Recently added

Skills that maintain the estate itself: declared-state capture and apply, laptop sync, project scaffolding, and dotty's release step.

個人の開発運用標準を実行する。リポジトリ構成・GitHub 設定・マシンの Claude 環境を正本 (shinyaoguri/setup の repo-standards.json) と突き合わせて監査・修正・雛形生成し、作業の記録 (Issue・PR へのスクリーンショット添付、気付きの起票) を標準どおりの手順で行う

Minimalist enterprise engineering harness for Jira bugs and features: plan/implement/evaluate workflow on a light or full track, with an independent quality gate, bounded iteration, and human-controlled merge.

Lexi James's authorial voice, thinking models, and review rubric, as a Claude Code skill.

Rebuild an existing product end-to-end to learn the full product development lifecycle. A gated, agent-orchestrated pipeline: mine a reference product, build a feature matrix, slice milestones, decide architecture via mirror-or-diverge ADRs, lock contracts, build in parallel per slice, and finish at a verified production-readiness gate.

Agentile for Claude — the Claude Code implementation of the Agentile methodology for 1–5 person teams who direct AI agents: capture → shape → spec → plan → build → verify → ship → learn. Ships the fixed loop machinery (skills, agents, hooks); each project tailors its content via scaffolded .agentile/ config.

SEO記事のコンテンツ制作 Cowork プラグイン — SERPs解析→記事分析→構成案→記事作成→WP下書きを、ゲート付きワークフローと3層サブエージェント（Sonnet実行/Haiku検査/Opus統合）で回す

SEO記事のコンテンツ制作 Cowork プラグイン — SERPs解析→記事分析→構成案→記事作成→WP下書きを、ゲート付きワークフローと3層サブエージェント（Sonnet実行/Haiku検査/Opus統合）で回す

AI agent development governance skill: five quality gates, AGENTS.md entry, Git/CI enforcement for any repo.

Bootstraps a structured AI-agent instruction system for a sibling-folder multirepo workspace — parent AGENTS.md, per-repo AGENTS.md, and a canonical docs repo with PRD/TRD/ERD/Design-System/API-Contracts, agent role files, playbooks, exec-plans, and a quality score.

The AI Founder Circle conversation engine. Drafts your daily chat starts, coaches live conversations, runs your day 1-3-7 follow-up sweep, and writes hand-raising posts, all in your Voice DNA.

Source-cited Obsidian knowledge vaults for Claude Code: an inbox to ingest from, one reviewed operation per change, git history in every vault, and skills for ingesting, querying, linting, tasks that live across sessions, canvases, and Bases. Pairs with the claude-atlas binary, which serves the tools.

Automatis skills for PR reviews, port conflicts, Git cleanup, and clear technical English.

Team-ready Claude Code skill pack with 16 integrations spanning service APIs (Trello, Linear, Azure DevOps, Heroku, Sentry, Slack, Firebase, Shopify), data ops (PostgreSQL), test/QA (RSpec, Rails security, k6, Maestro, xlsx-testcases), and mobile (React Native, Fastlane). Multi-account profile support, audit logging, security-first defaults. For dev, QA, QC, testers, and team leads.

Solo ticket tracker for AI coding agents: projects, tickets with a mandatory why, dependencies, a verification gate, an ADR index, and a status report at session start. State is one JSON file.

All-in-one skill bundle — coding workflows, MR replies, and more.

Make product walkthrough and motion-graphics promo videos (MP4) from a real web app

회계검토 스킬 — mykifrs(K-IFRS·일반기업회계기준 본문 + 질의회신 3,669건)와 myfss(금감원·금융위 감독자료)로 근거를 조회해 회계이슈를 판단하고 검토의견서를 작성한다. 계약서가 있으면 조항 번호로, 없으면 설명한 사실관계로 검토한다. scan(쟁점 지도) / memo(5단계 파이프라인) 모드.

AI agent skills supporting FusionX business-analysis work — user manuals, functional testing, requirement documentation, and more.

MCP-first Tapper KEG access, flight orientation, and safety guidance.

Optional Plan to Code to Review to Commit workflow for Tapper-enabled development.

MCP-first Tapper KEG access, flight orientation, and safety guidance.

Optional Plan to Code to Review to Commit workflow for Tapper-enabled development.

Telegram channel for Claude Code — messaging bridge with built-in access control. Durable inbound store so messages survive a disconnected session (replayed on restart with a structured replay flag), forward/reply attribution, the sender's highlighted quote, and ask_decision buttons. Manage pairing, allowlists, and policy via /telegram:access.

關令 — a task tool that refuses. Includes 1 MCP server.

PHP language server (Intelephense) wired to Herd's isolated PHP version instead of the global CLI default

Laravel's first-party language server (laravel/lsp) for Blade: routes, config keys, views, translations

BugBug workflows for AI agents workflows for AI agents

Control your own browser with Agent. High-efficiency Chrome browser automation MCP server and AI agent skill.

UXD skill incubator — new skills start here before graduating to consumer plugins

UX research pipeline — heuristic evaluation, usability testing, research methodology

Create UX prototypes from Jira tickets, Figma designs, or feature descriptions

UX design workflow — Figma context, design evaluation, and implementation handoff

UXD skill routing — discover the right skills for research, design review, and prototyping workflows

PatternFly skill routing — maps project signals to the right PF sub-skills for compliance, migration, and design audits

PatternFly team tools and skill incubation — issue triage, release management, codebase auditing, new skill development

React component development — coding standards, testing, and structure

PF version migration — breaking change detection, class scanning, upgrade planning

PatternFly MCP server — provides component documentation, design token lookup, and accessibility guidance via the Model Context Protocol

Design guide — component selection, interaction patterns, AI experience patterns, Figma design creation

Design audit — validate existing code and designs against PatternFly standards

Code review and quality — adversarial review, security patterns

Accessibility auditing, reporting, and documentation

Everything you need for PatternFly development — React components, design guidance, migration, and MCP docs

Capture and recall career accomplishments — bundles the brag MCP server, the /brag slash-command, and a quiet session-end capture nudge.

A story process for Claude Code: from feature request to merged pull request, kept in GitHub issues.

Review working changes, branches, commits, ranges, or repositories with Codex from Claude Code, keeping one persistent Codex thread per review session.

Review working changes, branches, commits, ranges, or repositories with Claude from Codex.

ClaudeClaw+ — governance, orchestration, persistent memory, and hardened web UI for Claude Code daemons. Sister project to moazbuilds/claudeclaw.

Session discipline for Claude Code, enforced by checks that fail. Defines what a project must carry so a cold agent can pick it up, and what happens at the start and end of a session. Unofficial; not affiliated with Anthropic.