Top 62 AI agent skills, agents, and paid APIs ranked by community votes.
Link the whole of agentlist to your agent. Find trending skills, vote and compare across everything uploaded
Convert markdown to a professionally formatted PDF via a simple REST API. No account or API key required — access is gated by L402 Lightning payments, making it ideal for agents that need to generate documents on the fly. Full API reference: https://markdown2pdf.ai/api-reference/overview
Hardens a project against npm/PyPI supply chain attacks (like the TanStack incident) by enforcing package age gates, pinning exact versions, and committing lockfiles
name: karpathy-guidelines
Forces the laziest solution that actually works, simplest, shortest, most minimal.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise.
name: obsidian-vault
Shape output for a reader with ADHD.
Operate the syntheticdocs app from any AI agent: sign in with your own credentials, manage projects and source documents, edit the canvas (document template), run RAG text generation, and produce/download PDF or DOCX documents via the bundled sdocs wrapper script.
Summarise the user's GitHub activity for a given day (default today) in a fixed format.
Fetches tweets from an X (Twitter) list via the X API v2.
You've been paying Opus prices for Haiku work. Stop Burning Tokens fixes that.
Fool proof invoicing and expense tracking, saving files locally or in Google Drive
name: humanizer
Using an act - aim - audience and knowledge framework this skill will ensure the written output keeps a red thread and keeps the readers attention while reading. Encourages the user to provide more content as well if it’s a bit light. Tries not to fabricate things.
A base for software teams building across projects, it aims to improve readability, reviewability of code outputs and the delight of your colleagues. The file is minimal enough to not waste tokens while still capturing the most essential parts of making everybody's life easier. Best saved at a user level (~/.claude (rename to CLAUDE.md), ~/.opencode etc). Project AGENT.md files can still exist on a project level and will also be considered.
Clean and finalize authorized natural-language text intended for readers by auditing suspicious invisible Unicode and rewriting prose while preserving facts, meaning, and the writer's voice.
Call a free, deterministic index of 56 AI crawlers and their operators: which bot a user-agent string is, whether an IP really belongs to GPTBot or is spoofing it, what blocking a given crawler actually costs, and a robots.txt generated from that answer. A2A JSON-RPC and MCP Streamable HTTP, no key, no signup, no quota. Rebuilt every six hours from each operator's own published documentation and IP ranges.
Run a multi-agent co-editing workflow for non-trivial implementation work.
Triage and remediate Semgrep SAST findings for a repo.
clean
Compact the current conversation into a handoff document for another agent to pick up.
Invoicing and expense tracking for a small business, stored as plain markdown. Create invoices, log expenses, record full or partial payments, see what is outstanding, and run a P&L. Every total is derived from the record files on demand rather than cached in a ledger, so the books cannot silently drift. A corrected rewrite of full-business-accounting v1.0.0 (MIT), which decremented Outstanding on payment but never incremented it on invoice creation.
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding).
Apple's approach to interface design and fluid, physical motion, translated for the web.
Grill me about specs for the workflows I want to build, within this workspace.
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute.
Marc Andreessens current agent file. Source: https://x.com/pmarca/status/2051374498994364529
Cut AI tells from any writing.
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target.
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away.
Use for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences or working style into a skill\", or wanting agents to follow how the user works.
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
8 data tools surfacing crypto + US-equity alpha to AI agents via MCP
Perform structured reconnaissance and attack surface enumeration for authorized penetration tests, CTF challenges, and bug bounty programs.
Audit applications for AI prompt injection, agent security, and LLM permission boundary vulnerabilities.
Audit application source code against the OWASP Top 10 vulnerability categories.
Gather and correlate open source intelligence from public sources for authorized investigations, threat intelligence, and attack surface assessment.
Guide rapid triage and initial response to security incidents following NIST SP 800-61 methodology.
Analyze disk images and file systems for digital evidence recovery in forensic investigations and CTF challenges.
Audit cloud infrastructure (AWS, GCP, Azure) for misconfigurations, excessive permissions, and security gaps.
Audit project dependencies, frameworks, languages, and dev tools for known vulnerabilities, CVEs, and security anti-patterns.
Compact the current conversation into a handoff document for another agent to pick up.
Elite frontend image-direction skill for generating premium, artistic, implementation-friendly website design references.
name: voice-builder
Generates a hand drawn infographic prompt that pulled 480k impressions over 3 posts!
Rebuild a LinkedIn profile for maximum conversions
Turn a LinkedIn Analytics export into an interactive dark-themed React dashboard
Investigates git history to understand why code exists before touching it.
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
Produces presentable PDFs from markdown documents. From agents. To Humans
Write better skills for agents
name: qa
Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.
Creates a sharable QR code of your wifi details for guests to scan. Built for Google Edge Gallery
Pinata's x402 system lets agents upload files to IPFS and serve them behind a pay-per-access paywall — or consume content gated by other publishers. Monetized files are served via Pinata's dedicated gateway; consumers receive a 402 response with USDC payment terms, pay on Base, then include the proof in the `X-Payment` header to receive the file. Full docs: https://docs.pinata.cloud/files/x402/x402-quick-start.md
The leading API for Farcaster social protocol data — covering users, casts, social graphs, and feeds from the decentralized Farcaster network. Agents can look up user profiles by FID, fetch follower graphs, read channel feeds, and publish casts without a subscription by paying per request via x402. Full API reference at https://docs.neynar.com/reference/quickstart
Real-time on-chain analytics with an impressive suite of endpoints covering smart money tracking, wallet balances, PnL, DEX trades, token flows, and counterparty analysis. Agents can pull premium blockchain data without an API key or subscription — pay per request in USDC via Base or Solana using the x402 protocol. Basic endpoints start at $0.01/call; smart money and premium analytics at $0.05/call. See the full endpoint list at https://docs.nansen.ai/getting-started/x402-payments
Email-only laundry pickup and delivery in Manhattan for busy professionals, with simple pricing and no app required.
This skill is written in shorthand AAAK compression. Your agent will understand it, and does contain curriculum for the citizenship test. Load it in your local model before going on the plane.
Minimal AGENTS.md that makes the agent speak in caveman language in chat and user-facing discussion, while keeping files and other saved artifacts normal and professional. Inspired by om_patel5 on X/Twitter.