Agent skill

Behive Research

A skill your agent uses when the user asks to research a topic deeply, gather intelligence, or build a knowledge base.

MITAuto-check passedKnowledge Management

Install Behive Research

skills CLI

$ npx skills add qa10devteam/behive --skill behive-research -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install qa10devteam/behive behive-research --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/qa10devteam/behive.git skills-src && mkdir -p .claude/skills && cp -r skills-src/integrations/hermes .claude/skills/behive-research && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "behive-research" agent skill from https://github.com/qa10devteam/behive/tree/main/integrations/hermes into .claude/skills/behive-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "behive-research", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/qa10devteam/behive/tree/main/integrations/hermes

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add qa10devteam/behive --skill behive-research -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install qa10devteam/behive behive-research --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/qa10devteam/behive.git skills-src && mkdir -p .agents/skills && cp -r skills-src/integrations/hermes .agents/skills/behive-research && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "behive-research" agent skill from https://github.com/qa10devteam/behive/tree/main/integrations/hermes into .agents/skills/behive-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "behive-research", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add qa10devteam/behive --skill behive-research -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install qa10devteam/behive behive-research --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/qa10devteam/behive.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/integrations/hermes .cursor/skills/behive-research && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "behive-research" agent skill from https://github.com/qa10devteam/behive/tree/main/integrations/hermes into .cursor/skills/behive-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "behive-research", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/qa10devteam/behive.git --path integrations/hermes

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add qa10devteam/behive --skill behive-research -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install qa10devteam/behive behive-research --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/qa10devteam/behive.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/integrations/hermes .gemini/skills/behive-research && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "behive-research" agent skill from https://github.com/qa10devteam/behive/tree/main/integrations/hermes into .gemini/skills/behive-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "behive-research", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install qa10devteam/behive behive-research

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add qa10devteam/behive --skill behive-research -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/qa10devteam/behive.git skills-src && mkdir -p .github/skills && cp -r skills-src/integrations/hermes .github/skills/behive-research && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "behive-research" agent skill from https://github.com/qa10devteam/behive/tree/main/integrations/hermes into .github/skills/behive-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "behive-research", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add qa10devteam/behive --skill behive-research -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install qa10devteam/behive behive-research --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/qa10devteam/behive.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/integrations/hermes .opencode/skills/behive-research && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "behive-research" agent skill from https://github.com/qa10devteam/behive/tree/main/integrations/hermes into .opencode/skills/behive-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "behive-research", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: behive-research
GitHub stars: 146
Token cost: ~1.4k tokens
SKILL.md length: 510 words
Files: 1
Skills in repo: 2
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses when the user asks to research a topic deeply, gather intelligence, or build a knowledge base.

Works in 5 steps: Decomposes topics into research axes → Fetches 1000+ sources via 8-layer… → Extracts typed claims with per-claim… → …
The user asks to research a topic deeply
SKILL.md covers Overview, When to Use, Don't Use For and Prerequisites, plus 8 more sections
Calls curl and jq

What it does

Behive Research is an agent skill from qa10devteam/behive. Use when the user asks to research a topic deeply, gather intelligence, or build a knowledge base. Connects to BeHive API (self-hosted or cloud) to run multi-source research missions with structured claim extraction, quality scoring, and knowledge graph construction.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management, covering Deep research, Knowledge graphs and Knowledge bases. It works with Model Context Protocol. The repository describes itself as: Open-source deep research engine that builds structured knowledge graphs. MCP-native. avg 0.82+ quality. The licence is MIT.

When your agent uses it

The user asks to research a topic deeply
Gather intelligence
Build a knowledge base

Example prompts

“/behive-research”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

Decomposes topics into research axes
Fetches 1000+ sources via 8-layer stealth drones (70+ APIs)
Extracts typed claims with per-claim quality scores (0.0–1.0)
Builds entity relationship graphs (Neo4j)
Produces synthesized reports with inline citations

What it can do on your machine

Read from SKILL.md and the folder at commit 91e9a64. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- curl
- jq
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Behive Research loads about 1.4k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 510 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~71
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from qa10devteam/behive at commit 91e9a64, republished under its MIT licence (© qa10devteam). 510 words, ~1,434 tokens.

Download SKILL.mdSave it as .claude/skills/behive-research/SKILL.md (or your agent's skills folder).

name: behive-research
description: Use when the user asks to research a topic deeply, gather intelligence, or build a knowledge base. Connects to BeHive API (self-hosted or cloud) to run multi-source research missions with structured claim extraction, quality scoring, and knowledge graph construction.
version: 1.0.0
author: QA10
license: MIT

BeHive Deep Research

Overview

BeHive is a deep research engine that extracts structured, scored claims from any topic. Unlike simple web search, it:

Decomposes topics into research axes
Fetches 1000+ sources via 8-layer stealth drones (70+ APIs)
Extracts typed claims with per-claim quality scores (0.0–1.0)
Builds entity relationship graphs (Neo4j)
Produces synthesized reports with inline citations

This skill connects Hermes Agent to a running BeHive instance.

When to Use

User says "research X deeply", "gather intelligence on Y", "find everything about Z"
User needs verified facts with sources, not LLM-generated summaries
User wants claims they can cite, filter by quality, or query later
User asks to build a knowledge base on a topic over time
User says "run a mission on X", "scale 100", "deep dive"

Don't Use For

Simple factual lookups (use web_search)
Single-page content extraction (use web_extract)
Real-time news (BeHive takes 5-15 min per mission)

Prerequisites

BeHive API running at http://localhost:8091 or configured endpoint.

Verify:

bash

curl -s http://localhost:8091/health | jq .

If using MCP (recommended), configure in ~/.hermes/config.yaml:

yaml

mcp_servers:
  behive:
    url: http://localhost:8090/mcp
    transport: streamable-http

Quick Research (MCP)

If BeHive MCP is configured, use MCP tools directly:

mcp_behive_research_topic(request={"query": "NVIDIA GPU market 2025-2026", "depth": 3, "force": true})

Then poll:

mcp_behive_mission_status(job_id="<returned_id>")

Get report:

mcp_behive_get_report(job_id="<id>", format="markdown")

Search past knowledge:

mcp_behive_search_knowledge(query="NVIDIA revenue", limit=20)

Research via REST API (terminal)

Start a Mission

bash

curl -s -X POST http://localhost:8091/research \
  -H "Content-Type: application/json" \
  -d '{"topic": "EU AI Act enforcement mechanisms 2026", "scale": 30, "depth": 3}' | jq .

Scale guide:

15 — quick scout (2-3 min, ~50 claims)
30 — standard (5-10 min, ~200-500 claims)
100 — deep (15-30 min, ~800+ claims)
300 — exhaustive (45-90 min, ~2000+ claims)

Poll Status

bash

curl -s http://localhost:8091/research/<mission_id> | jq .status,.phase,.progress

Phases: scout → harvest → process → synth → done

Get Report

bash

curl -s http://localhost:8091/research/<mission_id>/report | jq .

Search Claims

bash

curl -s "http://localhost:8091/search?q=NVIDIA+revenue&limit=20" | jq .

List Missions

bash

curl -s http://localhost:8091/missions | jq '.[] | {id, topic, status, avg_quality, total_claims}'

SSE Streaming (real-time progress)

bash

curl -N http://localhost:8091/research/<mission_id>/events

Returns Server-Sent Events with phase transitions, progress %, and claim counts.

Quality Interpretation

Score Range	Meaning	Action
0.85–1.00	Excellent — specific, verified, multi-dimensional	Trust directly
0.75–0.84	Good — solid claim with evidence	Use with confidence
0.65–0.74	Acceptable — valid but may lack specifics	Verify key details
0.55–0.64	Marginal — passed quality gate barely	Cross-reference
< 0.55	Rejected — never enters database	N/A

Knowledge Graph Queries

bash

# Get entities
curl -s "http://localhost:8091/graph/entities?limit=50" | jq .

# Get relationships for an entity
curl -s "http://localhost:8091/graph/entity/NVIDIA/relationships" | jq .

# Network stats
curl -s http://localhost:8091/intelligence/stats | jq .

Show full SKILL.md (211 more words)Show less

Workflow: Research → Report → Deliver

Start mission with appropriate scale
Monitor via SSE or polling (every 30s)
On completion, fetch report
Format key findings for user
Offer to search specific claims or explore the knowledge graph

Common Pitfalls

Using web_extract on localhost — Hermes blocks private IPs via web_extract. Always use terminal() + curl for BeHive API calls.
Scale too high for simple topics — Scale 30 is sufficient for most queries. Scale 300 takes 45+ minutes and may hit rate limits.
Not waiting for completion — Missions are async. Always poll or stream until status=done.
Confusing mission_id formats — IDs look like hive_1785227949_815112. Copy exactly from the start response.
Expecting real-time results — Even scale 15 takes 2-3 minutes. Set user expectations.

Benchmarks (real, honest)

Topic	Claims	Avg Quality	Duration	Sources
NVIDIA GPU market 2025	290	0.797	8 min	234
OpenAI GPT-5 capabilities	574	0.789	12 min	174
EU AI Act enforcement	267	0.759	6 min	130
Meta Llama 4	568	0.821	11 min	198

Hardware: EC2 g6.24xlarge, 4× NVIDIA L4, Bedrock Claude Haiku + Sonnet.

Verification Checklist

curl http://localhost:8091/health returns 200
MCP configured in config.yaml (if using MCP path)
Mission started and job_id captured
Status polled until done or error
Report delivered to user in readable format

Files

Just SKILL.md in integrations/hermes of qa10devteam/behive.

Open the folder on GitHubat commit 91e9a64

Compare with similar skills

Behive Research next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Behive Research compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Behive Research this skillqa10devteam/behive	146	—	~1.4k	Automated safety check: Pass	MIT	2 days ago
Askagenticnotetaking/arscontexta	3.5k	1 repos	~5.7k	Automated safety check: Pass	MIT	7 mo ago
Engraphdevwhodevs/engraph	171	—	~792	Automated safety check: Pass	MIT	4 mo ago
LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything	85k	1 repos	~1.5k	Automated safety check: Pass	MIT	yesterday
Learnagenticnotetaking/arscontexta	3.5k	1 repos	~1.9k	Automated safety check: Notes	MIT	7 mo ago
NotebookLM Research Workflowclaude-world/notebooklm-skill	463	—	~1.8k	Automated safety check: Pass	MIT	2 mo ago

Similar skills

Ask
agenticnotetaking/arscontexta
Query the bundled research knowledge graph for methodology guidance.
3.5k GitHub starsUsed in 1 repo~5.7k tokens
Knowledge ManagementAuto-check passed
Engraph
devwhodevs/engraph
Index and search document collections using hybrid semantic + graph + full-text search.
171 GitHub stars~792 tokensUpdated 4 mo ago
Knowledge ManagementAuto-check passed
LLM Wiki Knowledge Graph
Egonex-AI/Understand-Anything
Detects a Karpathy-pattern LLM wiki and builds an interactive knowledge graph with entities, implicit relationships and topic clusters.
85k GitHub starsUsed in 1 repo~1.5k tokens
Knowledge ManagementAuto-check passed
Learn
agenticnotetaking/arscontexta
Research a topic and grow your knowledge graph. An agent skill from agenticnotetaking/arscontexta.
3.5k GitHub starsUsed in 1 repo~1.9k tokens
Knowledge ManagementAuto-check: notes
NotebookLM Research Workflow
claude-world/notebooklm-skill
Creates NotebookLM notebooks from URLs, text and files, asks cited questions, runs web research and generates audio, slides, quizzes and other artifacts.
463 GitHub stars~1.8k tokensUpdated 2 mo ago
Knowledge ManagementAuto-check passed
Arkon Edit
nduckmink/arkon
Propose or directly apply edits to Arkon wiki pages, including proposing brand new pages.
1.5k GitHub stars~1.6k tokensUpdated 4 mo ago
Knowledge ManagementAuto-check passed

Questions about Behive Research

What does Behive Research do?

A skill your agent uses when the user asks to research a topic deeply, gather intelligence, or build a knowledge base. Behive Research is an agent skill from qa10devteam/behive. Use when the user asks to research a topic deeply, gather intelligence, or build a knowledge base.

When should I use Behive Research?

Behive Research fits situations like: the user asks to research a topic deeply; gather intelligence; build a knowledge base.

How do I install Behive Research in Claude Code?

Run `npx skills add qa10devteam/behive --skill behive-research -a claude-code`. Or copy the skill folder (integrations/hermes in qa10devteam/behive) into .claude/skills/behive-research in your project. Claude Code loads it when a task matches its description.

How do I install Behive Research in Codex?

Run `npx skills add qa10devteam/behive --skill behive-research -a codex`. Or copy the skill folder (integrations/hermes in qa10devteam/behive) into .agents/skills/behive-research in your project. Codex loads it when a task matches its description.

Can I use Behive Research in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add qa10devteam/behive --skill behive-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/behive-research, .gemini/skills/behive-research, .github/skills/behive-research and .opencode/skills/behive-research in your project.

What does Behive Research need to run?

Going by SKILL.md and its folder, Behive Research needs the command-line tools its instructions call (curl and jq).

Does Behive Research access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Behive Research safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Behive Research use?

Behive Research is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Behive Research use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Behive Research?

Skills that share tags, products or a category with Behive Research: Ask (agenticnotetaking/arscontexta, 3.5k stars), Engraph (devwhodevs/engraph, 171 stars), LLM Wiki Knowledge Graph (Egonex-AI/Understand-Anything, 85k stars) and Learn (agenticnotetaking/arscontexta, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Behive Research?

qa10devteam (a GitHub user) maintains it in qa10devteam/behive, which has 146 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 5, 2026.

Source: qa10devteam/behive on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Behive Research

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

BeHive Deep Research

Overview

When to Use

Don't Use For

Prerequisites

Quick Research (MCP)

Research via REST API (terminal)

Start a Mission

Poll Status

Get Report

Search Claims

List Missions

SSE Streaming (real-time progress)

Quality Interpretation

Knowledge Graph Queries

Workflow: Research → Report → Deliver

Common Pitfalls

Benchmarks (real, honest)

Verification Checklist

Files

Compare with similar skills

Similar skills

Ask

Engraph

LLM Wiki Knowledge Graph

Learn

NotebookLM Research Workflow

Arkon Edit

More from qa10devteam/behive

Behive Research

Related

Questions about Behive Research