austin-patrician/wordless/content-web-research
Claude Code and agent skill by austin-patrician/wordless
- community
Checking that the SKILL.md file is still in the repository.
Research current facts, examples, trends, and source material for a content brief using the available web search or crawling connectors. Use when content planning needs information beyond the user's supplied material. Do not use for local-only rewriting, drafting without factual research, or deep data-analysis research workflows.
Install
npx vskill@latest install austin-patrician/wordless/content-web-researchSKILL.md
Content Web Research
Build a compact, traceable evidence packet for the content team. This skill uses only the web search and crawling connector tools exposed in the current session; it does not require research_snapshot, research_submit_dimension, or other data-analysis research tools.
Workflow
- Restate the audience, content goal, geography, time range, and claims that need external support.
- Search narrowly for each material question. Prefer primary, official, regulatory, academic, filing, or directly accountable sources.
- Open or crawl the strongest results when a search snippet is insufficient.
- Cross-check decision-critical claims with an independent source. Do not treat several pages repeating the same origin as independent confirmation.
- Record the source title, publisher, URL, publication or update date when available, and the exact fact it supports.
- Separate verified facts, reasonable interpretation, and unresolved uncertainty.
- Hand the writer a concise editorial brief rather than a raw search transcript.
Safety And Permissions
- Use read-only search and retrieval operations whenever possible.
- If a connector operation is not explicitly read-only, wait for approval instead of attempting an alternative that bypasses it.
- Never publish, upload, modify remote data, submit forms, or change workspace files.
- Do not invent a source, URL, quotation, statistic, or publication date.
- If no suitable web connector is available, return a clear blocker and continue with only the evidence supplied by the user.
Handoff
Return:
- the recommended angle and audience promise;
- a short outline and evidence requirements for each section;
- a source list with URLs and supported claims;
- conflicts, stale information, and facts that still need verification;
- tone, constraints, and acceptance criteria for the writer.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingapps/desktop/resources/skills/content-web-research/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/austin-patrician/wordless/content-web-research)