Skip to content
Agentmart
Submit a tool

research

Skill by hmkm-dev

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hmkm-dev-research

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

The publisher has not written a description yet.

Use cases: research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions: not checked yet.

What's inside

Skill name
research
Description
None
License
MIT
Instructions
31 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • missing YAML frontmatter
  • name: missing
  • description: missing

Files (3)

  • SKILL.md
  • .gitkeep · tests/
  • .gitkeep · workflows/

SKILL.md (first lines)

# Skill: Research

**Status: IMPLEMENTED** — runs via the existing Research worker + MCP search/Playwright tools. Requires `SEARCH_PROVIDER=brave` + `BRAVE_SEARCH_API_KEY` configured (documented external prerequisite — a real Brave Search API account, free tier available).

## Purpose
Web search, page retrieval, source-gathering, and synthesis with preserved citations.

## Inputs
- `query`: what to research

## Outputs
- `summary`, `sources` (list of `{url, title}`)

## Allowed tools
`search`, `playwright`

## Workflow
1. MCP `search` tool call (real Brave Search API call)
2. Top results fetched via Playwright
3. Synthesis via the model router, instructed to only state claims the source material supports

## Success criteria
- `sources` non-empty
- Summary grounded in fetched page content

## Verification
`source_reference` evidence: each cited URL is the actual URL fetched, traceable to the real Playwright call. `cross_check_result`: a second independent fetch confirming the same claim before verified=true.

## Failure handling
`missing_information`/`external_service_failure` — not silently treated as "complete with zero findings"; the mission evaluator requires verified evidence.

From hmkm-dev/Agent-OS-3.0, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 27, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Cite this page

research skill. Agent Mart. https://agentmart.dev/skills/hmkm-dev-research (last updated 2026-10-24)