Item detail
github.com

vercel-labs/skills

RepoRadar surfaced vercel-labs/skills — an agent project — into the AI Coding section, where it sits at Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 9.5 out of 10.

Score8.4
Popularity1.0
Riskconditional
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum8.0
Maturity6.6
Open-source/build8.4
Evidence7.2
Workflow potential9.5
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for developers who use multiple coding agents and want one portable way to ship and reuse skill packages, and for skill maintainers who want a single install surface that is not tied to a single vendor's marketplace.

Who should use it

Developers using multiple coding agents (Claude Code, Codex, Cursor, OpenCode) who want shared skills Skill authors who want to ship one package instead of per-agent forks Agent platform teams evaluating a portable skill install surface Power users who want to try community skills across agents without rewriting install steps

Who should skip it

Pass on vercel-labs/skills if its scope or audience does not match what your team is building right now.

About this signal

vercel-labs/skills is tracked by RepoRadar as an agent project in the AI Coding section. First seen 2026-06-30; the source record was last checked on 2026-06-30. The current verdict is 'try now' with a Gold tier and easy setup difficulty. vercel-labs/skills leads on workflow potential (9.5) and setup ease (8.8); its lowest signal is maturity (6.6), so factor that in before investing setup time. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The vercel-labs/skills record combines a 8.4/10 composite score with separate popularity (1.0), risk (conditional), and setup (easy) signals. See the scoring methodology for the current weights and evidence definitions.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

It rewrites per-agent config files and install paths, so audit the dry-run output before running it on a workstation that already has curated Claude Code or Codex skill installs; Trust in the skill source matters: `skills add owner/repo` runs whatever SKILL.md is in the repo, so prefer skills from publishers you already trust instead of treating it as a free-for-all marketplace.

Evidence links
Closest alternatives / related signals
agent-skills cli claude-code codex cursor opencode mit
Verification record

What RepoRadar actually verified

Tested in a bounded workflow

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-13T10:37:27.963576Z.

passed · cohort-20260712-vercel-skills-local-install-workflow

Tester
RepoRadar automated local verification harness
Started
2026-07-13T10:37:26.477103Z
Completed
2026-07-13T10:37:27.963576Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
1 minute(s)
Evidence scope
Bounded representative workflow
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Created 1 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Created a valid SKILL.md with frontmatter and a unique incident-procedure marker.
  • Used the skills CLI's Codex target and copy mode, then validated the installed skill file inside the disposable project.
  • Executed bounded check: Install a synthetic incident-triage skill into a disposable Codex project with Vercel's skills CLI.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 1.49-second wall time.
Observed results
  • Command exited 0 after 1.49 seconds.
  • The CLI discovered the fixture skill and copied its complete frontmatter and instructions into the Codex-compatible project skill directory.
  • Validated .agents/skills/incident-triage/SKILL.md: 3 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
Observed strengths
  • Agent-specific skill installation is reproducible from a local directory and can avoid symlink behavior through explicit copy mode.
Friction
  • The installed path follows the CLI's cross-agent .agents convention rather than a user-global Codex skill directory.
Limitations
  • The local copy workflow validates discovery, frontmatter handling, and agent-target installation, not remote skill registries, updates, trust review, or execution by an agent.
  • This credential-free disposable workflow does not establish production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The local skills CLI and fixture required no registry account, paid marketplace, or agent/model invocation.

Privacy assessment: The synthetic SKILL.md stayed within the disposable project; only npm package resolution contacted an external registry.

Open retained test log →

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

35 dated snapshots retained from 2026-06-30 through 2026-08-13; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score8.4 current · +0.0 net
Repository momentum9.6 current · +1.6 net
GitHub stars (observed)28,813 current · +2,747 net
GitHub stars28,813 exact observation
Versionv1.5.22
Last release2026-08-05T15:25:32Z
Maintenanceactive
Current riskconditional
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineNo structured integrations recorded

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-138.49.628,813conditionaltry nowactive
2026-08-128.49.628,748conditionaltry nowactive
2026-08-118.49.628,632conditionaltry nowactive
2026-08-108.410.028,538conditionaltry nowactive
2026-08-098.49.628,411conditionaltry nowactive
2026-08-088.49.628,315conditionaltry nowactive
2026-08-078.49.627,886conditionaltry nowactive
2026-08-068.48.0Not recordedconditionaltry nownot recorded
2026-08-058.48.0Not recordedconditionaltry nownot recorded
2026-08-048.49.627,886conditionaltry nowactive
2026-08-038.49.627,886conditionaltry nowactive
2026-08-028.49.627,816conditionaltry nowactive

Why the record changed

stars changed

Stars changed: 28748 → 28813.

stars changed

Stars changed: 28632 → 28748.

stars changed

Stars changed: 28538 → 28632.

stars changed

Stars changed: 28411 → 28538.

stars changed

Stars changed: 28315 → 28411.

version changed

Version changed: v1.5.21 → v1.5.22.

stars changed

Stars changed: 27886 → 28315.

stars changed

Stars changed: 27816 → 27886.

stars changed

Stars changed: 27735 → 27816.

stars changed

Source-observed stars changed: 27718 → 27735. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Source-observed stars changed: 27717 → 27718. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Stars changed: 27415 → 27509.