web-search
Skill0 starsChanged 39 days agoApache-2.0View on GitHub
Trigger: web search, buscar en la web, external evidence, fuentes externas, docs lookup, url fetch. Prefer donsetch and context7 over built-in web tools; pick search, fetch, crawl, or docs per need.
81 other projects use a version of this.
Adopted by
Most recently taken up by
- Suge8/friedbuntheir own version, first seen Nov 8, 2026
- Kianzzz/Zhouxing-skill-publictheir own version, first seen Nov 8, 2026
- alibaba-damo-academy/ScholarSeedtheir own version, first seen Nov 8, 2026
- delorenj/skillstheir own version, first seen Nov 7, 2026
- FishRaposo/aria-agenttheir own version, first seen Nov 1, 2026
- usestring/string-claude-plugintheir own version, first seen Nov 1, 2026
Used with
Projects with it also use Video Generation, VLM and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
huang-x-hSkillVideo Generation
Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.
Also in 6 projects that use this
- huang-x-hSkill
VLM
Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze images, describe visual content, or create applications that combine image understanding with conversational AI. Supports image URLs and base64 encoded images for multimodal interactions.
Also in 6 projects that use this
dav-niu474Skillgift-evaluator
The PRIMARY tool for Spring Festival gift analysis and social interaction generation. Use this skill when users upload photos of gifts (alcohol, tea, supplements, etc.) to inquire about their value, authenticity, or how to respond socially. Integrates visual perception, market valuation, and HTML card generation.
Also in 5 projects that use this
- dav-niu474Skill
Podcast Generate
Generate podcast episodes from user-provided content or by searching the web for specified topics. If user uploads a text file/article, creates a dual-host dialogue podcast (or single-host upon request). If no content is provided, searches the web for information about the user-specified topic and generates a podcast. Duration scales with content size (3-20 minutes, ~240 chars/min). Uses z-ai-web-dev-sdk for LLM script generation and TTS audio synthesis. Outputs both a podcast script (Markdown) and a complete audio file (WAV).
Also in 5 projects that use this
- +1 more from huang-x-h
- +7 more from dav-niu474
Other versions81 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 81
- netease-youdao/LobsterAI★ 6.2ksame name
- jjyaoao/HelloAgents★ 3.2ksame name
- digitalinnovationone/dio-agent★ 2.8ksame name
- Xxiii8322766509/NagaAgent★ 1.5ksame name
- RTGS2017/NagaAgent★ 1.5ksame name
- fastclaw-ai/fastclaw★ 1.4ksame name
- freestylefly/wesight★ 969same name
- bear2u/my-skills★ 931same name
- OpenMinis/MinisSkills★ 602same name
- tmustier/pi-for-excel★ 444same name
71 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository31 other files it gives its agents.
- architecture-lintSkill
- architecture-questSkill
- autofixSkill
- branch-prSkill
- chained-prSkill
- cognitive-doc-designSkill
- comment-writerSkill
- design-patternsSkill
- gentle-uiSkill
- gh-address-commentsSkill
- gh-fix-ciSkill
- github-automationSkill
- github-prSkill
- go-testingSkill
- grillingSkill
- issue-creationSkill
- judgment-daySkill
- playwright-interactiveSkill
- playwrightSkill
- product-questSkill
- skill-creatorSkill
- skill-improverSkill
- systemic-issue-triageSkill
- tailwind-4Skill
- test-fixingSkill
- typescriptSkill
- ui-designSkill
- ui-ux-principlesSkill
- using-git-worktreesSkill
- work-unit-commitsSkill
- zod-4Skill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 64 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Prefer MCP tools: context7 for library/framework docs.
- Distinctive: line 17
Never fabricate sources: every claim requires a fetched URL, excerpt, or snippet.
- Distinctive: line 19
Do not retry endlessly past a wall, paywall, or deadline error: one bounded retry, then report the gap.
- Very specific: line 37
Read references/tool-notes.md for the exact call shapes, budgets, and token-saving modes.
- Distinctive: line 39
If the preferred tool is unavailable or fails non-recoverably, fall back to the built-in.
“Common” is measured: kept by at least 6 in 10 of the 64 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Activation Contract
Load when the task needs external or current information: web search, browsing a site, fetching a URL, crawling multi-page docs, or library/framework documentation lookups. Applies to orchestrator direct work and delegated sub-agents.
Hard Rules
- Prefer MCP tools: context7 for library/framework docs; donsetch for general web (
web_search,web_fetch,web_crawl). Use built-inwebsearch/webfetchONLY as fallback when the preferred tool is unavailable or fails. - Never fabricate sources: every claim requires a fetched URL, excerpt, or snippet. Report only evidence from retrieved content.
- Finish every web evidence trail with source identification: URL, title, publisher, and accessed date.
- Do not retry endlessly past a wall, paywall, or deadline error: one bounded retry, then report the gap.
- In SDD research, tool selection never bypasses capability admission: grants gate evidence, this skill only selects tools.
Decision Gates
| Need | Tool |
| Library/framework/API docs or version migration | context7 (resolve → query) |
| Find sites or URLs for a topic | donsetch web_search |
| Read one known URL | donsetch web_fetch |
| Multi-page docs/site or sitemap-aware crawl | donsetch web_crawl |
| Verify a page mentions X (cheap) | donsetch web_fetch with must_contain |
| Navigate structure of a long page | donsetch web_fetch toc, then section |
| Preferred tool unavailable or failed | built-in websearch / webfetch (fallback only) |
Execution Steps
- Classify the need (docs lookup vs general web vs verification) and pick the tool from the gate table.
- Read
references/tool-notes.mdfor the exact call shapes, budgets, and token-saving modes. - Capture sources (URL, title, publisher, accessed date) and note contradictions, uncertainty, and freshness.
- If the preferred tool is unavailable or fails non-recoverably, fall back to the built-in; if that fails too, state the gap — never invent.
Output Contract
Return sources as URL + title + excerpt; label anything unverified; keep evidence separate from opinion. Report fallback use when applicable.
References
references/tool-notes.md— operational notes: exact tool call shapes, budgets, and saving modes.../../_shared/research-lifecycle.md— SDD research admission contract (evidence gating) for SDD phases.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.