Serpapi Core Workflow A

What it does

When your agent uses it

• Implementing search
• Evidence collection
• With build a SerpAPI Google workflow

Example prompts

• “build a SerpAPI Google workflow”
• “/serpapi-core-workflow-a”

Requirements

• Python 3
• A credential in SERPAPI_KEY
• Compatibility (from SKILL.md): Designed for Claude Code; live searches and multi-page retrieval consume account allowance unless a matching server cache is served
• Pre-approved tools (allowed-tools): Read, Glob, Grep, WebFetch, Write, Edit

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Convert the business question into a minimal query and document permitted use, location, language, device, safe-search setting, freshness…
2. 2Validate parameters against the current Google Search API rather than copying options from another engine.
3. 3Estimate the maximum searches, check the account budget, and present the live execution boundary.
4. 4Execute the first page and require a terminal Success or Error status before parsing sections.
5. 5Normalize each required section independently and retain provenance fields such as position, source link, and search ID.
6. 6Follow serpapi_pagination.next or a documented start offset only while results continue and the page budget remains.
7. 7Reconcile counts, deduplicate stable links, test empty and missing-section fixtures, and store a redacted receipt.

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Glob
  • Grep
  • WebFetch
  • Write
  • Edit

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • serpapi.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • SERPAPI_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code; live searches and multi-page retrieval consume account allowance unless a matching server cache is served

  From compatibility in the SKILL.md frontmatter.

Context cost

Serpapi Core Workflow A loads about 1.1k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 381 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~66

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 381 words, ~1,063 tokens.

name

serpapi-core-workflow-a

description

Build a reproducible Google Search workflow that validates parameters, optional result sections, and bounded pagination. Use when implementing search, SEO monitoring, or evidence collection. Trigger with "build a SerpAPI Google workflow".

allowed-tools

Read, Glob, Grep, WebFetch, Write, Edit

compatibility

Designed for Claude Code; live searches and multi-page retrieval consume account allowance unless a matching server cache is served

argument-hint

[query] [location] [page-budget]

version

1.6.0

author

Jeremy Longshore <jeremy@intentsolutions.io>

license

MIT

tags

saas, serpapi, google-search, pagination, seo

model

inherit

effort

high

params = {
    "engine": "google",
    "q": "site:example.com release notes",
    "location": "Austin, Texas, United States",
    "hl": "en",
    "gl": "us",
    "safe": "active",
}
result = client.search(params)
if result["search_metadata"]["status"] != "Success":
    raise RuntimeError(result.get("error", "search did not complete"))
records = [
    {"position": row.get("position"), "title": row.get("title"), "link": row.get("link")}
    for row in result.get("organic_results", [])
]

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/.curated/serpapi-core-workflow-a of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287