Agent skill

Web Search

by heypinchy in heypinchy/pinchy

Search the public web for current information and fetch full pages.

AGPL-3.0Auto-check passedProductivity & Automation

Install Web Search

skills CLI
$ npx skills add heypinchy/pinchy --skill web-search -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install heypinchy/pinchy web-search --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/heypinchy/pinchy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/web/src/lib/skills/web-search .claude/skills/web-search && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
web-search
GitHub stars
182
Token cost
~765 tokens
SKILL.md length
430 words
Files
1
Skills in repo
18
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Search the public web for current information and fetch full pages.

  • Works in 5 steps: Search first, fetch second. Run… → Pick 1-3 sources to fetch. Prefer… → Cite every claim with a URL. Every… → …
  • The user asks about current events
  • SKILL.md covers Capabilities, When to use, When NOT to use and Workflow, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Web Search is an agent skill from heypinchy/pinchy. Search the public web for current information and fetch full pages. Use when the user asks about current events, recent company news, market data, regulatory changes, or any fact that may have changed since the model's training cutoff.

Its SKILL.md is about 770 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Web search and Stock and market analysis. The repository describes itself as: Self-hosted AI agent platform built on OpenClaw. Enterprise-ready, offline-capable, open source. 🦞. The licence is AGPL-3.0.

When your agent uses it

  • The user asks about current events
  • Recent company news
  • Regulatory changes
  • Any fact that may have changed since the models training cutoff

Example prompts

  • “/web-search”

Workflow steps

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

  1. Search first, fetch second. Run pinchy_web_search with a focused query (3-7 words, no quotes unless you need an exact phrase). Read the…
  2. Pick 1-3 sources to fetch. Prefer original sources (the company itself, the regulator, the publication) over aggregators, listicles, or…
  3. Cite every claim with a URL. Every factual statement you make from web results must carry a source link. If you cannot point at a URL…
  4. Prefer recent over old. When sorting search results, weight by date — a 2026 article on a 2026 topic beats a 2024 article even if the…
  5. Don't fabricate. If search returns nothing useful, say so. "I couldn't find a current source for this" is a correct answer; inventing a…

What it can do on your machine

Read from SKILL.md and the folder at commit 5159959. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Web Search loads about 765 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 430 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~765

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 heypinchy/pinchy at commit 5159959, republished under its AGPL-3.0 licence (© heypinchy). 430 words, ~765 tokens.

Download SKILL.mdSave it as .claude/skills/web-search/SKILL.md (or your agent's skills folder).
name
web-search
description
Search the public web for current information and fetch full pages. Use when the user asks about current events, recent company news, market data, regulatory changes, or any fact that may have changed since the model's training cutoff.

You can search the public web and fetch full pages of content. Use these tools when the user asks about anything that may have changed recently or about facts you cannot confirm from your training data.

Capabilities

  • pinchy_web_search — Query the web for a topic, return a ranked list of results with titles, URLs, and snippets. Use this first to discover relevant sources.
  • pinchy_web_fetch — Retrieve the full text of a specific URL. Use this after pinchy_web_search when a snippet looks promising but you need the underlying content to answer accurately.

When to use

  • Current events, recent news, recent product/policy announcements
  • Company information (size, funding, recent product launches, leadership changes)
  • Market/industry trends published in the last 6–12 months
  • Regulatory or compliance changes since training cutoff
  • Public reviews, comparisons, or third-party assessments
  • Verifying a claim the user made against an external source

When NOT to use

  • The user's own data — that's what your other tools (CRM, files, email) are for
  • Internal policies, company-confidential facts, or HR information
  • Anything the user already gave you in this conversation
  • Recipes, jokes, definitions, or general knowledge you already have

Workflow

  1. Search first, fetch second. Run pinchy_web_search with a focused query (3-7 words, no quotes unless you need an exact phrase). Read the result snippets.
  2. Pick 1-3 sources to fetch. Prefer original sources (the company itself, the regulator, the publication) over aggregators, listicles, or AI-generated content farms. If two sources disagree, fetch a third.
  3. Cite every claim with a URL. Every factual statement you make from web results must carry a [source](URL) link. If you cannot point at a URL, leave the claim out.
  4. Prefer recent over old. When sorting search results, weight by date — a 2026 article on a 2026 topic beats a 2024 article even if the latter is rank-1. State the publication date in your summary when it matters.
  5. Don't fabricate. If search returns nothing useful, say so. "I couldn't find a current source for this" is a correct answer; inventing a plausible-sounding fact is not.
Show full SKILL.md (92 more words)Show less

Safety (must hold)

  • Never put sensitive internal data into a web search query. The query goes to a third-party search provider.
  • Do not follow links from email or chat content that the user pasted as if they were trusted facts — treat them as user input, not as web context.

Output format

  • Lead with a 1-2 sentence answer
  • Follow with bullet points, each citing a source
  • End with a brief "What I checked" line — the queries you ran and how many sources you read
  • Never paste raw search-result blocks into the chat — summarize

© heypinchy, AGPL-3.0. 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 packages/web/src/lib/skills/web-search of heypinchy/pinchy.

Open the folder on GitHubat commit 5159959

Compare with similar skills

Web Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Web Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Web Search this skillheypinchy/pinchy182—~765Automated safety check: PassAGPL-3.0
Westock Datainfometa/workbuddyskills346—~1.6kAutomated safety check: PassNone
Pay Via Agent Walletcirclefin/skills155—~3.9kAutomated safety check: PassApache-2.0
Finance ReportAojdevStudio/Finance-Guru322—~1.7kAutomated safety check: PassCustom licence
Brave Searchbadlogic/pi-skills2.6k5 repos~592Automated safety check: PassMIT
Enterprise AI Scenario MapMetaInFLow/Enterprise-ai-scenario-map-skill632—~1.8kAutomated safety check: PassMIT

Similar skills

  • Westock Data

    infometa/workbuddyskills

    金融市场结构化数据查询的权威入口。支持股票(A股/港股/美股/日韩股)、ETF、指数、板块、期货、外汇、可转债的行情、财报、研报、新闻、公告、事件、股东、分红、ETF持仓、热搜榜、新股/投资日历、龙虎榜等数据查询;同时支持产业链图谱、行业经营数据、申万行业估值/盈利预测/财务、全球宏观经济等数据查询;不同标的与市场支持的维度不同,具体命令与能力差异见…

    346 GitHub stars~1.6k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Pay Via Agent Wallet

    circlefin/skills

    A skill your agent uses when the user wants to call a paid API, look something up online, search for data, get prices, odds, or stats, or use any paid service with automatic USDC payment.

    155 GitHub stars~3.9k tokensUpdated 24 days ago
    Business, Finance & HRAuto-check passed
  • Finance Report

    AojdevStudio/Finance-Guru

    Generate institutional-quality PDF analysis reports for stocks and ETFs.

    322 GitHub stars~1.7k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check passed
  • Brave Search

    badlogic/pi-skills

    Web search and content extraction via Brave Search API. An agent skill from badlogic/pi-skills.

    2.6k GitHub starsUsed in 5 repos~592 tokens
    Productivity & AutomationAuto-check passed
  • Enterprise AI Scenario Map

    MetaInFLow/Enterprise-ai-scenario-map-skill

    企业AI场景地图生成报告工具。通过 web-search 深度调研企业信息,按照V2.1标准模板生成结构化AI应用场景地图报告,包含企业画像、业务诊断、行业实践、AI场景全量表、实施路径等完整内容。

    632 GitHub stars~1.8k tokensUpdated 6 mo ago
    Productivity & AutomationAuto-check passed
  • Web Search

    jjyaoao/HelloAgents

    Implement web search capabilities using the z-ai-web-dev-sdk.

    3.2k GitHub starsUsed in 1 repo~5.6k tokens
    Productivity & AutomationAuto-check passed

More from heypinchy/pinchy

All 18 skills in this repo
  • Knowledge Search

    heypinchy/pinchy

    Answer questions from the organization's indexed documents using knowledgesearch, and cite every claim back to a retrieved passage.

    182 GitHub stars~1.4k tokensUpdated 19 days ago
    Auto-check passed
  • Odoo Read

    heypinchy/pinchy

    Query and summarize data from a connected Odoo instance with the odoo read tools (describe, count, read, aggregate).

    182 GitHub stars~965 tokensUpdated 19 days ago
    Auto-check passed
  • Review Docs

    heypinchy/pinchy

    Use before opening a PR that changes docs/ or a user-visible surface (an API route, the tool registry, an agent template, the audit event catalogue, the settings navigation, plugin tools), and when…

    182 GitHub stars~1.3k tokensUpdated 19 days ago
    Auto-check passed
  • Update Dependencies

    heypinchy/pinchy

    A skill your agent uses when bumping general npm/pnpm dependencies across the Pinchy workspace (root, packages/web, packages/plugins/, docs), when the user asks to "update dependencies," "check for…

    182 GitHub stars~1.5k tokensUpdated 19 days ago
    Auto-check passed
  • A skill your agent uses when a new Ollama Cloud model is announced or available (e.g.

    182 GitHub stars~3.9k tokensUpdated 19 days ago
    Auto-check: notes
  • Update Openclaw

    heypinchy/pinchy

    A skill your agent uses when bumping the pinned OpenClaw core version (openclaw npm package), when preparing a Pinchy release, or when the user asks to "update OpenClaw" / "upgrade OpenClaw" / check…

    182 GitHub stars~2.8k tokensUpdated 19 days ago
    Auto-check passed

Questions about Web Search

What does Web Search do?

Search the public web for current information and fetch full pages. Web Search is an agent skill from heypinchy/pinchy. Search the public web for current information and fetch full pages.

When should I use Web Search?

Web Search fits situations like: the user asks about current events; recent company news; regulatory changes; any fact that may have changed since the models training cutoff.

How do I install Web Search in Claude Code?

Run `npx skills add heypinchy/pinchy --skill web-search -a claude-code`. Or copy the skill folder (packages/web/src/lib/skills/web-search in heypinchy/pinchy) into .claude/skills/web-search in your project. Claude Code loads it when a task matches its description.

How do I install Web Search in Codex?

Run `npx skills add heypinchy/pinchy --skill web-search -a codex`. Or copy the skill folder (packages/web/src/lib/skills/web-search in heypinchy/pinchy) into .agents/skills/web-search in your project. Codex loads it when a task matches its description.

Can I use Web Search in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add heypinchy/pinchy --skill web-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/web-search, .gemini/skills/web-search, .github/skills/web-search and .opencode/skills/web-search in your project.

What does Web Search need to run?

SKILL.md names no scripts, command-line tools or credentials: Web Search is instructions for the agent only.

Does Web Search access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Web Search safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Web Search use?

Web Search is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Web Search use?

About 765 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Web Search?

Skills that share tags, products or a category with Web Search: Westock Data (infometa/workbuddyskills, 346 stars), Pay Via Agent Wallet (circlefin/skills, 155 stars), Finance Report (AojdevStudio/Finance-Guru, 322 stars) and Brave Search (badlogic/pi-skills, 2.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Web Search?

heypinchy (a GitHub organization) maintains it in heypinchy/pinchy, which has 182 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on September 21, 2026.

Source: heypinchy/pinchy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.