research-data-collection
Skill3 starsChanged 33 days agoMITView on GitHub
Collect, normalize, and summarize public web data for downstream agents. Use when researching markets, competitors, products, pricing, positioning, SEO content, source evidence, or customer language using search, HTTP extraction, Firecrawl, Playwright, Scrapling, or other scraping tools.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/general/code-reviewer/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- fastify-best-practicesSkill
- agent-toolkit-maintainerSkill
- onboard-repoSkill
- docker-patternsSkill
- accessibilitySkill
- code-reviewerSkill
- thermo-nuclear-code-quality-reviewSkill
- brag-slimSkill
- biome-formattingSkill
- instagram-public-researchSkill
- api-security-auditSkill
- cicd-security-auditSkill
- cloud-misconfiguration-auditSkill
- js-secrets-auditSkill
- llm-agent-security-auditSkill
- security-auditSkill
- source-leak-auditSkill
- ariadne-prdSkill
- ariadneSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Prefer public pages and official APIs.
- Distinctive: line 14
Check robots.txt, site terms, and task scope before crawling.
- Distinctive: line 15
Do not bypass paywalls, login walls, captchas, or access controls.
- Distinctive: line 16
Do not collect sensitive personal data without a lawful explicit scope and repository policy.
- Distinctive: line 23
Start with search or a human-curated source list for broad questions.
- Distinctive: line 24
Use public-page extraction for markdown-friendly sources.
- Distinctive: line 27
Avoid stealth or anti-bot modes unless the terms permit automation and a human explicitly approved the risk.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Research Data Collection
Collect useful evidence, not raw dumps. The output should help another agent make better decisions.
Safety Policy
- Prefer public pages and official APIs.
- Check robots.txt, site terms, and task scope before crawling.
- Do not bypass paywalls, login walls, captchas, or access controls.
- Do not collect sensitive personal data without a lawful explicit scope and repository policy.
- Rate-limit requests, keep crawls narrow, record provenance, and separate facts from inferences.
Tool Selection
- Start with search or a human-curated source list for broad questions.
- Use public-page extraction for markdown-friendly sources; use HTTP clients for static pages/APIs and browser automation only for JS-rendered pages.
- Restrict crawlers to bounded multi-page extraction.
- Avoid stealth or anti-bot modes unless the terms permit automation and a human explicitly approved the risk.
Output Contract
Return a compact research pack with objective/scope; source URL, title, access time, method, relevance and confidence; cited facts; relevant competitor claims, offers, pricing, proof, objections, and audience language; SEO entities/content gaps; artifacts where visual evidence matters; limitations; and next actions.
For landing-page research, prioritize audience pains, outcomes, positioning, proof, differentiation, official contact channels, search terms, FAQs, objections, and visual references. Mark channels as validated, user-provided, inferred, inaccessible, or pending; never invent a WhatsApp number.
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.