← All skill packs

AI Agent Workflow Collection

Skill pack
57 skills0 selected
3dcom2711Skills in this pack

Show available THRUNT threat hunting commands and artifact…

English

Map available telemetry, query surfaces, tenants, retention windows, and investigation blind…

English

Initialize a threat hunting case from a signal, detection, intel lead, or analyst…

English

Initialize a threat hunting program with an environment map, tool inventory, huntmap, and empty execution…

English

Create phase plans for a threat hunt with exact telemetry tasks, receipts, and query…

English

Publish a hunt as a case report, escalation, detection promotion, or leadership…

English

Execute a hunt phase with parallel telemetry work, query logging, receipt generation, and optional wave…

English

Turn a signal into testable hunt hypotheses, scope, datasets, and success…

English

Validate hunt conclusions against receipts, contradictory evidence, and success…

English

Add an idea to the backlog parking lot (999.x…

English

Add phase to end of current milestone in…

English

Generate tests for a completed phase based on Evidence Review criteria and…

English

Capture idea or task as todo from current conversation…

English

Cross-phase audit of all outstanding Evidence Review and findings validation…

English

Audit milestone completion against original intent before…

English

Run all remaining phases autonomously — discuss→plan→execute per…

English

Archive accumulated phase directories from completed…

English

Archive completed milestone and prepare for next…

English

Systematic debugging with persistent state across context…

English

Route freeform text to the right hunt or THRUNT command…

English

Execute a trivial task inline — no subagents, no planning…

English

Post-mortem investigation for failed THRUNT workflows — analyzes git history, artifacts, and state to diagnose what went…

English

Diagnose planning directory health and optionally repair…

English

Show available THRUNT commands and usage…

English

Includes Hunt Map Environment, Hunt New Case, Hunt New Program, and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Pack stats

Skills57CategorygeneralStars0

What’s included

Hunt Help

Show available THRUNT threat hunting commands and artifact layout

Hunt Map Environment

Map available telemetry, query surfaces, tenants, retention windows, and investigation blind spots

Hunt New Case

Initialize a threat hunting case from a signal, detection, intel lead, or analyst suspicion

Hunt New Program

Initialize a threat hunting program with an environment map, tool inventory, huntmap, and empty execution directories

Hunt Plan

Create phase plans for a threat hunt with exact telemetry tasks, receipts, and query outputs

Hunt Publish

Publish a hunt as a case report, escalation, detection promotion, or leadership summary

Hunt Run

Execute a hunt phase with parallel telemetry work, query logging, receipt generation, and optional wave targeting

Hunt Shape Hypothesis

Turn a signal into testable hunt hypotheses, scope, datasets, and success criteria

Hunt Validate Findings

Validate hunt conclusions against receipts, contradictory evidence, and success criteria

Thrunt Add Backlog

Add an idea to the backlog parking lot (999.x numbering)

Thrunt Add Phase

Add phase to end of current milestone in huntmap

Thrunt Add Tests

Generate tests for a completed phase based on Evidence Review criteria and implementation

Thrunt Add Todo

Capture idea or task as todo from current conversation context

Thrunt Audit Evidence

Cross-phase audit of all outstanding Evidence Review and findings validation items

Thrunt Audit Milestone

Audit milestone completion against original intent before archiving

Thrunt Autonomous

Run all remaining phases autonomously — discuss→plan→execute per phase

Thrunt Cleanup

Archive accumulated phase directories from completed milestones

Thrunt Complete Milestone

Archive completed milestone and prepare for next version

Thrunt Debug

Systematic debugging with persistent state across context resets

Thrunt Do

Route freeform text to the right hunt or THRUNT command automatically

Thrunt Fast

Execute a trivial task inline — no subagents, no planning overhead

Thrunt Forensics

Post-mortem investigation for failed THRUNT workflows — analyzes git history, artifacts, and state to diagnose what went wrong

Thrunt Health

Diagnose planning directory health and optionally repair issues

Thrunt Help

Show available THRUNT commands and usage guide

Showing 24 of 57 skills. Use the list’s page controls above to explore the rest.

Quick start

  1. Choose your skills. Select individual skills above, or choose the entire pack.
  2. Copy the install prompt. Use Copy install prompt above the list.
  3. Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.

Try it with your agent

After installation, start with a request like:

Example request
Use the Hunt Help skill to help with my task.
Ask me for the context you need before getting started.

Requirements & license

  • A coding agent that can access your project files and install skills.
  • Your agent checks each skill’s instructions, dependencies, and permissions during setup.
  • Reported license for the skills shown: MIT. The author’s terms apply.