SKILLEMALL.ai
GitHub ↗ RU Sign in

AB pangolinfo-ai-serp

Search Google and get AI Overviews using Pangolin APIs. Use this skill when the user wants to: search Google with AI answers, get search engine results, perform multi-turn AI search conversations, or capture search screenshots. Requires PANGOLIN_EMAIL + PANGOLIN_PASSWORD env vars (or PANGOLIN_API_KEY).

ClawHub Agent Skills author: liuyu020923 v1.0.2 MIT-0 10 files · 1 script body ≈ 3 258 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 73/100 · Nearly there — weak spots: consistency, running it twice

ProcedureInfrastructuretype 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
A
95/100
safety, quality, tests
Safety 60%
100
Quality 40%
88
Run on models
none yet
Process rating
B
73/100
Nearly there
Running it twice w 4
30
Consistency w 8
40
Tools and files w 18
60
the three weakest of ten parameters · all ten

How to improve

    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 · 0

    ✓ No critical or high findings

    Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 73/100

    • 30Running it twice. 2 mutating operations with no state check
    • 40Consistency. Frontmatter name (pangolinfo-ai-serp) differs from the folder (pangolin-ai-serp)
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 36 steps
    • 100Failures and branches. 11 branches, has a failure section
    • 100Execution cost. Instruction body is 3258 tokens
    • 100Progress reporting. Reports progress
    • low 14 top-level sections: this looks like several domains in one skill

    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)
    • -31 of 2 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 303: enough signal without eating the budget
    • +4Structure: 35 headings
    • +3Step-by-step instructions: 36 items
    • +3Output format is stated explicitly
    • +4Has examples (15 code blocks)
    • +4Reference files are cited in the instructions (2 of 4)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

    External checks

    ClawHub: clean
    This skill is a disclosed Pangolin-powered Google search integration, with expected privacy tradeoffs around sending searches to Pangolin and caching an API key locally.
    LLM: benign (high) · VirusTotal: · 29 May 2026