23 structured quality engineering skills for automotive and manufacturing — ISO 9001, IATF 16949, AIAG-VDA FMEA, VDA 6.3, PPAP, APQP, SPC, MSA. Works with Claude Code, Codex CLI, Cursor, Gemini CLI, and any agentskills.io-compatible tool.
31 skills
Every plugin for OpenAI Codex on GitHub — repos with a .codex-plugin/plugin.json or a Codex marketplace. Install with codex plugin marketplace add owner/repo then codex plugin add name@marketplace. Many work in both tools; see Claude Code plugins.
23 structured quality engineering skills for automotive and manufacturing — ISO 9001, IATF 16949, AIAG-VDA FMEA, VDA 6.3, PPAP, APQP, SPC, MSA. Works with Claude Code, Codex CLI, Cursor, Gemini CLI, and any agentskills.io-compatible tool.
31 skills
Multi-CLI swarm in tmux with discuss / vote (v0.6: LLM-first, multi-round, files injection, auto-promote) / execute modes.
13 skills · 13 commands
The complete self-hosted Cross-Session Memory runtime and lifecycle automation, native to Claude Code.
3 skills · 12 commands · 3 agents · 1 MCP server · hooks
Skills for building Python apps with Tap Strap, TapXR, and TapBand: connect, taps, air gestures, vision models, IMU motion, raw sensors, and knob / D-Pad gesture recipes.
8 skills
Cite-check drafts against real sources, find verified authorities, proofread, build Zotero libraries, write research memos, and prep Supreme Court cases.
7 skills · hooks
Reports and memos bury the answer under background, so readers must reconstruct the argument and decisions stall. This plugin applies Barbara Minto's Pyramid Principle (answer first, MECE-grouped support) and keeps a separate source-integrity layer that requires a specific source, locator, and confidence for every fact. Your reader gets the decision in the first sentence and can trust every number under it.
6 skills · 1 command
Token-economy observatory for Claude Code: forensic per-session audit, A/B savings verifier, reproducible benchmark, and cost prediction — directly in Claude chat. Auto-installs via npx on first use.
4 skills · 1 MCP server
Three MCP servers for PHP and JavaScript operations. PHP (php-tooling): PHPStan, ECS, Rector, PHPUnit, PHPUnit coverage gap analysis, Symfony Console. Administration (js-admin-tooling): ESLint, Stylelint, Prettier, Jest, TypeScript, Vite builds. Storefront (js-storefront-tooling): ESLint, Stylelint, Jest, Webpack builds. Includes SessionStart hook that injects MCP tool directives and PreToolUse hooks that enforce MCP tool usage by blocking bash commands. Supports native, Docker, Docker Compose, Vagrant and DDEV environments.
1 agent · 3 MCP servers · hooks
AIが書いた日本語ドキュメントから読解負荷の高い構文を削ぎ落とし、一読で理解できる本文に書き直すプラグイン。LLM定型句の検出(prh辞書)、AI臭の体裁・誇張語の検出(preset-ai-writing)、段落レベルの冗長排除に対応。やさしい日本語化スキル(meiseki:yorisoi)も同梱。Claude Code と Codex CLI の両方で動く。
4 skills · hooks
UbD 逆向设计驱动的教材写作 skill 组合:教学定位 → UbD 预期结果 → 章节树 → 四段式逐章写作 → 每题按学科档案验证,产出有主线、有梯度、可评估的成体系教材;内置 STEM、人文社科、经济学三份学科档案
5 skills
Native AgentBook version control and continuity infrastructure for agent work.
2 skills · 1 MCP server · hooks
Set up WorkOS AuthKit with no account: npx workos@latest install provisions an environment you can claim later. Also covers SSO, Directory Sync, RBAC, Vault, Audit Logs, migrations, and API references.
2 skills
Create media and control the QCut desktop video editor from Claude Code.
2 skills
Query and export from the macOS Apple Photos library via osxphotos - search by date/album/keyword/person, list albums and folders, fetch metadata, export originals or edited photos, and (opt-in via APPLE_PHOTOS_MCP_ENABLE_WRITES=1) organize albums and set titles/keywords/favorites (macOS only)
1 skill · 1 MCP server
Routes PixelLab asset/API requests across MCP, REST v2, website/editor workflows, Aseprite, Pixelorama, and legacy v1.
1 skill
Find repeated manual work in activity records. Get automation proposals with evidence and work counts for your review.
1 skill
YNAB MCP connector for budgets, transactions, categories, scheduled transactions, accounts, months, payees, and budget review workflows.
Build, debug, profile, test, refactor, and release Swift apps across iOS, macOS, Xcode, SwiftUI, SwiftPM, Tuist, and App Store Connect.
61 skills · 3 commands · 3 MCP servers
Convene a board of frontier AI models — Claude, Codex, Gemini, and Grok — that each review the same decision independently, debate across rounds, and hand back one clear recommendation.
30 skills
Seventeen skills that ship as one pack — a portable discipline for tracked, multi-session, agent-assisted development: the orchestrator seat a non-engineer works from (one session routing, auditing, and merging parallel lanes), a router entry point, a once-per-repo setup interview that records whether you lead from that seat or read code and pick skills, per-repo institutional memory written as side effects of work, relentless grilling, decision maps, throwaway prototypes, autonomous research lanes, ticket filing, human-step wizards, session handoffs, a build discipline of seam-scoped test-first tracer slices, a disciplined bug-diagnosis loop where no fix ships without a named cause, an adversarial review that breaks changes before they ship, a skeptic-verified state review of the codebase itself, an append-only decision trail that lets a human audit an unattended run after stepping away, and a PR-writing standard that leads with the problem, shows before-and-after proof, and says whether a revert undoes the change. Versioned together (team-workflow/vX.Y.Z); this version mirrors the latest pack tag.
30 skills
Turn a video, recording, voice memo, or media URL into an evidence packet — authoritative whisper transcript, timestamped frames, manifest — plus a routing recommendation. Six intents behind a mandatory purpose gate; the pipeline script is resumable and encodes the hard-won gotchas.
30 skills
Turn your agent into a senior geospatial data scientist: 18 skills for the full GeoAI lifecycle, including guarded ArcGIS Pro automation, with spatial failure modes designed out.
18 skills
AI News tracking, deep research, Notion/Teams/Slack publishing, and a 5-axis LLM-as-judge quality eval harness for Codex.
11 skills · 3 agents · 2 MCP servers
SpecDD-guided skills for working inside spec-driven development projects.
15 skills
Riccardo's public Antigravity custom commands, GCP/SRE tools, and agent skills.
7 skills · 3 commands
Review pull requests on GitHub, GitLab and Bitbucket across many stacks, learning each repo's own conventions over time and posting one review through that vendor's own CLI or REST API.
7 commands · hooks
Local graph memory that lets Codex recall project context across sessions.
4 skills · 1 MCP server
Official Scraps LLM Wiki bundle. Skills and agents for ingesting sources, querying the wiki, applying the default Scraps LLM Wiki schema, and running purpose-driven lint via the scraps CLI.
2 skills · 2 agents
Control native Mac apps — Calendar, Mail, Notes, Reminders, Messages — and drive any Mac app via Computer Use. Runs on-device. Requires the Macuse macOS app.
3 skills · 1 MCP server
한국 정부·공공기관 소상공인 지원사업 전수조사 스킬 — K-Startup·기업마당·NIPA·KOCCA·SMTECH 크롤링 + 즉시/로드맵/변형 3분류.
2 skills · hooks