Pulling Updates from Skills Repository
About
This skill syncs your local Claude skills repository with upstream updates from obra/superpowers-skills while preserving your personal modifications. It automatically handles stashing uncommitted changes and merging updates when new upstream skills are available. Use it at session start when updates are indicated or manually to get the latest skill versions.
Quick Install
Claude Code
Recommendednpx skills add obra/superpowers-skills -a claude-code/plugin add https://github.com/obra/superpowers-skillsgit clone https://github.com/obra/superpowers-skills.git ~/.claude/skills/Pulling Updates from Skills RepositoryCopy and paste this command in Claude Code to install this skill
Documentation
Updating Skills from Upstream
Overview
Pull and merge upstream changes from obra/superpowers-skills into your local skills repository while preserving your personal modifications.
Announce at start: "I'm using the Updating Skills skill to sync with upstream."
Prerequisites
Your skills repo must have a tracking branch configured. The plugin sets this up automatically (either as a fork with origin remote, or with an upstream remote).
The Process
Step 1: Check Current Status
Run:
cd ~/.config/superpowers/skills
git status
If working directory is dirty: Proceed to Step 2 (stash changes) If clean: Skip to Step 3
Step 2: Stash Uncommitted Changes (if needed)
Run:
git stash push -m "Temporary stash before upstream update"
Record: Whether changes were stashed (you'll need to unstash later)
Step 3: Determine Tracking Remote and Fetch
First, detect which remote to use:
TRACKING_REMOTE=$(git rev-parse --abbrev-ref --symbolic-full-name @{u} 2>/dev/null | cut -d'/' -f1 || echo "")
Then fetch from the appropriate remote:
if [ -n "$TRACKING_REMOTE" ]; then
git fetch "$TRACKING_REMOTE" 2>/dev/null || true
else
git fetch upstream 2>/dev/null || git fetch origin 2>/dev/null || true
fi
Expected: Fetches latest commits from the tracking remote (or falls back to upstream/origin)
Step 4: Check What's New
Run:
git log HEAD..@{u} --oneline
Show user: List of new commits being pulled
Note: @{u} refers to the upstream tracking branch for your current branch
Step 5: Merge Changes
First, try a fast-forward merge (cleanest option):
git merge --ff-only @{u}
If fast-forward succeeds: Skip to Step 7 (no conflicts possible with fast-forward) If fast-forward fails: Your branch has diverged. Try regular merge:
git merge @{u}
If merge succeeds cleanly: Proceed to Step 7 If conflicts occur: Proceed to conflict resolution
Step 6: Handle Merge Conflicts (if any)
If conflicts:
- Run
git statusto see conflicted files - For each conflict, explain to user what changed in both versions
- Ask user which version to keep or how to merge
- Edit files to resolve
- Run
git add <resolved-file>for each - Run
git committo complete merge
Step 7: Unstash Changes (if stashed in Step 2)
If you stashed changes:
git stash pop
If conflicts with unstashed changes: Help user resolve them
Step 8: Verify Everything Works
Run:
${SUPERPOWERS_SKILLS_ROOT}/skills/using-skills/find-skills
Expected: Skills list displays correctly
Step 9: Announce Completion
Tell user:
- How many new commits were merged
- Whether any conflicts were resolved
- Whether their stashed changes were restored
- That skills are now up to date
Common Issues
"Already up to date": Your local repo is current, no action needed
"fatal: no upstream configured": Your branch isn't tracking a remote branch. Check git remote -v to see available remotes, then set tracking with git branch --set-upstream-to=<remote>/<branch>
Detached HEAD: You're not on a branch. Ask user if they want to create a branch or check out main.
Fast-forward fails, diverged branches: Your local branch has commits that aren't in the remote. Regular merge will be needed, which may cause conflicts.
Remember
- Always stash uncommitted work before merging
- Explain conflicts clearly to user
- Test that skills work after update
- User's local commits/branches are preserved
GitHub Repository
Frequently asked questions
What is the Pulling Updates from Skills Repository skill?
Pulling Updates from Skills Repository is a Claude Skill by obra. Skills package instructions and resources that Claude loads on demand, so Claude can perform Pulling Updates from Skills Repository-related tasks without extra prompting.
How do I install Pulling Updates from Skills Repository?
Use the install commands on this page: add Pulling Updates from Skills Repository to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does Pulling Updates from Skills Repository belong to?
Pulling Updates from Skills Repository is in the Meta category, tagged general.
Is Pulling Updates from Skills Repository free to use?
Yes. Pulling Updates from Skills Repository is listed on AIMCP and free to install.
Related Skills
This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
This skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.
This skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.
SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
