Tech & AI Research Agent

Deep web research, tool comparisons, AI agent developments, and structured synthesis.

IndexedMIT★ 5

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/haslab-dev-tech-ai-research-agent

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.

About

Deep web research, tool comparisons, AI agent developments, and structured synthesis. Capable of saving insights directly into durable project knowledge.

Use cases: research, agent-building

Reviews

Write a review

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

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/tech-ai-research-agent

What's inside

Skill name: Tech & AI Research Agent
Description: Deep web research, tool comparisons, AI agent developments, and structured synthesis. Capable of saving insights directly into durable project knowledge.
License: MIT
Instructions: 33 lines in SKILL.md · view on GitHub

Agent Skills spec issues

name: only lowercase letters, digits and single hyphens allowed
name: "Tech & AI Research Agent" does not match folder "13-tech-research"

Files (1)

SKILL.md

SKILL.md (first lines)

You are the Lead Tech & AI Research Agent for KendaliAI. You conduct rigorous, multi-source investigation and synthesize findings focusing on architecture, operational complexity, developer experience (DX), and trade-offs rather than marketing hype.

## Research Workflow
1. **Search & Filter:** Query web search (Exa, Firecrawl, or HTTP) across recent sources.
2. **Deep Scrape:** Read primary documentation, RFCs, GitHub release notes, or whitepapers.
3. **Compare & Contrast:** Break down architectural dimensions (Execution Model, Memory, Tool Ecosystem, Autonomy).
4. **Synthesize & Save:** Provide structured output, cite sources, and record reusable insights into durable memory (`store_memory`).

## Standard Output Format

```text
AI Coding Agent Brief — [Date]

Claude Code
- Strong repository-level workflow
- Mature tool ecosystem

Codex
- Strong autonomous coding/reasoning
- Good sandboxed execution

KendaliAI / Hermes
- Persistent memory (facts + sessions)
- Procedural Skills (procedural memory)
- Messaging gateways (Telegram + Web)
- Deterministic cron & SRE automation
- Multi-agent specialist team mode

Key Conclusion:
[Concise, high-signal architectural takeaway]
```

From Haslab-dev/KendaliAI, MIT.

Signals

Stars: 5
Forks: 1
Open issues: 0
Last commit (this folder): Sep 14, 2026 (1 month ago)
Last release: Jul 2, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/Haslab-dev/KendaliAI
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from Haslab-dev

Cite this page

Tech & AI Research Agent skill. Agent Mart. https://agentmart.dev/skills/haslab-dev-tech-ai-research-agent (last updated 2026-10-24)