researching-web
installsforks
How to install researching-web?
alexei-led/cc-thingz/researching-web
$npx -y skills add alexei-led/cc-thingz --skill researching-webFollow the base skill. This Claude overlay only defines tool use and execution details.
SKILL.md
| 1 | # Web Research |
| 2 | |
| 3 | Follow the base skill. This Claude overlay only defines tool use and execution details. |
| 4 | |
| 5 | ## Claude tool rules |
| 6 | |
| 7 | - Use Perplexity for broad research questions, comparisons, or source discovery when it is available. |
| 8 | - Use `WebFetch` to inspect primary or official sources directly after source discovery. |
| 9 | - Do not answer research questions from memory. |
| 10 | - Do not route exact API syntax or code-example questions here; use `looking-up-docs`. |
| 11 | - Do not route repo-specific questions here when local files can answer them. |
| 12 | |
| 13 | ## Tool selection on Claude |
| 14 | |
| 15 | - Simple factual question: use the smallest web query that can answer it. |
| 16 | - Source selection: use Perplexity or another available search-capable tool, then fetch the best sources. |
| 17 | - Broad investigation: use Perplexity first when it fits; if the runtime offers a deeper research mode, use it when the question truly needs it. |
| 18 | - Follow-up detail: fetch only the sources needed to support the claim. |
| 19 | |
| 20 | Inspect enough sources to support the answer. Do not fetch every citation unless the |
| 21 | risk or ambiguity justifies it. |
| 22 | |
| 23 | ## Source handling |
| 24 | |
| 25 | - Prefer official docs, standards, vendor docs, maintainer posts, and primary announcements. |
| 26 | - Treat forum summaries and secondary blogs as supporting evidence, not sole authority, when stronger sources should exist. |
| 27 | - If sources conflict, show the conflict and reduce confidence. |
| 28 | - If only a research plan is possible, say that final evidence must be grounded in URL-cited sources. |
| 29 | |
| 30 | ## Optional delegation |
| 31 | |
| 32 | Use `Task` only for broad background research that can run independently without |
| 33 | changing the output contract. Keep the prompt bounded and ask it to return cited |
| 34 | facts, not final recommendations. |
| 35 | |
| 36 | ## Output |
| 37 | |
| 38 | Use the base skill's `Research Result` output contract exactly. |
People who liked this also viewed
6 picksType
- azure-aiUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector searSkillsJul 2026
- just-scrapeSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON fromSkillsJul 2026
- firecrawlCLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agentsSkillsJul 2026
- firecrawl-searchWeb search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "SkillsJul 2026
- firecrawl-agentAI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, producSkillsJul 2026
- firecrawl-mapDiscover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where sSkillsJul 2026
