research-agent
Compatibility entry point for the unified ShakerScan Hunt workflow.
Skill by andriyze
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/andriyze-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
Use cases: backend, research, productivity, agent-building
Reviews
Write a reviewNo 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/research-agent
What's inside
- Skill name
research-agent- Description
- Compatibility entry point for the unified ShakerScan Hunt workflow. Use only when an older prompt says Deep Hunt or autonomous research; follow the canonical hunt skill and /hunts API.
- License
- AGPL-3.0
- Instructions
- 15 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Deep Hunt compatibility Deep Hunt is now **Hunt**. Do not start the legacy `/agent/hunt/*` or `/research/*` planners. Read and follow [`../hunt/SKILL.md`](../hunt/SKILL.md) in full. Translate older wording as follows: - Deep Hunt, autonomous research, or autonomous hunt → one target-bound `POST /hunts` - planner turns → capability calls chosen by the current external coding agent - suspected findings → evidence-backed Hunt candidates - promotion → the registered deterministic candidate verifier The runtime remains the sole executor and authority boundary. Never expand target scope, approval, credentials, request collections, or budgets during the Hunt.
From andriyze/shakerscan, AGPL-3.0.
More from andriyze/shakerscan
- 0.570score
js-analyze
andriyze
Analyze JavaScript bundles, frontend routes, browser-captured APIs, libraries, and secrets for a ShakerScan target or completed scan.
SkillAFreshness: AClaude Code +9 - 0.570score
content-discovery
andriyze
Build target-specific content discovery seeds, path lists, and ShakerScan scan inputs from scan results, JS analysis, framework clues, and exposed docs.
SkillAFreshness: AClaude Code +9 - 0.570score
ai-security-session
andriyze
Interactive Testing through ShakerScan's `/session` API.
SkillAFreshness: AClaude Code +9 - 0.567score
shakerscan
andriyze
Operate ShakerScan.
SkillAFreshness: AClaude Code +9 - 0.565score
device-triage
andriyze
Explain or triage one registered connected device using existing ShakerScan evidence only.
SkillAFreshness: AClaude Code +9 - 0.565score
review-skills
andriyze
Review ShakerScan skills, commands, and subagents for broken references, invalid Claude Code configuration, prompt anti-patterns, missing hard gates, missing…
SkillAFreshness: AClaude Code +9 - 0.561score
hunt
andriyze
Drive ShakerScan Hunt for an authorized web, API, network, or connected-device target through the target-bound /hunts API.
SkillAFreshness: AClaude Code +9 - 0.561score
device-hunt
andriyze
Compatibility entry point for the unified ShakerScan Hunt workflow.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 5
- Last commit (this folder)
- Aug 25, 2026 (2 months ago)
- Last release
- Oct 18, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- AGPL-3.0
- Repository
- github.com/andriyze/shakerscan
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from andriyze
- 0.570score
js-analyze
andriyze
Analyze JavaScript bundles, frontend routes, browser-captured APIs, libraries, and secrets for a ShakerScan target or completed scan.
SkillAFreshness: AClaude Code +9 - 0.570score
content-discovery
andriyze
Build target-specific content discovery seeds, path lists, and ShakerScan scan inputs from scan results, JS analysis, framework clues, and exposed docs.
SkillAFreshness: AClaude Code +9 - 0.570score
ai-security-session
andriyze
Interactive Testing through ShakerScan's `/session` API.
SkillAFreshness: AClaude Code +9 - 0.567score
shakerscan
andriyze
Operate ShakerScan.
SkillAFreshness: AClaude Code +9 - 0.565score
device-triage
andriyze
Explain or triage one registered connected device using existing ShakerScan evidence only.
SkillAFreshness: AClaude Code +9 - 0.565score
review-skills
andriyze
Review ShakerScan skills, commands, and subagents for broken references, invalid Claude Code configuration, prompt anti-patterns, missing hard gates, missing…
SkillAFreshness: AClaude Code +9
Cite this page
research-agent skill. Agent Mart. https://agentmart.dev/skills/andriyze-research-agent (last updated 2026-10-24)