samhjn/palvia/deep-research
Claude Code and agent skill by samhjn/palvia
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Systematic research methodology with source evaluation and synthesis
Install
npx vskill@latest install samhjn/palvia/deep-researchSKILL.md
Deep Research Skill
When asked to research a topic, follow this methodology:
Research Tools (in order of preference)
- Browser tools (primary — most reliable for web research):
browser_navigate(url:)→ open a URL in the in-app browserbrowser_get_page_info(include_content: true)→ read page text, links, and interactive elementsbrowser_extract(selector:)→ extract specific elements (headlines, article bodies, etc.)- Search strategy: navigate to
https://www.google.com/search?q=YOUR+QUERYto find sources, then visit promising results
- `fetch_and_extract` (quick plain-text fetch — may fail due to sandbox network restrictions; if it returns HTTP 0 or network errors, switch to browser tools immediately)
- Post-processing scripts (use
run_snippetto execute):
extract_links— parse HTML to extract follow-up URLs for deeper investigationsummarize_text— condense long text into key points ranked by importance
Process
- Decompose the question into 2–5 focused sub-questions
- Search — start with a search engine query via browser, then visit the most promising results
- Gather — read each source page with
browser_get_page_info; usebrowser_extractfor specific content; follow links for deeper investigation - Evaluate — assess source credibility (official docs > research papers > established news > blogs), recency, and potential biases
- Synthesize — organize findings into a coherent analysis, cross-referencing multiple sources
- Cite — reference every key claim to its source URL with a confidence level (High / Medium / Low)
Iterative Deepening
- After the first pass, identify gaps or conflicting information
- Search for additional sources to fill gaps or resolve conflicts
- Stop when key claims have 2–3 corroborating sources, or when additional sources add no new information
Output Format
- Executive Summary — 2–3 sentence overview of key findings
- Findings — organized by sub-topic, each with inline source citations
- Source Table — list of sources used with credibility rating (High / Medium / Low)
- Uncertainties — flag conflicting information and knowledge gaps
- Conclusions — actionable takeaways
Guidelines
- Prefer primary sources (official docs, research papers, raw data) over secondary (news articles, blog posts)
- Note when information might be outdated — check publication dates
- Distinguish clearly between established facts, expert opinions, and speculation
- When a tool fails, switch to an alternative immediately — do not retry the same failing tool
- Save key findings to MEMORY.md for future reference
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingPalvia/Resources/BuiltInSkills/deep-research/SKILL.md
Popularity
- Repository stars
- 83
- Repository forks
- 14
- 7-day trend score
- 22
Stars and forks are for the whole GitHub repository, not this skill alone. 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/samhjn/palvia/deep-research)