Use when removing AI-generated slop, cleaning up verbose code, or removing unnecessary defensive checks. Triggers on "remove slop", "clean up AI code", "deslop".
Use when documentation should be synchronized after code changes, new skills, releases, merged PRs, or shipped work. Triggers on "update the docs", "sync docs", "post-ship docs", "documentation is stale", "refresh README".
Use when implementing E2E tests, debugging flaky tests, testing web applications with Playwright, or establishing E2E testing standards. Triggers on "e2e test", "end-to-end", "Playwright", "flaky test", "browser test".
Use when tests are failing and need systematic fixing until all pass. Triggers on "fix tests", "tests failing", "make tests pass".
Use when addressing PR review comments or resolving unresolved PR review threads from Copilot, Code Factory, bots, or humans. Triggers on "fix review comments", "address review feedback", "address code factory", "respond to PR comments", "resolve conversations", "unresolved review threads".
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.
██╗ ██╗ ██╗ ████████╗ █████╗ ███╗ ███╗██╗███╗ ██╗███████╗
██║ ██║ ███║ ╚══██╔══╝██╔══██╗████╗ ████║██║████╗ ██║██╔════╝
██║ ██║ ╚██║ ██║ ███████║██╔████╔██║██║██╔██╗ ██║███████╗
╚██╗ ██╔╝ ██║ ██║ ██╔══██║██║╚██╔╝██║██║██║╚██╗██║╚════██║
╚████╔╝ ██║ ██║ ██║ ██║██║ ╚═╝ ██║██║██║ ╚████║███████║
╚═══╝ ╚═╝ ╚═╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝╚═╝ ╚═══╝╚══════╝
Daily supplements for healthy code. A shared collection of AI development tools from the Version1 team.
This repository is public-facing. Shared skills and instructions must be generalizable and must not include secrets, private customer/project details, internal URLs, absolute local paths, incident-specific facts, or guidance that only makes sense inside one private repository.
v1tamins/
├── .agents/
│ ├── plugins/marketplace.json # Codex marketplace manifest
│ └── skills/ # Canonical shared skills for Codex and other agent runtimes
│ ├── md2docs/
│ └── ...
├── .claude-plugin/
│ └── marketplace.json # Claude Code marketplace manifest
├── claude/
│ ├── skills/ # Claude-compatible entries, symlinked or mirrored from .agents/skills
│ │ ├── code-review/
│ │ ├── pr-description/
│ │ ├── write-tests/
│ │ ├── fix-tests/
│ │ ├── deslop/
│ │ └── ...
│ └── hooks/ # Pre/post execution hooks
│ └── format.sh
├── cursor/
│ ├── commands/ # Cursor slash commands
│ │ ├── code-review.md
│ │ ├── security-audit.md
│ │ ├── write-unit-tests.md
│ │ └── ...
│ └── rules/ # Cursor rules
│ └── development.mdc
├── plugins/
│ └── v1tamins/ # Plugin package for Claude Code and Codex with generated v1-* skill mirrors
│ ├── .claude-plugin/plugin.json
│ ├── .codex-plugin/plugin.json
│ └── skills/
├── .github/
│ └── copilot-instructions.md # Repository-wide GitHub Copilot guidance
├── mcp/
│ └── mcp.json # MCP server configurations
├── scripts/
│ └── sync-skill-hosts.sh # Validate skill frontmatter and sync host metadata
└── templates/ # Reusable templates (CLAUDE.md, etc.)
# Clone the repo
git clone [email protected]:v1-io/v1tamins.git ~/v1tamins
# Run the compatibility install script
~/v1tamins/install.sh
# Copy-mode install for runtimes that reject symlink targets outside ~/.agents/skills
~/v1tamins/install.sh --copy-agent-skills
The preferred distribution is the plugin package in plugins/v1tamins/. The same package serves both Claude Code and Codex through sibling per-runtime manifests (.claude-plugin/plugin.json and .codex-plugin/plugin.json) reading from one shared skills/ directory. Plugin-distributed skills use a v1- prefix, such as v1-pr, v1-debug, and v1-address-review, to avoid collisions with other public or personal skills.
/plugin marketplace add v1-io/v1tamins
/plugin install v1tamins@v1tamins
For local development, point the marketplace at the checkout instead:
/plugin marketplace add ~/v1tamins
codex plugin marketplace add v1-io/v1tamins
Then install or enable the v1tamins plugin from Codex's plugin UI. For local development, use the checkout path instead:
codex plugin marketplace add ~/v1tamins
install.sh does not install the plugin. It remains the compatibility adapter for shared agent installs, Claude hooks, Cursor commands/rules, and older local setups.
The plugin skill files under plugins/v1tamins/skills/ are generated mirrors. Edit .agents/skills/ first, then run:
scripts/sync-skill-hosts.sh --write
scripts/sync-skill-hosts.sh
The canonical repo path for portable skills is .agents/skills/.
For repo-managed installs, keep ~/.agents/skills/ as a real user-owned directory and symlink each v1tamins skill into it:
mkdir -p ~/.agents/skills
for skill in ~/v1tamins/.agents/skills/*; do
ln -sfn "$skill" ~/.agents/skills/"$(basename "$skill")"
done
Some runtimes treat a skill symlink that resolves outside ~/.agents/skills/ as an escaped path and refuse to load it. For those runtimes, use copied agent skills instead:
~/v1tamins/install.sh --copy-agent-skills
Copied installs are refreshed by rerunning the installer. The installer marks copied v1tamins skill directories with .v1tamins-managed-copy so future runs can replace them without accumulating stale snapshots. Backups are moved to sibling .backups directories instead of staying under skill roots, because some runtimes load every SKILL.md under the root.
Do not symlink the whole ~/.agents/skills directory to this repo. Public, vendor, and personal skills installed into global skill directories should remain outside v1tamins so they do not appear in git status.
npx claudepluginhub v1-io/v1tamins --plugin v1taminsComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.