How we
review.

What we look for

• Engineering work. The skill changes how an agent plans, builds, tests, debugs, reviews, secures or ships software.
• A clear trigger. Its description says when to use it, so it fires on the right tasks and stays quiet on the rest.
• A scoped job. It does one thing well and is honest about what it touches.
• A usable licence. Published under a licence that lets you use it. Skills without a licence file wait until they have one.
• Installable. It installs with the open Skills CLI from a public repository.

The checks we run

Every listed SKILL.md is fetched and checked each day for valid frontmatter and for patterns drawn from published research on malicious skills:

• Remote code piped into a shell, and obfuscated payloads.
• Destructive commands and unnecessary privilege, such as rm -rf on a root path or sudo.
• Force pushes and skipped git hooks.
• Flags that bypass an agent's safety prompts.
• Reading or printing secrets, and hardcoded credentials.
• Hidden instructions aimed at the agent.

A match is not a verdict. A person reads it: a defensive mention, such as a skill that lists the commands it blocks, is cleared with the reason shown on the page. A new, unread match pauses the listing until it is read.

What the labels mean

• Edits code

  Changes files in your project.

• Writes docs

  Creates or updates documents such as specs, plans or ADRs.

• Runs commands

  Runs shell commands such as tests, builds or installs.

• Uses git

  Reads history or makes commits, branches or worktrees.

• Subagents

  Starts other agents to work in parallel.

• Browser

  Drives a real browser.

• Needs MCP

  Requires an MCP server to be configured.

• Network

  Reaches external services or the web.

Labels come from reading the skill, not from running it. A skill with no labels is guidance only.

Reviewed, and read in full

Every listing is reviewed: licence confirmed, SKILL.md scanned, access labelled, and a Fieldbook note written from its instructions. Read in full is a stronger mark: a person has read the skill and every file it tells the agent to load, end to end, and the date is shown. Submissions are read in full before they are listed.

Where the numbers come from

Install counts are the public counts from skills.sh (opens in a new tab), collected from the open-source Skills CLI. Fieldbook takes a snapshot every day; "today" is the change since the previous snapshot. Some repositories install as a bundle, which counts every skill in the bundle. Stars and update dates come from GitHub. Fieldbook is independent of skills.sh and Vercel.

What reviewed does not mean

A review is not a security audit or a guarantee. We read skills but do not run every one, and a skill can change after it is reviewed; the daily checks exist to catch that. Always read what you install. If you find a problem with a listed skill, open an issue (opens in a new tab).