CtrlK
BlogDocsLog inGet started
Tessl Logo

add-vercel

Add Vercel deployment capability to NanoClaw agents. Installs the Vercel CLI in agent containers and sets up OneCLI credential injection for api.vercel.com. Use when the user wants agents to deploy web applications to Vercel.

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced workflow with strong validation checkpoints and lean prose. The main weakness is progressive disclosure: the skill is a single monolithic file and references bundle assets that are not shipped alongside it.

Suggestions

Ship the referenced bundle assets under scripts/ and references/ (the container-skills directory and vercel-dockerfile.test.ts) so the inline paths resolve to real files.

Extract the credential-setup detail (token instructions, onecli secrets create invocation, per-agent merge loop) into a references file and keep SKILL.md as a phase-by-phase overview with clearly signaled links.

Confirm the delegation to the vercel-cli container skill is an explicit, clickable reference rather than only mentioned in the closing 'Done' section.

DimensionReasoningScore

Conciseness

The body is lean: it leads with executable bash commands and keeps prose to justified operational notes (e.g. explaining why a structural test guards a non-importable CLI). It does not explain concepts Claude already knows.

3 / 3

Actionability

Nearly every step gives copy-paste-ready, executable bash (rsync, onecli secrets, jq merge loop, grep checks, docker stop); the only manual step — pasting a token — is genuinely unavoidable and clearly bounded.

3 / 3

Workflow Clarity

Six numbered phases with explicit skip/stop gating and verification commands after each install, plus a red/green structural test in Phase 4b that forms a validate-fix-retry feedback loop for the destructive rebuild and batch container-stop operations.

3 / 3

Progressive Disclosure

Sections are well-organized into phases and the full command reference is delegated to the separate vercel-cli container skill, but the body itself is a ~160-line monolith with all setup logic inline, and it references bundle files (container-skills/, vercel-dockerfile.test.ts) that are not present in any bundle directory.

2 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, concrete, and covers both capability and explicit trigger conditions in third person. It is a strong example of the form with no significant weaknesses.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Installs the Vercel CLI in agent containers', 'sets up OneCLI credential injection for api.vercel.com', 'Add Vercel deployment capability' — matching the top anchor for specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('Installs the Vercel CLI... sets up OneCLI credential injection') and when ('Use when the user wants agents to deploy web applications to Vercel'), satisfying the explicit-trigger requirement.

3 / 3

Trigger Term Quality

Natural user-facing terms are present — 'deploy web applications to Vercel', 'Vercel', 'agents to deploy' — the kinds of phrases a user would actually say when needing this skill.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche — Vercel deployment for NanoClaw agents via OneCLI — with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
nanocoai/nanoclaw
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.