mrkeyoor.com_
Mon 10 Aug 15:27 UTC
Dev Toolsevaluationupdated 10 Aug 2026

skills

`skills` is a TypeScript command-line manager for reusable instruction packs used by Claude Code, Codex, Cursor, OpenCode, and more than 70 other coding agents. It finds `SKILL.md` files in Git repositories or local folders, installs them into each agent's expected directory, and handles listing, updating, removing, creating, or temporarily using those skills.

Verdict

`skills` is the best default we found for people who genuinely use several coding agents, and its project-scoped workflow is much better than maintaining copied folders by hand. Its open ecosystem is also a supply-chain boundary, not an app store guarantee. Use it for reviewed skills, prefer project scope for team visibility, and treat every update as a code change that deserves a diff.

Setup4/5One npx command, but it requires a very recent Node release
Docs5/5Detailed sources, scopes, commands, agents, auth, and caveats
Community5/5Fast releases and intense issue and pull-request activity
Maturity3/5Capable lifecycle tooling, with active overwrite and path bugs

Who it’s for

  • Developers who switch among Claude Code, Codex, Cursor, OpenCode, and other agents but want one skill collection.
  • Teams that want project-scoped instructions committed beside the code instead of copied into every developer's home directory by hand.
  • Skill authors publishing one repository for agents with different discovery paths.
  • Organizations distributing private skills through existing Git, GitHub CLI, or SSH credentials.
  • Power users who want searchable discovery plus scripted, non-interactive installation and updates.

Who it’s NOT for

  • Environments pinned below Node.js 22.20: the current package metadata requires Node 22.20 or newer.
  • Teams unwilling to inspect third-party instructions before installation: the CLI accepts arbitrary Git hosts, local paths, direct SKILL.md URLs, and archives, while skills can direct agents to use tools and external integrations.
  • Users who keep personal edits inside installed skill folders: an open request documents that update replaces the whole directory and loses local-only files.
  • Anyone who cannot tolerate install-name collisions: an open v1.5.22 report shows skills add replacing an existing same-name skill or symlink without a conflict prompt.
  • Teams expecting identical behavior on every supported agent: the README's compatibility table shows context: fork only on Claude Code and hooks on only a few agents.
  • Operators who must not send private source identifiers: telemetry can include identifiers for non-GitHub remote sources unless DISABLE_TELEMETRY or DO_NOT_TRACK is set.

Setup reality

For a public skill and a current Node installation, setup is as easy as the README claims: one npx skills add owner/repo command, an interactive selection, then symlinks from agent-specific folders to one canonical copy. Private repositories rely on credentials already configured for Git, GitHub CLI, HTTPS helpers, or SSH, which is sensible but still needs testing in each environment. Team adoption requires more policy: choose project versus global scope, decide whether symlinks are acceptable, review source instructions and bundled files, opt out of telemetry where needed, prohibit local edits in managed copies, and inspect updates before rolling them out.

One package manager for a fragmented agent world

Coding-agent skills are mostly folders containing a SKILL.md file, optional scripts and references, and YAML frontmatter describing when the agent should use the instructions. The format is simple. Distribution is not. Claude Code looks in .claude/skills, Codex has its own locations, and dozens of other agents use variations under .agents, application-specific folders, or user configuration directories.

Vercel Labs' skills CLI turns that path matrix into one interface. The README lists support for Claude Code, Codex, Cursor, OpenCode, and more than 70 other agents. Run npx skills add owner/repo, choose skills and target agents, and the tool discovers valid files and writes them where each agent expects them.

The project is a manager, not a bundle of Vercel prompts. It installs from GitHub shorthand, full GitHub or GitLab URLs, arbitrary Git remotes, local directories, direct file URLs, and common archives. The skills.sh directory adds discovery, but a skill does not have to be listed there to work. This openness is both the product's strength and its central risk.

Installation and daily use are well designed

Project scope is the default. Skills land inside the repository's agent directories, where a team can inspect and commit them. Global scope puts them under user directories for reuse across projects. Interactive installation recommends one canonical copy with symlinks into each agent folder, avoiding a pile of independent copies that drift. The --copy option covers environments where links are undesirable or unavailable.

The command set feels like a small package manager. list shows installed skills, find searches by keyword or repository owner, update refreshes all or selected entries, remove cleans up selected agents or scopes, and init creates a valid starter file. Non-interactive flags make a reviewed skill set reproducible in onboarding scripts. use can resolve a skill into a temporary directory and print a generated prompt, or start a supported agent with it, which is useful for trying a narrow workflow without a permanent install.

Private repository handling is unusually thoughtful. The CLI tries normal Git credentials, authenticated GitHub CLI cloning, and SSH rather than extracting a stored GitHub token into its Node process. Explicit GITHUB_TOKEN and GH_TOKEN values are supported for API access. Direct downloads also have default limits for bytes, expanded size, and file count, reducing accidental archive explosions.

There is one prerequisite the README should surface earlier: package metadata requires Node.js 22.20 or newer. That is easy on a current developer laptop and awkward in an older enterprise image. npx saves a separate global installation, but it does not remove the runtime version requirement.

Portable instructions are not identical behavior

Basic markdown skills transfer well because agents can all read procedural instructions. The CLI knows many native directories and can discover nested catalogs, experimental and system folders, plus skill paths declared by Claude plugin manifests. For an author, that is far better than shipping separate installers for every agent.

The compatibility table prevents overpromising. allowed-tools works across many listed agents, but context: fork is shown only for Claude Code. Hooks are supported by Claude Code, Cline, and Kiro CLI in the table, not by most other targets. A skill that depends on these features is not made portable merely because its folder can be copied. Authors should keep the core instructions agent-neutral, label special behavior, and test on every agent they claim to support.

The same warning applies to universal conversions. An open report against v1.5.21 says a universal-agent copy lost required name frontmatter and other custom keys even though the canonical copy stayed intact. Another report says some global installations wrote only to the canonical directory and skipped the agent-specific global path the selected CLI actually reads. With a fast-growing list of targets, path detection and frontmatter preservation are ongoing maintenance work. Verify with skills list and a real agent launch, not just a successful install message.

Treat skills like executable dependencies

A skill can tell an agent how to create pull requests, call external services, run scripts, or choose tools. Installing one changes the instructions given to software that may already have shell, repository, and network access. Read the complete SKILL.md, scripts, and referenced files before use. Prefer a commit you have reviewed, and inspect updates as carefully as dependency upgrades.

This matters because current conflict behavior can be destructive. An August 2026 issue shows v1.5.22 replacing an existing same-name Claude Code skill without prompting, including replacing a user-managed symlink with an upstream directory. A fix pull request is already open, but users on the released version should check target names first. Another open request explains that updates reinstall whole skill directories, so local helper files and edits disappear. Keep customization in your own source repository, never inside a managed installation.

Telemetry is documented and optional. Confirmed-public GitHub repository and skill identifiers may be sent, while other remote source types may include identifiers because their visibility cannot be verified through GitHub. Security-audit requests are limited to confirmed-public GitHub repositories. Set DISABLE_TELEMETRY=1 or DO_NOT_TRACK=1 for confidential environments and do your own review regardless of catalog status.

Health and the recommendation

The project was pushed on August 9, 2026, and v1.5.22 shipped on August 5 after a steady series of July releases. Its GitHub open count of 1,012 includes issues and pull requests, plus many catalog listing and re-audit requests, so it is not a thousand confirmed CLI defects. Recent work fixed private authentication, update host handling, portable lockfile sources, nested discovery, and removal bookkeeping. The pace is excellent, although the volume of new agents and sources keeps exposing edge cases.

Use skills when cross-agent distribution is a recurring problem. For one agent and two local instructions, manually committing a skill folder may be simpler and easier to audit. For a team or a multi-agent workstation, this CLI earns its place, provided you use reviewed sources, avoid modifying installed copies, verify each target path, and make updates visible in code review.

Alternatives

ProjectWhat it isPick it when
SkillKitA portability tool for installing, translating, and sharing skills across many coding agents.pick this instead when format translation between agent ecosystems matters as much as installation.
Skills HubA desktop application for managing and syncing agent skills across coding tools.pick this instead when you prefer a graphical manager over an npx command-line workflow.
NVIDIA SkillSpectorA scanner focused on malicious instructions, prompt injection, and supply-chain risks in agent skills.pick this instead when pre-install security analysis is the main need rather than cross-agent distribution.

What people are saying

  1. [github-trending] vercel-labs/skills
  2. [github-trending] google/skills
  3. [github-trending] mattpocock/skills
  4. [github-trending] addyosmani/agent-skills

Sources

  1. skills repository and README
  2. skills v1.5.22 release
  3. skills package metadata
  4. Same-name skill overwrite report
  5. Preserve-local update request
  6. Universal frontmatter loss report
  7. Global agent directory omission report