r '.name // "unnamed"' package.json)"
[ -f "Cargo.toml" ] && echo "🦀 Rust project: $(grep '^name' Cargo.toml | head -1)"
[ -f "pyproject.toml" ] && echo "🐍 Python project"
[ -f "go.mod" ] && echo "🐹 Go project: $(head -1 go.mod | cut -d' ' -f2)"

# Active branch purpose (from branch name)
BRANCH=$(git branch --show-current)
echo "🌿 Branch: $BRANCH"

Output format

Provide a structured summary:


📍 Context restored

Project: [name from package.json/Cargo.toml/etc] Branch: [current branch] Last Activity: [time of last commit]

🔄 Recent work (last 5 commits)

  1. [commit message 1] - [files affected]
  2. [commit message 2] - [files affected] ...

📝 Uncommitted changes

  • [list of modified files with brief description of changes]

⚠️ Outstanding TODOs

  • [file:line] TODO: [description]
  • [file:line] FIXME: [description]

🎯 Suggested next steps

Based on recent activity:

  1. [Most likely next action based on patterns]
  2. [Alternative focus area]

Usage examples

After a long break:

/catchup

→ Full context restoration

Quick status check:

/catchup --brief

→ Just commits and uncommitted changes

Focus on specific area:

/catchup auth

→ Filter to auth-related changes

Pro tips

  1. Document before /clear: Write a brief note in a commit message or CLAUDE.md before clearing context
  2. Use with Memory Bank: Combine with .claude/memory/ files for persistent state
  3. Branch naming: Use descriptive branch names (e.g., feat/user-auth) to aid context restoration

$ARGUMENTS

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.

The English summary is being prepared. Showing the original description.

FlorianBruniaux/claude-code-ultimate-guide6.2KUpdated Oct 18, 2026

Codebase health audit scoring 7 categories with progression plan

The English summary is being prepared. Showing the original description.

FlorianBruniaux/claude-code-ultimate-guide6.2KUpdated Oct 18, 2026

Autonomous improvement loop: scan codebase metrics, scaffold experiment files, run agent-driven iterations until metric improves

The English summary is being prepared. Showing the original description.

FlorianBruniaux/claude-code-ultimate-guide6.2KUpdated Oct 18, 2026

Generate bounded independent candidates, score them against a frozen rubric, and verify the selected result with a proof log.

The English summary is being prepared. Showing the original description.

FlorianBruniaux/claude-code-ultimate-guide6.2KUpdated Oct 18, 2026

canary

Free

Post-deploy monitoring: watch production after a deploy and alert on regressions

The English summary is being prepared. Showing the original description.

FlorianBruniaux/claude-code-ultimate-guide6.2KUpdated Oct 18, 2026

Launch and navigate the ccboard TUI/Web dashboard for Claude Code. Use when monitoring token usage, tracking costs, browsing sessions, or checking MCP server status across projects.

The English summary is being prepared. Showing the original description.

FlorianBruniaux/claude-code-ultimate-guide6.2KUpdated Oct 18, 2026

See all skills by FlorianBruniaux

Report a problem with this skill