Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude CodeCodex
Editorial review and publication readiness workflow that audits prose quality, resolves or injects inline review comments, and verifies technical SEO, GEO, and frontmatter metadata.
qingshanliuci/cnki-aigc---skill
Skill Claude CodeCodex
A Chinese academic-paper rewriting workflow for passages marked by CNKI's AIGC detector. CNKI is a Chinese academic database and plagiarism or AI-writing checking service; AIGC means AI-generated content.
Skill Claude CodeCodex
Write fastWorkflow skill files (skills/ .py): parameterized multi-command jobs whose steps are built in code and expanded into the agent's numbered plan, flat or as phases that pass facts to each other. Covers when to write a skill instead of a command, the file shape (Signature + PlanGenerator), the Input rules…
Skill Codex
Build, configure, provision, diagnose, verify, deploy, or extend an application created from the Miller starter. Use for projects containing miller.config.json, especially when creating an app, setting up production, configuring self-hosted Better Auth or Stripe, integrating either Next.js or an independent browser…
geekjourneyx/interactive-learning
Skill Claude CodeCodex
A guided learning workflow for turning text, links, documents, or questions into a step-by-step study session. It first decides what to learn, then checks whether you truly understand it.
Skill Claude CodeCodex
Solve a binary-exploitation / pwn CTF challenge end to end — triage the binary, find the memory-corruption bug, and build a pwntools exploit that lands a shell and reads the flag. Use when given an ELF challenge binary (often with a libc and an nc host:port), or when the user mentions buffer overflow, ret2libc, ROP…
businessbarista/daily-planner-skill
Skill Claude CodeCodex
Step 2 of daily planning (mid-morning): read the user's reply, update the list, and DM a proposed time-blocked schedule.
codejunkie99/familiar-second-brain
Skill Claude CodeCodex
Always use when working in Kimi Work desktop sessions that should read from or save to the user's Familiar second brain. Trigger for memory, notes, projects, prior work, research, summaries, durable outputs, "save this", "remember this", "from my brain", "what do I know", or any request that should use the local…
Quakedudone94/r19-iannuttall-claude-agents-devops
Skill Claude CodeCodex
☁️ DevOps & Cloud Infrastructure skill suite derived from iannuttall/claude-agents. CI/CD pipelines, container orchestration, IaC, monitoring and incident response. Provides 10 specialised commands for devops, cloud, docker workflows.
Skill Claude CodeCodex
A skill for creating and coordinating groups of AI agents to handle complex tasks. It can divide work among specialized agents and run parts in parallel or in sequence.
Skill Codex
Initialize, adapt, audit, upgrade, or downgrade projects built from gcss-v3-site-framework. Use for A1/A2/B/C delivery profiles, static-brand/cms-brand/retail setup, Astro and Sanity page models, the C Retail Catalog & Content Foundation with read-only Shopify catalog mapping, Cloudflare Worker routes, project…
huggingface/transformers-to-mlx
Skill Claude CodeCodex ✓ vendor
Convert Hugging Face transformers language models to MLX format for Apple Silicon inference. Use when asked to convert a model from transformers to MLX, port a model to MLX, create an MLX implementation of a model, or test/validate an MLX model conversion. Triggers include mentions of "convert to MLX", "MLX…
Skill Claude CodeCodex
In-session, token-efficient LLM security scan of a repo (SAST triage). A lightweight, native Claude Code pipeline — survey → threat-model → deep-dive → adversarial-verify → report — using Read/Grep/Glob (and optional subagents), no external tooling. Use when asked to "security scan", "find vulnerabilities", "SAST"…
Skill Claude CodeCodex
Connect to remote ACP server and execute commands via imclaw-cli.
Skill Claude Code
Launch multi-agent ideation to explore a concept through structured dialogue between a Free Thinker and a Grounder, arbitrated by the team lead, and documented by a Writer. Three actions: Plan (interview + configure), Ideate (depth-aware exploration + conditional production), Continue (versioned resumption with smart…
OrdinaryChart/r08-composiohq-awesome-claude-skills-ecommerce
Skill Claude CodeCodex
🛒 E-commerce & Retail skill suite derived from ComposioHQ/awesome-claude-skills. Product catalogue optimisation, conversion rate, customer journey and retail analytics. Provides 10 specialised commands for ecommerce, retail, shopify workflows.
regimentpebblehearth/r09-travisvn-awesome-claude-skills-security
Skill Claude CodeCodex
🔒 Security & Compliance skill suite derived from travisvn/awesome-claude-skills. Security audits, vulnerability management, GDPR/SOC2/ISO27001 compliance and incident response. Provides 10 specialised commands for security, compliance, gdpr workflows.
Skill Claude CodeCodex
You are running the daily research briefing or ad-hoc research workflow for the user.
Skill Claude CodeCodex
The art of keeping your AI stack small and shaped on purpose. Use when building AI features, selecting models, designing extraction/RAG/agent pipelines, or about to reach for a frontier LLM (GPT-5, Claude Opus, Gemini Pro). Enforces a smallest-tool-first ladder (regex, spaCy NER, small LLM, frontier) and challenges…
Skill Claude CodeCodex
Run the full Oh My MiniMax Code loop to independently Accepted evidence (INTAKE → DISCOVER → PLAN → PLANREVIEW → EXECUTE → VERIFY → REPAIR → ACCEPT, optional RELEASE). Triggers: "max mode", "verified mode", "run this to accepted evidence", "oh-my-mcode", "ship with evidence", "prove it passes". Do not trigger for…
Skill Codex
Implement one phase of ./specs/91-impl-plan.md end-to-end with high quality bars (correctness, elegance, performance), then run an independent code review against the relevant specs and fix every valid finding before declaring done. Use whenever the user says "build phase N", "implement the next phase", "land…
Skill Claude CodeCodex
Analyzes raw requirements into visual specs and generates artifacts. Invoke when user runs /vspec:new for analysis or /vspec:verify for models and prototypes.
zenithbaseshadow/r18-anthropics-claude-code-datascience
Skill Claude CodeCodex
🤖 Data Science & AI/ML skill suite derived from anthropics/claude-code. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.
joeseesun/qiaomu-feishu-lark-agent
Skill Claude CodeCodex
An agent for operating Feishu/Lark, a workplace platform with messaging, documents, databases, calendars, tasks, and user directories. It supports actions across those services through commands.
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: