Brave Search
badlogic/pi-skills
Web search and content extraction via Brave Search API. An agent skill from badlogic/pi-skills.
Web search and page fetch through the TinyFish CLI. An agent skill from ntorga/agent-starter-kit.
Install Web Search
$ npx skills add ntorga/agent-starter-kit --skill web-search -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ntorga/agent-starter-kit web-search --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/web-search .claude/skills/web-search && rm -rf skills-srcUse ~/.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/
Install the "web-search" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/web-search into .claude/skills/web-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-search", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ntorga/agent-starter-kit/tree/main/skills/web-searchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ntorga/agent-starter-kit --skill web-search -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ntorga/agent-starter-kit web-search --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/web-search .agents/skills/web-search && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "web-search" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/web-search into .agents/skills/web-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-search", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ntorga/agent-starter-kit --skill web-search -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ntorga/agent-starter-kit web-search --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/web-search .cursor/skills/web-search && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "web-search" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/web-search into .cursor/skills/web-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-search", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ntorga/agent-starter-kit.git --path skills/web-search--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ntorga/agent-starter-kit --skill web-search -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ntorga/agent-starter-kit web-search --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/web-search .gemini/skills/web-search && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "web-search" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/web-search into .gemini/skills/web-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-search", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ntorga/agent-starter-kit web-searchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ntorga/agent-starter-kit --skill web-search -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/web-search .github/skills/web-search && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "web-search" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/web-search into .github/skills/web-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-search", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ntorga/agent-starter-kit --skill web-search -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ntorga/agent-starter-kit web-search --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/web-search .opencode/skills/web-search && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "web-search" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/web-search into .opencode/skills/web-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-search", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
web-search- GitHub stars
- 146
- Token cost
- ~945 tokens
- SKILL.md length
- 528 words
- Files
- 1
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
Web search and page fetch through the TinyFish CLI. An agent skill from ntorga/agent-starter-kit.
- Works in 2 steps: Check for the CLI. Run command -v… → Check authentication. Run tinyfish auth…
- Tasks that involve Web search
- SKILL.md covers Purpose, Procedure and Guardrails
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Web Search is an agent skill from ntorga/agent-starter-kit. Web search and page fetch through the TinyFish CLI.
Its SKILL.md is about 950 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. The repository describes itself as: The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) . The licence is MIT.
When your agent uses it
- Tasks that involve Web search
Example prompts
- “/web-search”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- Check for the CLI. Run command -v tinyfish. If it is missing, stop and tell the user
- Check authentication. Run tinyfish auth status. If it reports no valid key, tell the user to run tinyfish auth login themselves and stop…
What it can do on your machine
Read from SKILL.md and the folder at commit 851e942. 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 (its code samples are bash).
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):
docs.tinyfish.ai
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 945 tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 528 words of instructions outside code blocks.
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 ntorga/agent-starter-kit at commit 851e942, republished under its MIT licence (© ntorga). 528 words, ~945 tokens.
Download SKILL.mdSave it as
.claude/skills/web-search/SKILL.md (or your agent's skills folder).- name
- web-search
- description
- Web search and page fetch through the TinyFish CLI.
- usedBy
- all
- relatedTo
- tinyfish
- version
- 0.1.0
- lastUpdated
- 2026-09-12
Purpose
Answers about current facts, public tools, and external systems need web grounding. Search finds pages. Fetch reads them. Search runs through the TinyFish CLI. Page fetch tries the host's native web fetch tool first and falls back to the TinyFish CLI when the native tool is blocked. This skill defines when to use each surface, the exact commands, and how to read the output. Full flag reference: https://docs.tinyfish.ai/cli/commands
Procedure
Verify the tool is installed
Check for the CLI. Run
command -v tinyfish. If it is missing, stop and tell the user:- The TinyFish CLI is required for web search and fetch.
- Install it by following https://docs.tinyfish.ai/cli/commands.
- It is free, but it requires an API key — the user creates one and completes login with
tinyfish auth loginthemselves. Do not install the tool or runtinyfish auth loginon your own. Once the user confirms setup, continue.
Check authentication. Run
tinyfish auth status. If it reports no valid key, tell the user to runtinyfish auth loginthemselves and stop. Do not runtinyfish auth loginortinyfish auth seton your own.
Choose the surface
- Answer from local context first. Use project files and the conversation when they hold the answer. Skip the web when the question is about this codebase.
- Search when the right page is unknown. Use search for "what is", "how does", and "compare" questions, and for anything time-sensitive: versions, releases, prices, news.
- Fetch when the page is known. Try the host's native web fetch tool first. Fall back to
tinyfish fetch content getwhen the native tool is blocked, fails, or returns empty content.
Search
Run the search:
bash tinyfish search query "best React state management libraries"Add hints when the question is geo- or language-specific:
bash tinyfish search query "best pho in Saigon" --location "Vietnam" --language "en"Read the results. The default output is JSON. Each result carries
position,site_name,title,url, andsnippet. A snippet often answers a simple question. Fetch only the pages that need full content.
Show full SKILL.md (213 more words)Show less
Fetch
Fetch with the TinyFish CLI. Use this when the native web fetch tool is blocked or fails:
bash tinyfish fetch content get "https://example.com/article"One call accepts up to 10 URLs. The server fetches them in parallel.
Read the content. Each entry in
resultscarriestitle,final_url,author,published_date, andtext. Thetextfield holds clean markdown. Ads and navigation are stripped. Checkerrorsfor failed URLs. The other results still succeed.Adjust the extraction when needed. Pass
--linksor--image-linksto also collect outbound links or images. Set--per-url-timeout-ms 45000for slow sites. Use--format htmlor--format jsonwhen markdown loses structure you need.
Ground the answer
- Cite the sources. Name the URL behind every external fact. Never state a fact the fetched content does not support.
Guardrails
- Never use
tinyfish agent runfor plain reading. It drives a real browser and bills per step. Search and fetch cover reading tasks for free. - Never guess or invent URLs. Search first when the address is unknown.
- Never fetch more pages than the answer needs. Every page adds context cost.
- If a command fails with an auth error, run
tinyfish auth statusand report the result. Do not runtinyfish auth loginortinyfish auth seton your own.
© ntorga, 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/web-search of ntorga/agent-starter-kit.
Open the folder on GitHubat commit 851e942
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Web Search this skillntorga/agent-starter-kit | 146 | — | ~945 | Automated safety check: Pass | MIT | |
| Brave Searchbadlogic/pi-skills | 2.6k | 6 repos | ~592 | Automated safety check: Pass | MIT | |
| Enterprise AI Scenario MapMetaInFLow/Enterprise-ai-scenario-map-skill | 632 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Web Searchjjyaoao/HelloAgents | 3.2k | 1 repos | ~5.6k | Automated safety check: Pass | MIT | |
| Ddg SearchTheSyart/claude-agent-examples | 405 | 1 repos | ~493 | Automated safety check: Pass | None | |
| Local Web SearchuluckyXH/OpenMOSS | 1.3k | — | ~392 | Automated safety check: Notes | MIT |
Similar skills
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。
Web Search
jjyaoao/HelloAgents
Implement web search capabilities using the z-ai-web-dev-sdk.
Ddg Search
TheSyart/claude-agent-examples
Web search without an API key using DuckDuckGo Lite via webfetch.
Local Web Search
uluckyXH/OpenMOSS
A skill your agent uses when the user asks for web search that should run via the local-160 Responses API with websearch tool (base URL like https://proxy.example.com, model gpt-5.2-codex(xhigh)).
Web Search
EXboys/skilllite
Web search and content extraction with Tavily and Exa via inference.sh CLI.
More from ntorga/agent-starter-kit
All 21 skills in this repoAgent Decision
ntorga/agent-starter-kit
Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework.
Agent Memory
ntorga/agent-starter-kit
Long-term and session memory across sessions. An agent skill from ntorga/agent-starter-kit.
Architect Design Tree
ntorga/agent-starter-kit
Builds the design tree for the grill — decisions mapped as nodes with dependencies, recommendations, and impact, pruned by path.
Architect Impl Grounding
ntorga/agent-starter-kit
Grounds the grill's settled decisions in the codebase — annotates impl.md with file paths, signatures, reference files, test specs, and LOC; re-grounds the next epic after each landing.
Boot
ntorga/agent-starter-kit
Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.
Browser Inspect
ntorga/agent-starter-kit
Browser inspection and interaction for verifying rendered web UI during development.
Related
Categories
Questions about Web Search
What does Web Search do?
Web search and page fetch through the TinyFish CLI. An agent skill from ntorga/agent-starter-kit. Web Search is an agent skill from ntorga/agent-starter-kit. Web search and page fetch through the TinyFish CLI.
When should I use Web Search?
Web Search fits situations like: tasks that involve Web search.
How do I install Web Search in Claude Code?
Run `npx skills add ntorga/agent-starter-kit --skill web-search -a claude-code`. Or copy the skill folder (skills/web-search in ntorga/agent-starter-kit) 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 ntorga/agent-starter-kit --skill web-search -a codex`. Or copy the skill folder (skills/web-search in ntorga/agent-starter-kit) 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 ntorga/agent-starter-kit --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 names 1 domain. As links in the text: docs.tinyfish.ai. 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 MIT 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 945 tokens (SKILL.md is roughly 3.8k 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: Brave Search (badlogic/pi-skills, 2.6k stars), Enterprise AI Scenario Map (MetaInFLow/Enterprise-ai-scenario-map-skill, 632 stars), Web Search (jjyaoao/HelloAgents, 3.2k stars) and Ddg Search (TheSyart/claude-agent-examples, 405 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Web Search?
ntorga (a GitHub user) maintains it in ntorga/agent-starter-kit, which has 146 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 12, 2026.
Source: ntorga/agent-starter-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.