52,571 tagged ai-agents, measured the same way as everything else here.
Browse within: LLM 348agentic-ai 322agent 227antigravity 221chatgpt 214agentic-skills 192ai-workflows 185coding-agents 174cli 145ai-assistant 131agents 109openclaw 94claude-code-skills 82agent-infrastructure 81
may215/antigravity-awesome-group-skills
Skill Claude CodeCodex
Group skill: Comprehensive security audit — threat modeling, SAST, dependency check, auth review, API security, pen testing, secrets check, GDPR, hardening, and compliance report.
alessio-locatelli/ceo-agent-workflow
Skill Claude Code
Carry out the set of tasks a CEO does each session.
ky-ji/xie-saining-research-taste-skills
Skill Codex
Use when evaluating AI/ML research ideas, choosing research directions, framing problems, planning experiments, improving research taste or paper storytelling, resisting trend-following, or applying Saining Xie's interview-derived views on visual intelligence, world models, research culture, and scientific taste.
Skill Claude CodeCodex
PRD-driven delivery loop with a token-lean audit trail (requests → decisions → specs → tasks → commits). All docs/ log access goes through ./scripts/owl. Use for any feature, bug fix, or change in a repo using ATHENA docs/.
Skill Claude CodeCodex
Initializes the AGENTSYNC.md hub for AI agent coordination and task tracking.
Skill Claude CodeCodex
Use when authoring, editing, or reviewing a SKILL.md file — lints it against the Agent Skills best-practice rules and checks whether the description would actually activate the skill on the prompts it claims to cover, before the skill ships.
dososo/blcaptain-research-driven
Skill Claude CodeCodex
Improves research quality when accuracy matters; work depends on external facts such as documentation, APIs, pricing, licenses, standards, current events, research, or source code; a question is complex or multi-part; confidence is low; or sources conflict. Excludes casual chat, pure formatting, mechanical edits, and…
Skill Claude CodeCodex
Use a fresh task profile and a four-level policy to turn material ambiguity into a precise, self-contained prompt without asking the user to make technical choices the agent can investigate.
Skill Claude CodeCodex
Persistent memory system for AI coding agents. Use when you need to save facts about the user, store interaction preferences, log session events, or search previously saved memories. Triggers on remembering, saving context, recalling past decisions, or when the user says "remember this". Also use proactively when the…
ASER-ho/coding-agent-safety-gate
Skill Claude CodeCodex
A set of safety rules for keeping an AI coding assistant within an approved workspace, task, file scope, and security boundary.
Skill Claude CodeCodex
A repository audit and cleanup tool for AI coding-agent instructions, such as AGENTS.md, CLAUDE.md, and editor-specific rule files. It consolidates these instructions into AGENTS.md and adds checks to detect later drift.
Skill Claude CodeCodex
Delegate tasks or get a second opinion from Claude Code CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Claude Code, or offloading work to it. Do not use when already running inside Claude Code…
Skill Claude CodeCodex
Run, inspect, resume, and stop Agent Workflow Kit workflows from Codex.
Skill Claude CodeCodex needs its repo
Turn notes (Notion, Google Docs, Markdown) into branded 1920×1080 HTML slide decks with PDF and PNG export. Pulls real brand tokens from any URL.
Skill Claude Code
A guided process for choosing a user interface’s visual direction and recording the decisions in DESIGN.md.
papperrollinggery/zhijuan-codex-agency-chief-of-staf
Skill Codex
A coordinator for complex, multi-stage projects that span conversations and tasks. It helps discuss requirements, create execution plans, assign roles, track progress, and preserve useful project knowledge.
Skill Codex
Coordinate bounded Claude implementation workers with durable authenticated A2A/LAN jobs, explicit evidence, recovery, and read-only verification.
catalystsystemslab/codex-skill-sync
Skill Codex
Simple sync flow for installed SKILL.md skills and Codex plugins. Use when the user says /skill-sync, check skills, update skills, run all skill updates, map skill repos, refresh Codex plugins, or create weekly skill maintenance.
Skill Claude CodeCodex
A guide for writing concise Git commit messages that match a repository's existing style. Git commits are saved records of code changes, and the guide also covers separating unrelated changes into different commits.
Skill Claude CodeCodex
Review tracker issue readiness before implementation and draft the appropriate no-mutation tracker update.
Skill Claude CodeCodex
Research one sales contact from their name + company or their email address, and write a Markdown brief — role, recent posts and talks, interests, company context, trigger events, and conversation-starter hooks — using free web search plus a few paid calls billed through taskfuel.ai. Use when the user wants background…
Skill Claude CodeCodex
Turn a one-line goal from the user into a complete, ordered task spec and drop it into the inbox/ folder for Cowork to execute unattended. Use whenever the user states a goal they want handed off / run later / done autonomously, or says things like "queue this", "hand this to Cowork", "add a task", or "I want X done".…
Skill Claude CodeCodex
Web accessibility best practices for semantic HTML, ARIA attributes, and WCAG color contrast. Use this skill whenever the user writes, reviews, or fixes HTML/JSX/TSX/Svelte markup or UI components, builds page structure, navigation, forms, buttons, modals, or tabs, picks text/background colors or theme tokens, or…
Skill Claude CodeCodex
Security auditing skill for web applications and codebases. Scans for OWASP Top 10, dependency vulnerabilities, secrets exposure, XSS/CSRF/injection flaws, auth weaknesses, and misconfigurations. Use when task involves security scan, vulnerability assessment, pen test review, threat modeling, or hardening a codebase.
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: