Skill Claude CodeCodex
Design effective automated workflows using scheduled tasks, prompt chaining, and delivery channels.
not rated 1.6k
+9 today A SkillSpector: pass 19 tokens
original Apache-2.0
afm
02Skill Claude CodeCodex needs its repo
Maintain and extend AFM (maclocal-api), a Swift OpenAI-compatible local LLM server and CLI for Apple Foundation Models, MLX models, API gateway proxying, and Vision OCR. Use when working on AFM CLI commands (afm, afm mlx, afm vision), OpenAI /v1/chat/completions and /v1/models behavior, streaming SSE, tool-calling…
not rated 347
+1 5d ago A SkillSpector: pass 114 tokens
original MIT
Skill Claude CodeCodex
Use when answering from or editing an Open Knowledge Format (OKF) bundle, a knowledge folder of markdown concept files with YAML frontmatter and index.md and log.md files.
not rated 336
+13 today A 40 tokens
original Apache-2.0
alexa
04Skill Claude Code
Expose HybridClaw as a custom Alexa skill and prepare guarded Alexa smart-home/device control payloads without exposing Amazon credentials.
not rated 159
changed 19d ago A SkillSpector: warn 27 tokens
original MIT
Skill Claude CodeCodex
Run local black-box voice tests against the physical Dotty robot by playing a TTS prompt through the workstation speakers while the C920 records video and room audio. Use when testing Dotty's wake word, ASR, spoken response, expressions, or end-to-end voice behavior on this bench.
not rated 114 4d ago B 64 tokens
original MIT
lilbee-mcp
06Skill Claude CodeCodex
Search and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.…
not rated 66
+2
changed 4d ago A SkillSpector: warn 95 tokens
original MIT
Skill Claude CodeCodex
You are a seasoned, atmospheric Game Master running a persistent tabletop RPG campaign. Your tone is immersive and descriptive — paint scenes with sensory detail, give NPCs distinct voices, and let choices have real consequences. You lean toward "yes, and..." rulings and fun over rigid rule enforcement, but the world…
not rated 59 7d ago A 0 tokens
tiktok-video
08Skill Claude CodeCodex
A workflow for making vertical short videos for TikTok or Douyin from a written request. It creates a storyboard, voiceover, word-timed karaoke captions, background music, and a 1080×1920 MP4 video.
not rated 51
+1 2d ago A SkillSpector: pass 59 tokens
original MIT
Skill Claude CodeCodex
Use when implementing Redis caching strategies, session management, pub/sub messaging, data structure operations, Lua scripting, transactions, clustering, persistence, and production Redis best practices. Covers all Redis data types, caching patterns, and client libraries.
not rated 51 3mo ago A 50 tokens
original MIT
Skill Claude Code
Review and fix Gemini API usage against Google's official best practices. Use when modifying src/core/gemini.ts, adding new API calls, or auditing Gemini integration quality.
not rated 36 4d ago A 40 tokens
copy · 100% MIT
project-map
11Skill Claude CodeCodex
Use this skill when the user asks for project structure, architecture map, or file overview.
not rated 21 7mo ago A 0 tokens
original MIT
bharat2808/codex-universal-proxy
Skill Claude CodeCodex
Install and manage the unofficial codex-universal-proxy local compatibility tool. Use when the user wants Codex to install it from npm, clone/download the repo, configure model routing, start/restart/inspect the proxy, switch the local experimental Ollama/proxy workflow on or off, or uninstall it.
not rated 18 1mo ago A SkillSpector: warn 69 tokens
original MIT
Skill Claude Code
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
not rated 7 5mo ago A 64 tokens
radif-ru/ai-multi-agent-system
Skill Claude CodeCodex
A read-only assistant for reviewing incoming Yandex or Gmail messages from a chat.
not rated 6 12d ago A 61 tokens
original MIT
Skill Claude CodeCodex
XLSX workbook work. Load for XLSX, Excel workbook, or spreadsheet deliverable.
not rated 6
changed 1mo ago A 23 tokens
original Apache-2.0
hermit-audit
16Skill Claude CodeCodex
A read-only audit checklist for Hermit and Claude Code setups, covering how they are structured, used, checked, and improved, including token use and model selection.
not rated 4 1mo ago A 133 tokens
original MIT
pp-llamaswap
17Skill Claude Code
The llama-swap operations console — durable history, drain-aware control, and measurement commands with three specific guarantees: keep-set unloads are refused statically by id AND alias (never from server ttl), --drain fails closed when slot state is unreadable, and fit/ctx refuse to answer inside their uncertainty…
not rated 4
+1
changed 15d ago A 138 tokens
original Apache-2.0
gemmamatch
18Skill Claude CodeCodex
Auto-detect hardware and recommend the best Gemma 4 model for local deployment on PC, Mac, or mobile.
not rated 2 6mo ago A 28 tokens
test-ui
19rahulcvwebsitehosting/wayfinder
Skill Claude Code
Test the Wayfinder agent extension UI by starting the dev environment and visually verifying changes via CDP. Covers the new tab page (left sidebar — Home, Scheduled Tasks, Settings, etc.) and the right side panel (chat interface). Use after making UI changes to apps/agent/.
not rated 2 3mo ago A 60 tokens
AGPL-3.0
alejandro-ventures/llm-agnostic-icm-framework
Skill Claude Code needs its repo
Remove backgrounds from portrait and general images, outputting PNGs with transparent backgrounds.
not rated 2 2mo ago A 19 tokens
original Apache-2.0
anjian-audit
21ck3938700-ship-it/anjian-agent
Skill Claude CodeCodex
Use AnJian MCP tools for an authorization-gated website security assessment and Chinese report.
not rated 0 2mo ago A 23 tokens
original MIT
mgannotti/scout-plugin-hybrid-routing
Skill Claude CodeCodex
Route a task to the right model across a hybrid stack — Scout's hosted cloud models, on-device runtimes (Ollama, LM Studio, Foundry Local, llama.cpp, vLLM), and org-hosted endpoints — by classifying it on sensitivity, role and difficulty, and enforcing an egress boundary so confidential and restricted content never…
not rated 0 2mo ago A 138 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: