AI & Agents skills for AI agents
Skills for building and steering AI agents: prompting, orchestration, memory, skill engineering, and starter kits for learning to work with AI.
115 skills · every one included with AgentVolt Pro
AI Starter Toolkit
A free, curated starting point — the essential prompts and habits to get real value from AI on day one.
ChatGPT Mastery Kit
The fastest way to go from casual ChatGPT user to power user, with 50+ proven prompt patterns.
Skill Status Report
Scan every skill in a project and report which pass validation, which are stale, and which lack required metadata.
Skills Scaffolder
Scaffold a new skills directory — folder structure, metadata, a baseline validation pass — with the right conventions from day one.
Research Bundle
Run a multi-step research task as one pipeline: gather sources, extract findings, validate consistency, emit one structured bundle.
Workspace Admin
Administer a Cowork or Claude workspace — settings, access, configuration — with every change scoped and verified.
Skill Runner
Execute a named skill's run phase correctly: validate inputs, run the defined steps in order, and check outputs.
Tech Debt Paydown
Identify, prioritize, and pay down technical debt without turning every session into a rewrite.
ISO 42001 Specialist
Work through ISO/IEC 42001 AI management system requirements: clauses, controls, and documentation.
Staged Pipeline Runner
Run a task as discrete stages, each validated before the next begins, so failures surface where they were caused.
Backend Engineer
Backend work from requirements to a validated implementation, instead of jumping straight into code.
Claude Sub-Agent Roster Designer
Turn a single overloaded Claude agent into a routed team of specialized Sonnet-tier sub-agents supervised by an Opus-tier planner.
Finance Lead
Build the numbers, forecast runway under multiple scenarios, and evaluate spending decisions against them.
Content Strategist
Define the goal, map audience and channel, plan a topic cluster, and set a cadence a team can keep.
PRD Writer
Produces a product requirements document that gives engineering everything needed to scope and build a feature without repeated round-trips for missing context.
Self-Improving Skill Overnight Loop
Run an automated overnight research loop on a Claude skill: try a tweak, run binary assertions, keep or revert based on pass rate, and iterate.
Product Manager Workflow
Clarify the problem, size the opportunity, write the spec, and sequence the work so engineering has what it needs.
Growth Marketer
Diagnose which funnel stage is the real constraint, then build and prioritize an experiment backlog.
Wiki Decision Log
Keep a dated, cross-linked log of decisions and changes so context survives between sessions and contributors.
Prompt Engineering Patterns
Applies proven prompt structuring patterns when Claude is building LLM-powered features.
Interactive Learning Artifact Explainer
Ask Claude to teach any concept visually and it builds an interactive artifact with clickable next steps and animations that walks you through the topic.
Feature Flag Cleanup
Find stale feature flags, determine which side won, and safely remove the dead code path.
Customer Success Growth Strategist
Turn customer success signals into growth actions — expansion, renewal, advocacy — instead of ad hoc outreach.
CTO Advisor Workflow
CTO-level reasoning: architecture tradeoffs, build versus buy, and tech debt against feature work.
Wiki Linter
Lint an entire wiki for broken links, orphaned pages, and inconsistent formatting.
Support Wiki Linter
Lint a support wiki for the drift that accumulates over hundreds of articles: broken links, stale screenshots, inconsistencies.
Customer Success Financial Analyst
Turn subscription and usage data into the financial metrics that predict renewal risk and expansion opportunity.
Ralph Loop Autonomous Overnight Runner
Wire the Claude Code CLI mode (-p flag) into the Ralph loop plugin so a while-loop keeps feeding the same prompt with updated files until the task is done.
Chaos Experiment
Turn a vague "test resilience" request into one well-scoped chaos experiment with a hypothesis, blast radius, and abort plan.
Support Wiki Ingestor
Convert a sprawling support wiki into clean, chunked, tagged documents an agent can retrieve from.
Chaos Engineering for Skills
Inject failure conditions into skills and agent workflows deliberately to find where they break first.
Fullstack Engineer
Carry a task from requirement through frontend, backend, and deployment with built-in verification at each layer.
Agent Durable Memory and Correction Loop
Add a persistent memory file and a self-correction log so a Claude agent stops re-forgetting your rules every week.
Arquiteto de Empresa
Map a business's organization, processes, and systems into one structured document, validated for gaps.
Demand Gen Specialist
Demand generation as a discipline: campaign planning by funnel stage and lead scoring grounded in conversion data.
Agile Product Owner
Groom a backlog into well-formed stories, scope sprints realistically, and keep acceptance criteria tight.
All ai & agents skills
- Compliance OS
- Senior Engineer
- Fullstack Code Review
- Council Skill
- Session Handoff
- Kubernetes Operator Builder
- VPS Autonomous Claude Deploy
- AEO Specialist Subagent
- SEO Auditor
- Self-Evolving Codebase Memory
- General Counsel Advisor
- Skill Status Check
- Frontend Engineer
- Solo Founder Operator
- AEO Workflow
- VP of Engineering Advisor
- Cowork Plugin Management (Build Your Own)
- Recursive Skill Failure-Fix Loop
- Startup CTO
- Engineering Interview Loop
- UX Researcher
- RICE Prioritizer
- Chief Data Officer Advisory Workflow
- Critique Sub-Agent Reviewer
- Chief AI Officer Advisory Workflow
- Wiki Ingester
- Support Engineering Lead
- SOP to Claude Skill Generator
- Feature Flags Architect
- TDD Loop
- CEO Advisor Workflow
- Sprint Planner
- Test Case Generator
- Codebase to PRD
- Fresh-Context Sub-Agent Orchestrator
- Customer Success Project Manager
- OKR Writer
- Plugin Audit
- Prompt Engineer
- Agent Cron and Heartbeat Scheduler
- SLO Architect for Skills
- Sandboxed Tool-Output Compactor
- Changelog Generator
- Accessibility Audit
- SLO Design
- Skill Reviewer
- EU AI Act Specialist
- Wiki Query
- Operator Audit
- Backend Code Review
- User Story Writer
- Frontend Code Review
- Cross-Session Project Memory
- Chief Customer Officer Advisory Workflow
- Customer Success Webinar
- Customer Success Content Creator
- Sprint Health
- Sprint Retro
- Product Strategist
- Wiki Initializer
- Obsidian Emerge Idea Surfacer
- Financial Health
- Product Manager
- Pre-Flight Code Check
- Product Analyst
- Quality & Regulatory Review
- Focused Fix
- Webinar Marketer
- Google Workspace Workflow
- Persona Builder
- Competitive Matrix
- Project Health
- Loop Library
- Skill Creator (Build Your Own Skill)
- Frugal Fable Planner-Worker Orchestrator
- Structured Code Reviewer
- Wiki Librarian
- SaaS Health Check
- Sonar-via-OpenRouter Search Upgrade
Browse other categories
Questions
What exactly is a skill?+
A packaged set of instructions your AI follows — a sales-call framework, an audit checklist, a content system. You install it once and your agent knows how to run that workflow.
Do I need to know how to code?+
No. Installing a skill is unzipping a folder into your agent’s skills directory, or connecting the AgentVolt MCP once and letting your agent pull skills itself.
Which AI tools does this work with?+
Every skill uses the open SKILL.md standard, so the same file works in Claude, ChatGPT, Cursor, Codex, Gemini, and 20+ other agents. No per-tool versions.
Is it really every skill?+
Yes — one subscription unlocks the entire library, including new skills as experts publish them. There is no per-skill checkout and no usage limit.
Can I cancel?+
Anytime, from your billing dashboard. You keep any skill files you have already downloaded — they are plain files on your machine, not licensed software that phones home.
Are the skills safe to install?+
Every skill is automatically scanned for dangerous commands, hardcoded secrets, obfuscated code, and suspicious network access, then reviewed before it goes live.