17,533 tagged ai-agent, measured the same way as everything else here.
Browse within: LLM 341agent 300cli 284openclaw 220ai-tools 197chatgpt 193agentic-ai 180cybersecurity 160Multi-Agent 132agentskills 123curated 122myclaw 122skill-collection 121coding-agent 113
Skill Claude CodeCodex
Data-backed brief — research, source, double-verify, and render a visually rich single-file HTML report. Use when the user wants a sourced, fact-checked brief or report on a topic.
lubochka/xiigen-general-skills
Skill Claude CodeCodex
Resolve which instructions win when rules conflict. Use at the start of every task and whenever instructions disagree.
Skill Claude CodeCodex
Use when asked to proofread, review, or 校对 code or documents for correctness, logical consistency, or quality issues. Covers general code logic review (any language), plus formal-verification backends for C (ACSL contracts via Frama-C static proof and E-ACSL runtime checks), Python (icontract + CrossHair), Rust (Kani…
Skill Codex
A workflow layer for running long, mostly unattended Codex development sessions with saved state, task queues, isolated workspaces, retries, and verification records.
lastmindforever36/agent-grounded-infrastructure
Skill Claude CodeCodex
Evidence-grounded autonomous engineering router. Use when the user invokes $agi or asks for broad, ambiguous, long-running, production-grade, benchmark-driven, or high-leverage software work that should choose its own tools, skills, agents, validation, and checkpoints from live repo evidence.
Skill Claude Code
Research a strategy/market question from many YouTube videos and return a decision-led report (not summaries).
Skill Claude CodeCodex
Design and operate native thread-local cron jobs for a cron-enabled Codex CLI build.
Skill Claude CodeCodex
Guidelines for designing command-line tools that both people and coding agents can use reliably. A command-line tool is a program operated through typed commands in a terminal.
wgwtest/project-engineering-strategy
Skill Codex
Use when a software project needs durable cross-session governance for formal documents, WBS or tracker coordination, worktree delivery boundaries, evidence and acceptance states, handoffs, or architecture and design-document control.
Skill Claude Code
A multi-tab HTML planning document used as a shared workspace between a person and an AI agent. It can contain a plan and activity log, with optional tabs for requirements, user stories, user flows, and tasks.
Skill Claude CodeCodex
Skill "agent-browser" from skytiger6724/gemini-skills, covering browser automation with agent-browser, core workflow, command chaining, chain open + wait + snapshot in one call and chain multiple interactions.
Skill Claude CodeCodex
Content creation pipeline orchestrator for any AI agent. Chains great-writer -> brilliant-visualizer -> typeset -> deliver into a complete write-to-deliver flow. Optional multi-platform publishing via /publish skill (superb-publisher). Loose coupling: depends only on skill names and I/O contracts, not sub-skill…
Skill Claude CodeCodex
A pragmatic working-rules skill for agents. It makes agents more direct, judgment-oriented, less repetitive, and more careful before executing complex tasks.
Skill Claude CodeCodex needs its repo
Extract design information from Figma files. Pull design tokens, component structure, colors, typography, spacing, and export assets. Use when the user asks about their Figma designs, needs to extract design tokens, or wants to convert Figma designs to code. Triggers on: "figma", "design tokens", "get colors from…
Skill Claude CodeCodex
Skill "public" from to-agent/agent-exec, covering skill: agent-exec, endpoint: get /, what is this?, root surface and start.
Skill Claude CodeCodex
Analyze AI coding-agent runs and generate user-facing replay reports. Use when Codex needs to review Codex, Claude Code, OpenCode, Gemini CLI, or other coding-agent transcripts/logs; debug agent behavior; summarize file changes, commands, failures, interruptions, verification, and risks; or create Markdown/HTML…
GabrielPazBR/agente-de-projeto
Skill Claude CodeCodex
Cria, implanta ou repara um agente de projeto no Codex, com MemPalace local, Graphify, RTK, servidores MCP, skills, perfil funcional e AGENTS.md persistente. Use na configuração inicial de um workspace ou para diagnosticar uma implantação existente.
Skill Claude CodeCodex
Use mnemex before implementing a significant code change. Mnemex is a local-first decision-integrity layer: it anchors a decision to code and reports whether that decision is still fresh.
Skill Claude CodeCodex
Test web applications in real browsers via Chrome DevTools Protocol including DOM inspection, console analysis, network profiling, performance auditing, Lighthouse CI, and visual regression.
Skill Claude CodeCodex
Turn requirements into validated, executable plans. C31-brainstorm defines WHAT; C31-plan defines HOW — with coverage gates, wave analysis, and threat modeling.
yay0128/skill-document-analysis
Skill Claude CodeCodex
A general framework for examining documents, from contracts and procedures to research papers and notes. It first identifies a document's type and purpose, then produces a structured review with a quality score.
architect-4-citadell/elektra-skills
Skill Claude CodeCodex
Autonomous Goal-directed Iteration. Apply Karpathy's autoresearch principles to ANY task. Loops autonomously -- modify, verify, keep/discard, repeat. Supports bounded iteration via Iterations: N inline config.
lililly123789/wechat-article-scraper
Skill Claude CodeCodex
A batch tool for downloading WeChat public-account articles from their URLs as Markdown files. It also downloads the articles' images and links them locally.
METAXGTSEOSEM/Awesome-post-skills
Skill Codex
Generate B2B industrial product page content optimized for Google rankings and RankMath SEO scoring. Covers product title (3 variants), short description, features (feature -> benefit), application scenarios, MD-formatted spec tables, FAQ, schema markup, and full keyword placement (primary/secondary/LSI in title, URL…
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: