← All skill packs

AI Agent Workflow Collection

Skill pack
55 skills0 selected
notqueSkills in this pack

A/B test agent variants for quality and token cost.

English

Proactive architecture improvement: find shallow modules, propose deepening opportunities, design conversation.

English

Cobalt Core infrastructure knowledge: KVM exporters, hypervisor tooling, OpenStack compute.

English

Review and fix temporal references in code comments.

English

Audit and create cron jobs with reliability and safety.

English

Audit cron scripts for reliability and safety.

English

C-suite executive decision support: strategy, technology, growth, competitive intelligence, project evaluation.

English

Audit CVE/vulnerability source coverage for a technology stack. Maps each component (container, library, base image, runtime) to authoritative CVE feeds, flags gaps, and produces audit-ready reports. Generic: works for any service or stack.

English

Detect documentation drift against filesystem state.

English

Deterministic API endpoint validation with pass/fail reporting.

English

Enterprise search engineering — relevance tuning, query understanding, index management, search quality measurement, ranking optimization, schema design. Use when building search features, debugging relevance, tuning ranking, designing indices, or measuring search quality.

English

Query and display structured decision traces from routing, agent selection, and skill execution.

English

Feature lifecycle: design, plan, implement, validate, release. Phase-gated workflow.

English

Comprehensive 3-wave review of all repo source files, producing a prioritized issue backlog.

English

Deterministic palette/matrix pixel art (not AI). Use for procedural tile art, color-quantized output, matrix sprites.

English

Game lifecycle orchestrator: scaffold, assets, audio, QA, deploy.

English

AI sprite generation: portraits, idle loops, animated sheets via Codex/Nano Banana. Use for generated character art.

English

Generate project-specific CLAUDE.md from repo analysis.

English

Triage GitHub notifications and report actions needed.

English

Generate headless Claude Code cron jobs with safety.

English

Facility operations, bed management, capacity planning, staffing models, patient flow optimisation, and operational KPIs for healthcare organisations.

English

Generate rich self-contained HTML artifacts instead of markdown. Auto-detects artifact shape (spec, code-review, prototype, report, editor, data-viz, diagram, deck) and loads shape-specific patterns. Bundles Birchline design system with 4 theme presets. Use for "make HTML", "as HTML", "HTML artifact", or auto-injected by router when output benefits from rich visualization.

English

Validate content framing on joy-grievance spectrum.

English

Kubernetes debugging for pod failures and networking.

English

Includes Agent Comparison, Architecture Deepening, Cobalt Core, and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

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

Pack stats

Skills55CategorygeneralStars0

What’s included

Agent Comparison

A/B test agent variants for quality and token cost.

Architecture Deepening

Proactive architecture improvement: find shallow modules, propose deepening opportunities, design conversation.

Cobalt Core

Cobalt Core infrastructure knowledge: KVM exporters, hypervisor tooling, OpenStack compute.

Comment Quality

Review and fix temporal references in code comments.

Cron Automation

Audit and create cron jobs with reliability and safety.

Cron Job Auditor

Audit cron scripts for reliability and safety.

Csuite

C-suite executive decision support: strategy, technology, growth, competitive intelligence, project evaluation.

Cve Source Check

Audit CVE/vulnerability source coverage for a technology stack. Maps each component (container, library, base image, runtime) to authoritative CVE feeds, flags gaps, and produces audit-ready reports. Generic: works for any service or stack.

Docs Sync Checker

Detect documentation drift against filesystem state.

Endpoint Validator

Deterministic API endpoint validation with pass/fail reporting.

Enterprise Search

Enterprise search engineering — relevance tuning, query understanding, index management, search quality measurement, ranking optimization, schema design. Use when building search features, debugging relevance, tuning ranking, designing indices, or measuring search quality.

Explanation Traces

Query and display structured decision traces from routing, agent selection, and skill execution.

Feature Lifecycle

Feature lifecycle: design, plan, implement, validate, release. Phase-gated workflow.

Full Repo Review

Comprehensive 3-wave review of all repo source files, producing a prioritized issue backlog.

Game Asset Generator

Deterministic palette/matrix pixel art (not AI). Use for procedural tile art, color-quantized output, matrix sprites.

Game Pipeline

Game lifecycle orchestrator: scaffold, assets, audio, QA, deploy.

Game Sprite Pipeline

AI sprite generation: portraits, idle loops, animated sheets via Codex/Nano Banana. Use for generated character art.

Generate Claudemd

Generate project-specific CLAUDE.md from repo analysis.

GitHub Notification Triage

Triage GitHub notifications and report actions needed.

Headless Cron Creator

Generate headless Claude Code cron jobs with safety.

Healthcare Operations

Facility operations, bed management, capacity planning, staffing models, patient flow optimisation, and operational KPIs for healthcare organisations.

HTML Artifact

Generate rich self-contained HTML artifacts instead of markdown. Auto-detects artifact shape (spec, code-review, prototype, report, editor, data-viz, diagram, deck) and loads shape-specific patterns. Bundles Birchline design system with 4 theme presets. Use for "make HTML", "as HTML", "HTML artifact", or auto-injected by router when output benefits from rich visualization.

Joy Check

Validate content framing on joy-grievance spectrum.

Kubernetes Debugging

Kubernetes debugging for pod failures and networking.

Showing 24 of 55 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 Agent Comparison 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.
AI Agent Workflow Collection | Agent Skills Atlas