By andrew-d
Intercepts GitHub URL fetches and curl/wget commands, redirecting to the authenticated gh CLI.
A curated mirror of Claude Code skills from trusted upstream repositories, with automated syncing and review workflows.
This repository maintains a mirror of skills from upstream repositories. Skills are curated to include only those from trusted sources, and the mirror is kept in sync via automated syncing and pull request workflows. Users can configure Claude Code to use this repository as a plugin source.
The syncing process consists of three main steps:
sync.py clones all configured upstream repositoriesmarketplace.json file is generated for Claude Code to discover available skillsThe GitHub Action (sync.yaml) runs this process on a weekly schedule and on manual trigger. When changes are detected, it creates a pull request with the updates. The PR diff becomes the review surface—review all changes before merging.
Configuration is defined in upstream.yaml. The schema is:
upstreams:
- name: <upstream-name> # Unique identifier for this upstream
repo: <git-url> # Git repository URL
ref: <branch/tag> # Git reference (branch or tag)
plugins: # (Optional) Plugin-level filtering
include: # (Optional) Only include these plugins
- <plugin-name>
- plugin-name:
skills: # (Optional) Skill-level filtering
include: # (Optional) Only include these skills
- <skill-name>
exclude: # (Optional) Exclude these skills
- <skill-name>
exclude: # (Optional) Exclude these plugins
- <plugin-name>
upstreams:
- name: trailofbits
repo: https://github.com/trailofbits/skills
ref: main
All plugins and skills from the repository are included.
upstreams:
- name: security-tools
repo: https://github.com/example/skills
ref: main
plugins:
include:
- security-analysis
- vulnerability-scanner
Only plugins named security-analysis and vulnerability-scanner are included.
upstreams:
- name: experimental
repo: https://github.com/example/skills
ref: main
plugins:
exclude:
- unstable-plugin
- beta-feature
All plugins except unstable-plugin and beta-feature are included.
upstreams:
- name: mixed-tools
repo: https://github.com/example/skills
ref: main
plugins:
include:
- analysis-plugin:
skills:
include:
- code-review
- type-checking
- utils-plugin:
skills:
exclude:
- deprecated-util
analysis-plugin is included, but only with skills code-review and type-checkingutils-plugin is included with all skills except deprecated-utilSecurity depends on careful review:
When reviewing a sync PR, check:
To run the sync process locally:
python sync.py
This will:
upstream.yamlplugins/marketplace.json with skill metadataNo dependencies are needed beyond Python 3.12 and PyYAML:
pip install pyyaml
To configure Claude Code to use this repository as a plugin source:
marketplace.json file to discover available skillsRefer to Claude Code documentation for exact configuration steps for your environment.
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub andrew-d/claude-skills --plugin trailofbits--gh-cliAudit supply-chain threat landscape of project dependencies for exploitation or takeover risk
Automatically nudges Claude to offer learning exercises after git commits. Requires the learning-opportunities plugin.
Core Swift language features, concurrency, testing, SwiftData, Charts, and Codable
Science-based learning exercises for deliberate skill development during AI-assisted coding
Generates a repo-specific orientation.md for use with the learning-opportunities skill
GitHub CLI integration with focused skills for pull requests, issues, GitHub Actions, and viewing GitHub file URLs
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Efficient skill management system with progressive discovery — 410+ production-ready skills across 33+ domains