CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

vercel-firewall

Vercel Firewall expert guidance — automatic DDoS mitigation, the Vercel WAF (custom rules, IP blocking, managed rulesets, rate limiting), Attack Mode, system bypass, bot management, and the `vercel firewall` CLI. Use when configuring platform-level security, responding to attacks, or staging firewall rules.

72

Quality

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

An exemplary CLI-oriented skill body: fully executable commands, explicit staged rollout with user validation checkpoints, and safety guidance for destructive operations. Its only weaknesses are minor repetition between sections and the absence of any bundle-file split for reference-grade detail.

DimensionReasoningScore

Conciseness

The body is dense and fact-packed with non-obvious details ('Staged — requires publish', 'ja3_digest (Enterprise only)', 'Counters are per region — N regions can collectively exceed your configured limit by ~N×') and no padding about concepts Claude already knows. Minor repetition — the staged rollout is restated in the rate-limit section and 'log first' advice appears several times — keeps it just below the leanest anchor.

4 / 5

Actionability

Nearly everything is copy-paste executable: all four 'rules add' modes, AND/OR condition composition with exact JSON, a complete rate-limit flag example, the condition schema with operator and type tables, and 'vc metrics' queries. Specific examples cover the common cases, matching the fully-executable anchor.

5 / 5

Workflow Clarity

The staged rollout is an explicitly numbered four-stage sequence (log everywhere → user reviews dashboard traffic filtered by rule ID → block in preview with an environment condition → block in production) with user-confirmation checkpoints, rollback guidance ('roll back with --action log or rules disable'), and destructive commands explicitly deferred to the user — a clear sequence with validation and error-recovery feedback.

5 / 5

Progressive Disclosure

No bundle files exist, and the single SKILL.md is well-sectioned with clear headers and official documentation links, so navigation is easy. However, reference-grade detail (the operators list, condition types, and full flag tables) is inlined in a 300+ line file where a references/ split would keep the overview lean — good structure with minor organization gaps.

4 / 5

Total

18

/

20

Passed

Description

92%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 that states what the skill covers in concrete, domain-specific terms and gives an explicit 'Use when...' trigger clause. Trigger-term coverage is good but omits a few natural user phrasings, which is the only meaningful gap.

DimensionReasoningScore

Specificity

The description enumerates concrete capabilities — 'automatic DDoS mitigation', 'custom rules, IP blocking, managed rulesets, rate limiting', 'Attack Mode, system bypass, bot management', and the 'vercel firewall' CLI — giving comprehensive coverage of the firewall domain with no real gaps, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

It explicitly answers both questions: the 'what' is the enumerated capability list plus the CLI, and the 'when' is a concrete trigger clause — 'Use when configuring platform-level security, responding to attacks, or staging firewall rules.'

5 / 5

Trigger Term Quality

Strong natural keywords a user would actually say — 'Vercel Firewall', 'Vercel WAF', 'DDoS', 'rate limiting', 'Attack Mode', 'IP blocking' — but a few common variations are missing ('block this IP', 'firewall rules', generic '429'/'challenge page' phrasing), placing it just below the comprehensive-coverage anchor.

4 / 5

Distinctiveness Conflict Risk

'Vercel Firewall' and 'Vercel WAF' form a clear niche with distinct, product-specific triggers; only negligible overlap risk with a hypothetical general-Vercel skill, and the third-person voice is consistent throughout.

5 / 5

Total

19

/

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

Path

plugins/vercel/skills/vercel-firewall/SKILL.md

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.