CtrlK
BlogDocsLog inGet started
Tessl Logo

bootstrap

Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations). Use when setting up or repairing a repository so linking, environment provisioning, env pulls, and first-run db/dev commands happen in the correct safe order.

67

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is bootstrap in vercel/vercel-plugin

SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

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

A well-structured, highly executable orchestrator skill with strong sequencing, explicit validation checkpoints, and error-recovery loops. The main improvements are tightening the tangential UI-baseline section, making the vague Geist font fix concrete, and slimming the next-forge section now that a dedicated skill reference exists.

Suggestions

Make the Geist font fix actionable: state the specific change (e.g., importing Geist from next/font and setting the CSS variables) or move it to a reference, since 'Apply the Geist font fix' is not executable as written.

Trim the 'UI Baseline for Next.js + shadcn Projects' section or move it to a reference file — opinionated dark-mode and shadcn component-list guidance is tangential to the linking/env/db bootstrap mission and costs tokens on every invocation.

Condense the 'next-forge Projects' section to detection criteria plus the '=> skill: next-forge' pointer, removing detail duplicated from the referenced skill.

DimensionReasoningScore

Conciseness

The body is efficient — rules and commands with no explanations of concepts Claude already knows — but the opening line duplicates Rules bullet 1 and the shadcn/dark-mode UI baseline section is tangential to bootstrapping, matching anchor 4 (minor instances that could be trimmed) rather than anchor 5.

4 / 5

Actionability

Mostly executable guidance: copy-paste vercel commands, a runnable key-diff script, and a non-printing AUTH_SECRET generator cover the common cases. Two minor gaps keep it below anchor 5: 'Apply the Geist font fix in layout.tsx and globals.css' specifies no fix, and the Neon CLI fallback path gives no commands.

4 / 5

Workflow Clarity

Matches anchor 5: strict ordering ('Execute bootstrap in strict order'), an explicit env-verification checkpoint ('Proceed only when missing key list is empty'), a verification checklist, and feedback loops for error recovery ('If DB commands fail, fix... and re-run only the failed db step'; 'If verification fails, stop and report exact failing step plus remediation') — validation is present for the risky database operations.

5 / 5

Progressive Disclosure

Good structure: a single coherent workflow kept inline with well-organized sections and one clearly signaled, one-level-deep pointer ('=> skill: next-forge — Full next-forge monorepo guide'). It falls short of anchor 5 because the 9-line next-forge section partially duplicates detail the pointer already defers to, and that pointer is the only external reference.

4 / 5

Total

17

/

20

Passed

Description

83%Weight 40%Scale 1-5

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

A strong description with an explicit 'Use when' trigger clause and a specific, well-scoped Vercel niche. Both 'what' and 'when' are answered concretely; only minor gains are available from broader synonym coverage and a fuller enumeration of capabilities.

DimensionReasoningScore

Specificity

Lists several concrete actions ('linking, environment provisioning, env pulls, and first-run db/dev commands') within a clearly named domain (Vercel-linked resource bootstrapping), matching the score-4 anchor for several specific actions with minor coverage gaps; it is not a comprehensive action list like the score-5 anchor.

4 / 5

Completeness

Clearly answers both what ('Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations)') and when ('Use when setting up or repairing a repository...') with concrete trigger activities, exactly matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Includes natural user phrasing ('setting up or repairing a repository', 'linking', 'env pulls', 'db/dev commands') plus Vercel-specific vocabulary, giving good keyword coverage; a few common synonyms (e.g., 'initialize', 'onboard', '.env') are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The Vercel-linked-resources niche and Vercel CLI vocabulary make it mostly distinct from generic setup skills; minor overlap risk remains because 'setting up or repairing a repository' is broad wording, so it sits at anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
openai/plugins
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.