SKILLEMALL.ai
GitHub ↗ RU Sign in

BC vercel-insights

Reports a Vercel site's errors, traffic and speed: runtime error logs, failing requests, page views, visitors, top pages, referrers, and Core Web Vitals. Trigger on requests like "what errors did my site have in the last 30 minutes", "why am I getting 500s", "show me the logs", "how is my traffic this week", or "which pages are slowest". Read only.

ClawHub Agent Skills author: Anatoli ILIEV v1.1.1 MIT-0 53 files body ≈ 14 304 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

Reports a Vercel site's errors, traffic and speed: runtime error logs, failing requests, page views, visitors, top pages, referrers, and Core Web Vitals.

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost

ProcedureData and analyticstype 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
85/100
safety, quality, tests
Safety 60%
87
Quality 40%
83
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
30
Running it twice w 4
30
the three weakest of ten parameters · all ten

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 · 13

✓ No critical or high findings

Medium and low: 13
  • low Secrets in code secret-high-entropy-token docs/api-notes.md:792
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "deploymentId": "dpl_…000",
    quoted
  • low Exfiltration net-credential-use docs/openclaw-setup.md:242
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service; the skill's own vendor host)
    curl -sS -H "Authorization: Bearer $VERCEL_TOKEN" https://api.vercel.com/v2/teams \
    known servicevendor-host
  • low Secrets in code secret-high-entropy-token examples/example_outputs.md:41
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    acme-docs       prj_…sJz  data     data
    fixture
  • low Secrets in code secret-high-entropy-token examples/example_outputs.md:62
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    acme-docs       prj_…sJz  data     data
    fixture
  • low Secrets in code secret-high-entropy-token examples/example_outputs.md:79
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    Vercel Web Analytics: prj_…sJz
    fixture
  • low Secrets in code secret-high-entropy-token examples/example_outputs.md:127
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    Vercel Web Analytics: prj_…sJz (top-pages)
    fixture
  • low Secrets in code secret-high-entropy-token examples/example_outputs.md:149
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    Vercel Web Analytics: prj_…sJz (top-routes)
    fixture
  • low Secrets in code secret-high-entropy-token README.md:390
    High-entropy token-like string (may be an id, hash or a credential)
    Vercel Web Analytics: prj_…sJz
  • low Secrets in code secret-high-entropy-token README.md:437
    High-entropy token-like string (may be an id, hash or a credential)
    Vercel Speed Insights: prj_…sJz
  • low Secrets in code secret-high-entropy-token README.md:457
    High-entropy token-like string (may be an id, hash or a credential)
    Vercel Speed Insights: prj_…sJz (slowest-pages, p75)
  • low Secrets in code secret-high-entropy-token README.md:474
    High-entropy token-like string (may be an id, hash or a credential)
    Vercel Speed Insights: prj_…sJz (vitals-by-device, p75)
  • low Secrets in code secret-high-entropy-token README.md:566
    High-entropy token-like string (may be an id, hash or a credential)
    Vercel request logs: prj_…000 (logs, last 30 minutes)
  • low Secrets in code secret-high-entropy-token SKILL.md:533
    High-entropy token-like string (may be an id, hash or a credential)
    Vercel Speed Insights: prj_…sJz

Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 14304 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 59/100

  • 0Result and completion. Does not say what the result is
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 20 mutating operations with no state check
  • 40Execution cost. Instruction body is 14304 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 34 steps, 1 vague phrases
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 19 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable

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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +5Description quotes 5 example trigger phrases
  • +3Description length 350: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 34 items
  • +4Has examples (11 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

External checks

ClawHub: clean
This skill is a disclosed, read-only Vercel observability helper, but users should understand that account-scoped tokens can expose broad analytics, metrics, and log data.
LLM: benign (high) · VirusTotal: · 18 Aug 2026