SKILLEMALL.ai
GitHub ↗ RU Sign in

BC vercel

Vercel API integration with managed OAuth. Manage projects, deployments, domains, teams, and environment variables. Use this skill when users want to interact with Vercel - deploying apps, managing projects, checking deployment status, or configuring domains. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login; default to read and list calls, and confirm every write or new connection with the user.

ClawHub Agent Skills author: byungkyu v1.2.0 MIT-0 2 files body ≈ 5 506 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

IntegrationInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
90
Quality 40%
74
Run on models
none yet
Process rating
C
60/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 6

✓ No critical or high findings

Medium and low: 6
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Grep Glob
  • low Secrets in code secret-high-entropy-token SKILL.md:247
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "team…oKu",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:281
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "prj_…uYG",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:309
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "prj_…uYG",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:376
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "uid": "dpl_…mZJ",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:411
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "dpl_…mZJ",
    quoted

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5506 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 60/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 43 mutating operations with no state check
  • 40Consistency. Frontmatter name (vercel) differs from the folder (vercel-api)
  • 50When it triggers. No condition that starts the skill
  • 70Execution cost. Instruction body is 5506 tokens
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 58 steps
  • 100Failures and branches. 6 branches, has a failure section
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 497: enough signal without eating the budget
  • +4Structure: 60 headings
  • +3Step-by-step instructions: 58 items
  • +4Has examples (56 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: clean
This skill is a disclosed Vercel API helper that uses Maton authentication and includes appropriate confirmation and credential-handling safeguards.
LLM: benign (high) · VirusTotal: · 4 Sept 2026