The Skill Library for AI Agents That Do Real Work
Skills, harnesses, and automations for the AI tools you already use, ready to drop in.
Plain SKILL.md files your agent reads directly, harnesses that run in minutes, and automations that chain them together. No subscriptions, no lock-in, one clear place to start.
AI Ultimate Skill Collection · 3,029 skills
Every skill your agent needs, sorted into 12 packs
Coding, research, writing, marketing, operations, data, design and more. Each skill is a plain SKILL.md file your agent reads directly, deduplicated and license-audited, so you install once and stop hunting.
- 12 category packs, one download sorted so you can find the skill you need
- Deduplicated across sources one version of each skill, not twelve
- Manifest, attributions and license audit know what you can use commercially
- Works with the agents you already run Claude Code, Codex, Cursor and any SKILL.md reader
- Lifetime access, instant delivery no subscription
Agent Harness Collection · about 40 harnesses
Agents that are running within minutes
About 40 curated agent harnesses across 6 categories, including 16 that run within minutes of download. Each one is a working setup, not a template, with the skills it needs already wired in.
- Six categories of harness research, coding, content, ops, data, support
- 16 run in minutes clone, configure, go
- Skills pre-wired built on the Skill Collection packs
- Documented setup per harness what it does, what it needs, what it costs to run
Agent Automation Collection · written in-house
Skills chained into jobs that finish
Automations written in-house rather than collected, built to chain skills together for the jobs that take more than one step: scheduling, hand-offs, unattended runs, and the checks that catch a bad run before it ships.
- Multi-step jobs, end to end not single prompts
- Scheduling and unattended runs with the guardrails included
- Built on the same skill packs so the pieces fit
- Desktop Agent Command Center available browse, search and launch what you own
Every product is educational and practical material about AI tools. Results vary with your tools, your skills, and the time you put in; nobody here promises you an outcome.
Resources
Know the tools before you pick one
Short profiles of the open-source agent repositories people actually run: what each one does, how it is used, and what to check before you adopt it.
What an AI Agent Skill Is, and Why the Same Request Comes Back Better
A skill is the written method you would hand a sharp new colleague. What one holds, how an agent picks it up, and why the same request comes back better with one attached.
How to Use Skills in Claude Code: Add One, Name It, Check It Ran
A plain guide to skills in Claude Code: where a skill goes, how to write the line that lets Claude find it, how to call it by name, and how to tell it was followed.
Prompts vs Skills: Why Rewriting the Request a Third Time Doesn't Work
A prompt asks for the work. A skill carries the steps, checks and traps behind it. Why rewording the same request rarely fixes a generic draft, and what to move out of the prompt instead.
Six Skills to Try First if You Use an Agent for Client Work
Six everyday client jobs, from the proposal to the Friday update: where an agent usually goes wrong on each, what a written method changes, and what to check before it goes out.
Make Your Agent Check Its Sources Before You Do
AI agents can hand back references that look right and don't exist. How to give yours a research method: three sources per claim, every reference checked, and a record of where each claim came from.
Turn a Weekly Job Into an Automation Your Agent Runs While You're Away
A weekly job your agent can finish on its own: one skill per step, a check between steps that stops the run when something is off, and a finished draft for you to review.
What an Agent Harness Is, and When to Start From a Ready-Made One
A harness is everything wired up around the model so it can do real work. What one holds, why it changes results, and when starting from one that already runs beats building your own.
One Folder, One Standard: Giving Your Whole Team's Agents the Same Methods
When everyone on a team keeps private prompts, the work comes back five different ways. How to keep one shared set of methods, who should own them, and how changes reach every agent.
Aider: pair programming in the terminal
An open-source terminal tool that edits your code, runs tests, and commits to git, working with Claude, GPT and local models.
How it works
Download once. Point your agent at it. Get to work.
Pick your starting point
Start with the Skill Collection for $7. Add harnesses and automations when your agent needs to run whole jobs.
Drop the files into your agent
Every skill is a plain SKILL.md file. Claude Code, Codex, Cursor and any agent that reads skills picks them up as they are.
Keep it for good
Lifetime access, delivered instantly, no subscription. Come back to your dashboard whenever you need another pack.
Any agent that reads SKILL.md files: Claude Code, Codex, Cursor, and most open agent frameworks. The files are plain text and tool-agnostic, so nothing is locked to one vendor.
The Skill Collection is curated and deduplicated from public sources, with a manifest, attributions file and license audit so you know what you can use commercially. The Automation Collection is written in-house.
The Skill Collection is $7, one time, with lifetime access and instant download. If it is not useful, one email to support within 30 days gets your money back. No questions.