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
A tool that turns legal analysis into a structured risk report with four visual views: a radar chart, risk matrix, impact path diagram, and decision tree. These show risks, their likelihood and severity, how they spread, and possible decisions.
andrelandgraf/fullstackrecipes
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
miles990/claude-software-skills
Skill Claude Code
Enterprise-grade repository analysis with arc42/C4 architecture documentation, technical debt quantification, security assessment, and multi-stakeholder reporting.
Skill Codex
Use pyslang-mcp for compiler-backed Verilog and SystemVerilog context. Trigger this skill for RTL, HDL, Verilog, SystemVerilog, module, interface, package, .sv, .svh, .v, .vh, or .f filelist analysis, review, debugging, coding, refactoring, hierarchy inspection, diagnostics triage, symbol lookup, include/define…
Skill Claude CodeCodex
Use this skill when you need to run auto-cr on JavaScript/TypeScript code or explain how to configure it.
Skill Claude Code
Extract structured knowledge from source material. Two modes — extract (default) for comprehensive atomic claim extraction, and analyze for design proposals where one impact-analysis note replaces claim decomposition. A relevance filter ("does this change how we build our project?") applies to all modes. For extract…
Skill Claude Code needs its repo
List, inspect, submit, update, and transition form responses via Dailybot — including forms with workflow states and audience-scoped permissions. Also authors forms — create and configure a form (workflow states, permissions, anonymous/public/approval, ChatOps command) and manage its questions (types, report titles…
Skill Claude CodeCodex
Hosted-gateway LLM router — save 87% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 78 models from OpenAI, Anthropic, Google, DeepSeek, xAI, NVIDIA, and more. 6 free models included. Also exposes realtime market data (global…
Skill Claude CodeCodex
Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
Skill Codex
Use only when the user explicitly asks to perform the task through Agent Flow anywhere in the request, for example Agent Flow, AgentFlow, $agent-flow, or agent-flow. Route that request to a verified result with the smallest useful budget. Light budget stays solo; standard and release budgets may use subagents when the…
Skill Claude CodeCodex
Use when the user wants to create, improve, evaluate, inspect, run, schedule, automate, or export Skill RSI projects or Agent Skill improvement loops. In Codex desktop, every Skill RSI invocation must open the local Skill RSI web app/sidebar first.
clear0215/research-planning-architect
Skill Codex
Research-plan design for ML/AI or scientific project ideas that need evidence-backed novelty diagnosis, cross-field inspiration, top-venue/journal positioning, baseline/SOTA tables, method design, tiered experiment matrices, compute planning, and reviewer red-team. Use when Codex must turn a raw or partial idea into…
Skill Claude CodeCodex
Use when a workflow, script, schema, agent loop, evidence gate, or review step may be controlling the wrong part of the work; especially when clean structure may be freezing uncertain truth or hiding thin judgment.
Skill Claude CodeCodex
Use web-ai-sdk documentation and package references to build with the Web AI surface.
Skill Claude CodeCodex
Multi-currency settlement skill — quote, swap, and settle across 40 stablecoins via Sera Protocol.
Skill Claude CodeCodex
Manage VPS SSH aliases in /.ssh/vps.config (included from /.ssh/config) with unified key-based authentication and direct key sync.
Skill Claude CodeCodex
Scans a repo's GitHub Actions workflows for the ten critical CI/CD attack vectors — template injection, fork code executed with privileges (pwn requests), cache poisoning, impostor action SHAs, secrets dumps, GITHUBENV hijack, write-token untrusted triggers, credentials in caches/artifacts, unverified remote code…
JetQiao/football-prediction-skill
Skill Codex
Generate explainable China Sports Lottery football predictions with event-time snapshots, T-24h/T-6h/T-90m/closing model horizons, separate directional and value states, strict reference/target market isolation, sourced pre-match intelligence, hierarchical Dixon-Coles probabilities, multi-window model validation…
cz1993/vibe-coding-repository-standard
Skill Codex
Audit and establish or upgrade the canonical repository governance baseline. Use only when explicitly asked to bootstrap, standardize, or upgrade a repository; do not use for feature development or source-code restructuring.
Skill Claude CodeCodex
Use when building or editing a Blazor UI that uses the Lumeo component library (the Lumeo NuGet package and its satellites Lumeo.Charts / Lumeo.DataGrid / Lumeo.Editor / Lumeo.Scheduler / Lumeo.Gantt / Lumeo.Motion), or when the user mentions Lumeo components (Button, DataGrid, Sheet, Dialog, Tabs, DatePicker, Toast…
Skill Claude Code
Monitor the long-running task and report when it completes.
Skill Claude CodeCodex
/workspace-root = volume mount of parent dir.
Skill Claude CodeCodex
A functional test-case designer that turns approved requirements or design documents into structured QA test cases. QA, or quality assurance, is the process of checking that software works as intended.
Skill Claude CodeCodex
Use when the user explores an idea, questions whether to build something, plans a new product from scratch, or designs a feature for an existing codebase. Triggers: (1) explicit "superplanning" mention; (2) "brainstorm", "I have an idea", "explore this idea", "half-baked idea", "think through this"; (3) "is this worth…
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: