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
Open a pull request the safe way and handle review comments on it. Use when creating a branch, pushing work, opening a PR, or working through bot/human review threads. Encodes branch hygiene, an explicit-refspec push that can't accidentally advance main, "open the PR but never merge — bots/maintainer review," and the…
Skill Claude CodeCodex
Addresses comments made on the GitHub Pull Request tracking changes of the current branch. What this does is read all Pull Requests comments addressed to the agent, improve or fix the code based on those comments, and reply too each one of those comments. Use this when the user is asking you to address the comments…
Skill Claude CodeCodex
A general-purpose crawler for extracting product information from online shops, including names, prices, and images.
Skill Claude CodeCodex
A security service that decides whether an AI agent may call a tool. It uses user roles, task details, signed permissions, data labels, approvals, and audit records; risky requests can be stopped for human review.
Howard-Jerry/quant-agent-skills
Skill Claude Code needs its repo
A research workflow for tracking the life cycle of an investment theme and identifying the companies or other assets best connected to it. It separates broad industry research, theme-based research, and analysis of individual stocks.
green-code-initiative/ai-green-skills
Skill Claude CodeCodex
Ensures information security and compliance with French security standards.
Skill Claude Code
Build something straight from a prompt - a short requirements interview, then implement it and run an adversarial build-and-review loop until an independent reviewer is satisfied. Use when the user wants to build a feature without writing a specification first, or mentions "/freehand".
Skill Codex
Analyze exact-commit CUBRID GitHub Actions evidence collected by cubrid-ci and write an evidence-backed report under my-cubrid-docs. Use for failed-test analysis, failure attribution, root causes, or a CI analysis report for a CUBRID pull request. Use cubrid-ci status for a simple status query; this skill remains…
Skill Claude CodeCodex
Write documentation that stays accurate and decisions that stay recorded.
Skill Claude CodeCodex
Estrutura a arquitetura de um app React Native seguindo Clean Architecture — camadas, fluxo de dados unidirecional, módulos coesos e limites claros. Use ao criar módulos/features, definir estrutura de pastas ou organizar o fluxo dados→UI.
daibang123a/golang-agent-skills
Skill Claude CodeCodex
Review Go HTTP API code for compliance with REST best practices, security, and performance. 80+ rules covering routing, middleware, validation, auth, and observability. Use when building or reviewing Go web services, HTTP handlers, REST APIs, or middleware chains. Triggers: "Review my API", "Check API security"…
Kingdom1223/stk-automation-agent-toolkit
Skill Codex
Use when creating or modifying STK scenarios through automation, connecting to STK by COM or MCP, generating external ephemeris, building transmitter/receiver links, or exporting STK simulation data.
Skill Claude CodeCodex
Production pipeline for interactive and generative visual art using p5.js. Creates browser-based sketches, generative art, data visualizations, interactive experiences, 3D scenes, audio-reactive visuals, and motion graphics — exported as HTML, PNG, GIF, MP4, or SVG. Covers: 2D/3D rendering, noise and particle systems…
DBvc/agent-skill-control-theory
Skill Claude CodeCodex
Use when diagnosing an actively broken frontend behavior, regression, rendering bug, flaky UI interaction, or state/timing problem. Not for reviewing a completed diff, designing new UI, writing commit messages, or subjective visual taste critique without broken behavior.
theashishmaurya/pr-review-agent
Skill Claude CodeCodex
Backend API, database, and server-side code review.
Skill Claude CodeCodex
PostgreSQL RAG Data Ingestion and Retrieval Operations Tool - supports keyword search (BM25), vector search, and hybrid search.
254095728-bit/agent-skill-menu
Skill Codex
Discover, search, understand, organize, and inspect locally installed Agent Skills across Codex, Claude Code, GitHub Copilot, Cursor, Gemini CLI, OpenClaw, and custom roots. Use when the user asks what skills are installed, which skill fits a task, wants relevant skill options from the current conversation, searches…
Skill Claude CodeCodex
Iteratively refine beads for ralph-tui execution through 4-6 polishing rounds until convergence, ensuring each bead fits one agent context window, has quality gates appended, uses correct bd CLI syntax, and follows schema-backend-UI dependency ordering. Use when user wants to polish beads for ralph, refine ralph…
liang94211/android-agent-docs-skills
Skill Codex
Audit Android system-app Agent documentation for evidence integrity, Gradle variant and platform-branch coverage, executable verification, navigability, and code drift. Use after initial documentation, after platform adaptation changes, or whenever the documentation may no longer be trustworthy.
midFang/ai-agent-skills-workflow
Skill Codex
A procedure for fixing one tracked bug in its own Git worktree, which is a separate working copy tied to a branch. It includes self-checking the fix and building an Android APK for human testing.
Skill Claude Code
Manage AI agent skills - download from GitHub, discover skills in repositories, deploy to multiple agents with symlink support, update, uninstall with safe deletion, and track versions. Use when users want to install, manage, or update skills for AI coding assistants like Claude Code, Cursor, Windsurf, etc.
Lzy599775/agent-auto-sci-skills
Skill Claude Code
Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature attributions, handling multi-output explanations, and producing local or global SHAP visualizations.
Major-Woolfi/Skills_for_AI-Agents
Skill Claude CodeCodex
A set of coding and repository conventions covering Python, Telegram bots, project structure, typing, logging, documentation, Docker, and deployment files.
Skill Claude CodeCodex needs its repo
Use when running the full AutoSurvey-backed outline, draft, related-works, or unattended survey pipeline.
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: