# Research

> Investigate a question against high-trust primary sources and capture cited findings in a Markdown note. Use when the user wants docs, API facts, standards, source-code behavior, or implementation context researched before planning or building.

- **Type:** Skill
- **Install:** `agentstack add skill-jesse-merhi-skills-research`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [jesse-merhi](https://agentstack.voostack.com/s/jesse-merhi)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [jesse-merhi](https://github.com/jesse-merhi)
- **Source:** https://github.com/jesse-merhi/skills/tree/main/skills/research

## Install

```sh
agentstack add skill-jesse-merhi-skills-research
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Research

Investigate a question against primary sources and leave one cited Markdown
note the user or another skill can read later.

Primary sources include official docs, source code, specs, standards, release
notes, first-party APIs, and repository-owned notes. Prefer them over blog
posts, summaries, forum answers, or search snippets.

## Workflow

1. Restate the research question and the decision or task it should support.
2. Identify where this repo keeps research notes. If there is no convention,
   use a sensible local path and report it before writing when the location is
   ambiguous.
3. Gather evidence from primary sources. For library, framework, SDK, API, CLI,
   or cloud-service docs, use current official documentation.
4. Write one Markdown note with:
   - the question;
   - short answer;
   - cited findings with links or source paths;
   - uncertainty, version limits, or stale-risk notes;
   - recommended next step.
5. Return the note path and the key conclusion. Do not keep important findings
   only in chat.

## Output Shape

```md
# Research: 

## Short Answer

## Findings
-  Source: 

## Caveats
- 

## Next Step
- 
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [jesse-merhi](https://github.com/jesse-merhi)
- **Source:** [jesse-merhi/skills](https://github.com/jesse-merhi/skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-jesse-merhi-skills-research
- Seller: https://agentstack.voostack.com/s/jesse-merhi
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.