insightpulseai/odoo/deep-research
Claude Code and agent skill by insightpulseai/odoo
- community
Checking that the SKILL.md file is still in the repository.
Deep Research Skill — Conduct exhaustive context gathering and output deterministic research artifacts.
Install
npx vskill@latest install insightpulseai/odoo/deep-researchSKILL.md
The same SKILL.md was published earlier as insightpulseai/odoo/deep-research.
Deep Research Skill
You are executing the Deep Research Skill.
Objective
Convert open-ended "deep research" requests into structured, deterministic outputs. Do not implement code changes during this phase. Your sole output is a set of research artifacts that comprehensively answer the user's questions or scope out an implementation plan.
Triggers
/sc:research- "conduct deep research"
- "deep dive into"
Hand-off Contract
Your research must produce a PRD-ready delta list or explicit spec patch recommendations that another agent (or the user) can immediately implement.
Required Outputs
Every Deep Research run MUST produce the following artifacts in the relevant specification or workspace directory (e.g. spec/<feature>/):
- `research.md`: The primary research document containing technical findings, architectural constraints, and recommendations.
- `sources.md` (or inline citations within
research.md): Explicit citations to the precise internal files viewed, tools used, or external documents accessed to produce the research. - `findings.json`: A machine-readable summary of the key findings, open questions, and confidence levels.
Guardrails (Strict Enforcement)
- No invented facts: Do not hallucinate repository internals or Odoo behaviors.
- Cite sources: Every claim must be tied to an actual file examined or an external documentation run.
- Explicit Assumptions: You MUST include an "Assumptions & Open Questions" section detailing what could not be verified and what decisions are pending user input.
- Scope Limit: Stop once the research phase is complete. DO NOT attempt to write application code.
Execution Procedure
- Receive input scope, question, and context.
- Formulate a search plan utilizing exact-text
grep_search, local semantic queries, or file inspection (view_file,view_code_item). - Compile findings into memory.
- Draft the structured outputs (
research.md,sources.md,findings.json). - Terminate and hand execution back to the user or orchestration agent with a summary of outputs.
Security
- Security scanPassed, 95 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 repositoryCheckingagents/skills/deep-research/SKILL.md
Popularity
- Repository stars
- 6
- Repository forks
- 2
- 7-day trend score
- 15
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/insightpulseai/odoo/deep-research)