SKILLEMALL.ai
GitHub ↗ RU Sign in

AC pangolin-serp

Search Google and scrape Amazon using Pangolin APIs. Supports AI Mode search (Google AI Overview with multi-turn dialogue), standard SERP with AI Overview extraction, Amazon product/keyword/category scraping, and screenshot capture. Use when needing to search Google programmatically, get AI overviews, scrape SERP results, perform multi-turn Google AI search, or extract Amazon product data. Requires PANGOLIN_EMAIL and PANGOLIN_PASSWORD env vars (or PANGOLIN_TOKEN).

ClawHub Agent Skills author: Pangolinfo & AgentGo v1.0.1 MIT-0 8 files body ≈ 1 747 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: when it triggers, consistency, progress reporting

ReferenceInfrastructuretype 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
C
63/100
Has gaps
Progress reporting w 2
0
When it triggers w 12
20
Consistency w 8
40
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: 8. 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 63/100

    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (pangolin-serp) differs from the folder (pangolinfo-scrape-legacy)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 9 steps
    • 100Execution cost. Instruction body is 1747 tokens
    • 100Running it twice. No mutating operations

    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 1 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 468: enough signal without eating the budget
    • +4Structure: 24 headings
    • +3Step-by-step instructions: 9 items
    • +3Output format is stated explicitly
    • +4Has examples (17 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)

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

    External checks

    ClawHub: clean
    This is a straightforward Pangolin API helper, with expected credential use and remote search/scrape requests, but users should treat tokens and submitted queries as sensitive.
    LLM: benign (high) · VirusTotal: · 29 May 2026