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 Code
A tool for creating a one-page or multi-section visual research report on a canvas. It combines written findings, tables, statistics, charts, and quotations in a report layout.
Skill Claude CodeCodex
Translate Claude's previous response (or any pasted text) into plain, direct English by piping it through the local Antigravity CLI (agy), with audience modes (colleague/manager/director) controlling how detailed vs. high-level the result is. Use whenever the user invokes /debuzz, asks to "de-buzzfeed" a reply, says…
Skill Claude CodeCodex
Use when a user's request is vague, ambiguous, or underspecified. Runs recon-first clarification — codebase exploration before questions, then one bundled question round with defensible defaults — and outputs a Goal Contract for the durable /goal runtime. Triggers on "I want to...", "I need...", "let's build...", "can…
Skill Claude Code
Skill "steer" from disler/mac-mini-agent, covering steer — macos gui automation, commands, how to work, 1. know your environment first and 2. focus the app, then verify.
Skill Claude CodeCodex
A guided generator for recommendation articles about tools, services, products, or other resources.
dylan-sutton-chavez/edge-python
Skill Claude CodeCodex
Write, run, test and package Edge Python programs with the edge CLI. Use when editing .py files in an Edge Python project or when the user asks for Edge Python code.
Skill Claude Code
A reusable writing-style skill template written partly in Chinese. It can learn writing rules from your edits and add those rules to its instructions over time.
Skill Claude CodeCodex
Export, write, and manage Feishu/Lark cloud documents. Supports docx, sheets, bitable, wiki, WeChat article import/export, drive management, and browser-based export for public or browser-readable docs. Use this skill when you need to read, analyze, write, or manage content in a Feishu knowledge base.
Skill Claude CodeCodex
Use before deciding how to optimize a CUDA kernel (hand-written CUDA, Triton, CUTLASS/CuTe), when a kernel is slower than expected, and whenever you are about to run Nsight Compute (ncu) or read its output — instead of guessing at the bottleneck, writing your own profiling script, or reading ncu's console tables by…
Skill Claude CodeCodex
A role-playing and analysis framework based on Donald Trump’s publicly documented statements, decisions, interviews, and behavior. It can either imitate his speaking style or use the framework to analyze how he may approach a situation.
Skill Claude CodeCodex
A skill for investigating JavaScript by collecting, searching, deobfuscating, and explaining code, including code that runs in a web browser. It also supports observing and debugging scripts and detecting cryptographic code.
Skill Claude Code
Cross-session peer coordination via the SLM mesh network. Lets multiple AI agent sessions on the same machine, and web apps the owner has allowed (ChatGPT, Claude on the web, Grok Bot, Muse, Composio), discover each other, send messages, wait for replies with meshwait, share lightweight state, and lock files to avoid…
Skill Claude CodeCodex ✓ vendor
Submit or retire an azd template in the awesome-azd gallery. Use when asked to submit, add, contribute, remove, retire, or clean up a template in awesome-azd. New submissions require only a GitHub repository URL — all metadata (title, description, languages, frameworks, Azure services, IaC) is auto-detected by the…
Skill Claude CodeCodex
OpenClaw personal agent release guard from the demo home directory.
Skill Claude CodeCodex
Use when resuming a long om-auto-create-pr-loop run, e.g. 'resume PR 123 from its next step'. Claim the PR, resume its PLAN.md Tasks in an isolated worktree, preserve per-step commits and checkpoint tests with UI screenshots, then run the full gate. Keep spec-only PRs design-only; use om-auto-continue-pr for simple…
Skill Claude Code
A research and writing workflow for in-depth technology articles. It selects topics, gathers evidence from multiple sources, tests claims, connects technology to business needs, and checks the finished article.
yunshenwuchuxun/latex-paper-skills
Skill Claude CodeCodex
Write, revise, and validate ML/AI research papers in LaTeX. Use for topic-to-paper planning, review papers, empirical papers, verified result backfill, citation audits, and academic prose refinement.
Skill Claude CodeCodex
OWASP-aligned methodology for authorized, non-destructive web application testing — authentication, authorization, injection, XSS, SSRF, file handling, business logic and misconfiguration — with the payload strategy for each class, evidence capture, and the bypasses to try before calling a class clean.
Skill Claude Code
Model-agnostic Paul Erdős ("Straight from The Book") extremal, probabilistic, and structural graph-theory skill for codebase compression (Szemerédi Regularity), Steiner context pruning, Moser–Tardos LLL parallel worktree scheduling, Erdős–Rényi supply-chain security scanning, and Ramsey clique detection across Gemini…
membranedev/application-skills
Skill Claude CodeCodex
0codekit integration. Manage Workspaces. Use when the user wants to interact with 0codekit data.
Skill Claude CodeCodex
A tool for implementing planned software features with TDD, a method where tests guide the code changes through failing, passing, and cleanup stages.
arvindrk/extract-design-system
Skill Claude CodeCodex
Extract design primitives from a public website and generate starter token files for your project.
Skill Claude CodeCodex
Control the in-app Browser. Use to open, navigate, inspect, test, click, type, screenshot, or verify local targets such as localhost, 127.0.0.1, ::1, file://, the current in-app browser tab, and websites shown side by side inside Codex.
Skill Claude CodeCodex
Deploy and operate a cloud Isaac Workstation with Isaac Automator: provision a GPU VM running Isaac Sim, Isaac Lab, and/or Isaac Lab Arena on AWS, GCP, Azure, or Alibaba Cloud, connect to it, move data in and out, control cost with stop/start, repair, import existing deployments, and destroy. Use when the user wants a…
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: