By BenjaminG
Benjamin's collection of Claude Code skills — daily workflow, code quality, dev tools, and specialist agents.
Reviews JSX/TSX in a code diff for accessibility regressions. Invoked by the gate-wf workflow when .tsx/.jsx files are present.
Reviews a code diff for logic bugs, spec-code mismatches, and cross-file behavioral parity gaps. Invoked by the gate-wf workflow.
Checks reviewer findings against project context (CLAUDE.md, ADRs, Linear, PR comments, past sessions) and synthesizes findings for documented-rule violations. Invoked by the gate-wf workflow.
Reviews JSX/TSX in a code diff for i18n/l10n regressions. Invoked by the gate-wf workflow when .tsx/.jsx files plus an i18n library are present.
Reviews database migrations and bulk-update operations in a code diff for data-loss and rollback risks. Invoked by the gate-wf workflow when migration files or bulk-update APIs are present.
Use Atlassian CLI (acli) to manage Jira work items, projects, and workflows from the command line. Ideal for bulk operations, automation, scripting, and when users request CLI-based Jira interactions. Trigger on requests like "use Jira CLI", "create Jira issues via CLI", "bulk update Jira tickets", "automate Jira workflows", or when users want to script Jira operations.
This skill should be used when implementing code that requires SOLID principles and clean code practices. It provides detailed guidance on Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, and Dependency Inversion principles with comparison examples in TypeScript.
Specialist for TypeScript backend development including Node.js servers, NestJS applications, APIs, databases (PostgreSQL, MongoDB, Redis), authentication, testing, deployment, server-side code, microservices, database queries, migrations, controllers, services, repositories, and middleware. Use for ANY work involving .ts backend files, server-side architecture, performance optimization, and backend security.
This skill should be used when the user wants to write their end-of-day / evening "build-in-public" update for a given Linear project — 3-4 impact-focused bullets plus a Next line synthesized from the project's Linear activity and the repo's git/PR shipping evidence, ready to paste into the pod thread. Invoke as /build-in-public with a Linear project ID. Triggers on "build-in-public post", "evening update", "what did I ship today", "end-of-day update", or any variant of "what did I do today" for a work update — even without the word "skill". Default to drafting; never post anywhere automatically.
Interact with a local Chrome browser session via Chrome DevTools Protocol (only on explicit user approval after being asked to inspect, debug, or interact with a page open in Chrome). Pass `--isolated` to drive a sandboxed Chrome with a dedicated profile instead of the user's real browser.
Uses power tools
Uses Bash, Write, or Edit tools
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.
Benjamin's collection of skills for Claude Code, Codex, and other AI agents — packaged as a plugin and as a skills-installable bundle.
/plugin marketplace add BenjaminG/ai-skills
/plugin install ai-skills@bgelis-ai-skills
Skills are namespaced after install: /ai-skills:gate, /ai-skills:interview, etc.
codex plugin marketplace add BenjaminG/ai-skills
codex plugin add ai-skills@bgelis-ai-skills
You can also install it from codex → /plugins → bgelis-ai-skills.
npx skills add BenjaminG/ai-skills
See the skills CLI docs for scoping flags (-g global, -a <agent>, etc.).
| Skill | Description |
|---|---|
| Daily workflow | |
daily-update | Draft a daily Slack update from Linear |
| Code quality | |
applying-solid-principles | SOLID principles and clean code practices |
code-slop | Detect and fix slop patterns |
gate | Deterministic branch quality gate with parallel reviewers |
quality-gate | Quality gate review for React/Next.js |
refactor-instructions | Code refactoring guidelines |
second-pass | Second-pass review of recent work |
ubiquitous-language | Domain-driven naming review |
| Review & PR | |
consensus | Run a prompt N times and consolidate by vote |
pr | Publish a PR with type detection + Linear/Jira linking |
pr-feedback | Triage and resolve PR review comments |
qa-plan | Manual QA plan generation |
qa-run | Execute a manual QA plan |
| Developer tools | |
acli | Jira management via acli |
chrome-cdp | Drive a local Chrome session via DevTools Protocol |
codex-cli | OpenAI Codex CLI for automated code analysis |
commit | Stage + commit with auto-generated message |
confluence-cli | Confluence content management via CLI |
hooks | Create and manage Claude Code hooks |
| Investigation & planning | |
elevate | Elevate a draft idea into a sharp proposal |
innovate | Generate divergent solutions for a problem |
interview | One-question-at-a-time clarification loop |
investigate | Structured investigation workflow |
ralph-loop | Run autonomous iterative loops over multi-step tasks |
retrospective | Reflect on the work done on the current branch vs main |
skill-creator | Guide for creating skills |
| Specialist agents | |
backend-developer | TypeScript backend specialist |
frontend-developer | React/TypeScript frontend specialist |
swiftui-performance | SwiftUI performance optimization |
ui-skills | Opinionated constraints for better interfaces |
.
├── .agents/
│ └── plugins/
│ └── marketplace.json # Codex marketplace catalog
├── .claude-plugin/
│ ├── plugin.json # Claude Code plugin manifest
│ └── marketplace.json # one-plugin marketplace catalog
├── .codex-plugin/
│ └── plugin.json # Codex plugin manifest
├── plugins/
│ └── ai-skills -> .. # Codex marketplace path to root plugin
├── scripts/
│ └── bump-version.sh # bump version in both manifests + tag a release
├── skills/ # all skills live here as <name>/SKILL.md
└── ...
# Test the Claude Code plugin locally without installing
claude --plugin-dir .
# Reload after edits
/reload-plugins
To create a new skill, see skills/skill-creator/SKILL.md.
Both plugin manifests carry a version field (semver). Claude Code's /plugin update
compares it: users only receive an update once the number changes — pushing commits
without a bump ships nothing. Codex compares it the same way.
Bump both manifests in lockstep and tag the release with the helper:
scripts/bump-version.sh patch # 1.0.0 -> 1.0.1
scripts/bump-version.sh minor # 1.0.0 -> 1.1.0
scripts/bump-version.sh major # 1.0.0 -> 2.0.0
scripts/bump-version.sh 1.4.0 # explicit
scripts/bump-version.sh patch -n # rewrite manifests only, no commit/tag
It updates .claude-plugin/plugin.json and .codex-plugin/plugin.json, commits as
chore(release): vX.Y.Z, and creates an annotated tag — but does not push. Ship it:
git push && git push origin vX.Y.Z
npx claudepluginhub benjaming/ai-skills --plugin ai-skillsComprehensive 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.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
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
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.