shrivatsas/dev-setup/research
Claude Code and agent skill by shrivatsas/dev-setup
- community
Checking that the SKILL.md file is still in the repository.
Conduct preliminary research, generate a research outline, and produce concise, evidence-first results for comparisons, benchmarks, technology selection, and topic scans.
Install
npx vskill@latest install shrivatsas/dev-setup/researchSKILL.md
The same SKILL.md was published earlier as shrivatsas/dev-setup/research.
Research
Use this skill when the user wants structured research, an outline, or a research report.
Response Style
- Lead with the conclusion or most useful finding.
- Keep prose short and direct.
- Prefer concrete evidence, dates, names, and sources over abstract commentary.
- Separate facts, inferences, and assumptions.
- Avoid hedging unless uncertainty is real and important.
Trigger
/research <topic>
Workflow
Step 1: Build an initial framework
Use model knowledge to draft:
- Main research objects or items in the domain
- A proposed field framework
Then ask the user to confirm:
- items to add or remove
- whether the field framework is sufficient
Step 2: Supplement with web research
Ask the user for a time range, for example:
- last 6 months
- since 2024
- unlimited
Use this template exactly, replacing only the variables:
Step 3: Check for existing field definitions
Ask whether the user already has a field definition file.
If yes, read it and merge it with the research outputs.
Step 4: Generate outline files
Combine:
- the initial framework
- the web research supplement
- any existing field definitions
Create these files:
outline.yamlfields.yaml
outline.yaml should include:
topicitemsexecution.batch_sizeexecution.items_per_agentexecution.output_dir
fields.yaml should include:
- field categories and definitions
- each field's name, description, and
detail_level detail_levelhierarchy:brief->moderate->detaileduncertainfields reserved for the deep phase
Step 5: Show results
Create ./{topic_slug}/ and save:
outline.yamlfields.yaml
Show the generated files to the user for confirmation.
Follow-up Commands
/research-add-items- supplement items/research-add-fields- supplement fields/research-deep- start deep research
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 repositoryCheckingskills/research/SKILL.md
Popularity
- 7-day trend score
- 5
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/shrivatsas/dev-setup/research)