# Agent Skills — AI Coding Tool Review & Pricing

> Agent Skills provides a library of structured, production-grade engineering workflows and quality gates for AI coding agents. It prevents agents from skipping critical steps like specs, testing, and reviews by embedding rigorous verification, anti-rationalization tables, and senior-engineer best practices into the development loop.

Source: https://ai.dosa.dev/tools/agent-skills · Updated Nov 1, 2026 · Category: Developer Productivity & Workflow · Published by dosa.dev

## At a glance

- **Tool**: Agent Skills
- **Company**: Addy Osmani
- **Category**: [Developer Productivity & Workflow](https://ai.dosa.dev/category/productivity)
- **Pricing model**: Free
- **Official website**: https://skills.addy.ie/

## Key features

- 25 structured engineering skills covering the full SDLC
- Slash commands for standardized lifecycle stages like /spec, /build, and /ship
- Anti-rationalization mechanisms that rebut common agent shortcuts
- Verification gates requiring evidence (tests, build output) rather than assertions
- Parallel review personas for automated quality gate checks during shipping

## Pricing

**Model**: Free

Agent Skills is free to use; it is an open-source project that utilizes token consumption within your AI agent, as using the full suite of skills increases session length and context usage.

## Who it is for

- **Best for**: Developers and teams needing to enforce consistent, production-quality standards and discipline across AI-driven coding tasks.
- **Not ideal for**: Projects where maximum speed or token cost minimization is the only goal, as these workflows prioritize rigorous verification and evidence-based progress over the shortest path.

## Verdict

Agent Skills is an essential tool for turning AI agents into reliable engineering partners, successfully replacing guesswork and shortcuts with a repeatable, evidence-driven development process.

## Recent updates

Release 0.6.15, featuring updated plugin manifests and refined security and accessibility quality gates, was released on October 31, 2026.

## Frequently asked questions

### Is Agent Skills free?

Yes - Agent Skills is Free. Agent Skills is free to use; it is an open-source project that utilizes token consumption within your AI agent, as using the full suite of skills increases session length and context usage.

### Is Agent Skills open source?

Agent Skills is not listed as open source on ai.dosa.dev - it is Free.

### Who is Agent Skills best for?

Developers and teams needing to enforce consistent, production-quality standards and discipline across AI-driven coding tasks.

### Who is Agent Skills not ideal for?

Projects where maximum speed or token cost minimization is the only goal, as these workflows prioritize rigorous verification and evidence-based progress over the shortest path.

### What are the best Agent Skills alternatives?

The closest Agent Skills alternatives on ai.dosa.dev are Pieces for Developers, agenttrace, Vibe Kanban - all listed under Developer Productivity & Workflow.

### Who makes Agent Skills?

Agent Skills is developed by Addy Osmani. It is listed in the Developer Productivity & Workflow category on ai.dosa.dev.

## Top alternatives

- [Pieces for Developers](https://ai.dosa.dev/tools/pieces-for-developers) (Paid) — Developers who work across multiple tools, IDEs, and environments and need to maintain a persistent, searchable history of code snippets, research, and workflow context.
- [agenttrace](https://ai.dosa.dev/tools/agenttrace) (Open Source) — Developers and teams needing to monitor and debug the efficiency, cost, and health of AI coding agents across multiple workflows.
- [Vibe Kanban](https://ai.dosa.dev/tools/vibe-kanban) (Open Source) — Software engineers who use multiple AI coding agents and need a structured environment to manage, plan, and review their output in parallel.
- [ai-memory](https://ai.dosa.dev/tools/ai-memory) (Open Source) — Developers or teams using multiple AI coding agents who need consistent context and project history persistence across different tools, machines, and sessions.
- [smolvm](https://ai.dosa.dev/tools/smolvm) (Open Source) — Running isolated coding agent sandboxes, untrusted code, and persistent local development environments that require a real Linux kernel boundary.
- [coop](https://ai.dosa.dev/tools/coop) (Open Source) — Running autonomous AI coding agents that require broad system access while maintaining a strong security boundary for the host machine.
- Full alternatives guide: https://ai.dosa.dev/tools/agent-skills/alternatives