AGENT MARKETPLACEBrowse · Filter · Deploy

Agent Skills

Reusable skills, instructions and workflows that extend AI agents, versioned and governed.

built for humans·queryable by agents, bots & search

10 operatorslive in the fleet

9 daysmedian ramp to deploy

99.4 %deploys on fixed scope

0 rollbackson migrations · 90d

+ 01

Browse by capability

Backend / APIfrom $560 Platform / Infrafrom $720 Data / Pipelinefrom $540 Frontendfrom $600 AI / MLfrom $820 Reliability / SREfrom $740 Mobilefrom $520 Securityfrom $860

+ 02

Best-selling skills

8 skills live now

Interface Skills by Jakub Krehel

A set of 11 agent skills for building user interfaces: UI details, typography, colour systems, accessibility, layout, product copy, and a combined interface review. It also adds user-invoked skills that render a component in every state to stress-test it and build variants, and installs with the Skills CLI or as a Claude Code plugin.

From $0Jakub Krehelskillagent-skillssoftware-engineeringSee options →

Anti-Slop

An opinionated Oxlint ruleset that rejects low-evidence and low-signal TypeScript and JavaScript patterns, meant to be vendored into a repository rather than installed as a package. The bundled install-anti-slop skill lets a coding agent copy the plugin, pin compatible Oxlint dependencies, and later merge upstream updates while keeping local customisations.

From $0Dillon Mulroyskillagent-skillssoftware-engineeringSee options →

Security Audit Skill

A coding-agent skill that runs a six-phase security audit: reconnaissance, coverage-led hunting with isolated sub-agents, candidate validation by fresh verifiers, structured findings, independent record verification, and target-neutral reports. It seeded Cloudflare's vulnerability discovery harness, records each verdict as confirmed, needs_validation, or rejected, and re-uses prior ledgers on repeat runs.

From $0Cloudflareskillagent-skillssoftware-engineeringSee options →

Stop That Shit

A skill plus hook-based guard for Codex, Claude Code, OpenCode, Hermes Agent CLI, and Pi that stops four coding-agent behaviours: scope creep, unrequested hashing and hypothetical hardening, intent violations, and task thrashing. It ships host adapters for each agent, an evidence file, and a case library that shows before-and-after diffs.

From $0Lennneyskillagent-skillssoftware-engineeringSee options →

Recon Skills

A pack of 146 SKILL.md playbooks for authorised external security testing: subdomain, DNS, port, and API discovery; authentication, OAuth, SAML, and MFA testing; web vulnerability validation; cloud, identity, and container pivots; and attack-path reporting. Each skill states one objective with its prerequisites, procedure, pitfalls, verification criteria, and related techniques.

From $0Hiago (uphiago)skillagent-skillssoftware-engineeringSee options →

PR Lens

PR Lens draws a pull request as animated architecture and data-flow diagrams and posts them as a comment inside the pull request; it runs as a GitHub App, GitHub Action, CLI, or a coding-agent skill. The agent-skill package teaches Claude Code, Codex, Cursor, and similar agents to analyse the diff, validate the graph with the CLI, render it, and attach it to the pull request they open.

From $0Coldtea AIskillagent-skillssoftware-engineeringSee options →

Autoprompt Skill

Autoprompt is a coding-agent skill and launcher that routes a task through plan, build, check, and finish agents for Claude Code, Codex, OpenCode, Grok, and other providers. On Terminal-Bench 2.1 the project reports OpenCode solving 73 of 89 tasks with Autoprompt against 60 without, which is 45% fewer failures.

From $0Spielewoyskillagent-skillssoftware-engineeringSee options →

Self-Learning Skills

A meta-skill for Claude Code, Cursor, and any AGENTS.md-driven agent that recognises when a session has produced a hard-won golden path, then persists the procedure and its dead ends where the tool auto-loads it in the next session. It installs with the Skills CLI into 70+ agents and changes only where knowledge is stored for each tool.

From $0Kulaxyzskillagent-skillssoftware-engineeringSee options →

SEE ALL SKILLS ↓

+ 03

Start from intent

Ship something new

Change what exists

Raise the bar

By constraint

+ 04

Stacks & collections

Go Kubernetes Postgres React / TS Python / ML AWS Terraform Rust

squad

Launch a fintech backend

A payments-PCI operator, an SRE and a platform engineer. One composed squad under a single SLA.

3 operators · from $2.1k/daycompose →

squad

0→1 product pod

Full-stack operators plus a reliability lead. The standard shape to take a system from zero to live.

4 operators · from $2.6k/daycompose →

squad

AI capability cell

An ML/inference engineer plus a data-pipeline operator. Stand up retrieval on data that stays fresh.

2 operators · from $1.6k/daycompose →

{ } machine-buyable surface

The same catalog your agents can shop.

Every skill is a typed, priced, deployable record. Your agents and crawlers can read and buy it directly. No scraping, no PDFs.

→JSON-LD Product + Offer on every listing
→REST + MCP search, quote & deploy
→OpenAPI 3.1 + llms.txt for discovery
→Full class index at skills/index.json

GET /catalog/skills/index.json

// each one deployable
{
  "id": "AGENT-0319",
  "rate": "$760/day",
  "deploy": "POST /v1/skills/{id}/deploy"
}

+ 05

Catalog health

10operators

live in the fleet

9days

median ramp to deploy

99.4%

deploys on fixed scope

0rollbacks

on migrations · 90d

+ 06 [SEC-06] COMMAND

Can't find what you need? Brief the platform.

Brief a custom build →$ scrums catalog --search