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.
61 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.
New Skill Scaffolder
Create a new Claude Code skill correctly: right mechanism, valid name and folder, a triggering description, and a smoke test.
Skill Library Lint and Overlap Report
Lint every skill in a repo at once: frontmatter, name-folder match, weak descriptions, overlapping triggers, broken refs, plus a CI script.
Autonomous /goal Prompt Builder
Turn rough ideas into one paste-ready /goal prompt with clear scope, constraints, acceptance checks, and autonomy rules.
Autonomous Creative Build Goal Prompts
Turn a rough game, 3D site, or video idea into one build prompt with scoped autonomy, acceptance tests, and delivery criteria.
Self-Verifying Agent Loop: Plan, Check, Retry, Close
Turns a goal into a task plan with machine-run checks, executes with retry caps, escalates, and refuses to close until verified.
Skill Test Runner (Trigger and A/B)
Test a skill in fresh sessions: ready-to-run prompts, commands, and rubric for trigger recall, false triggers, and blind A/B.
Chief AI Officer Plan Review
Evidence-first review of one AI plan: eval gaps, cost per successful task, model and vendor risk, prompt injection, and EU AI Act screen.
Claude Code Subagent Roster Designer
Design a small team of Claude Code subagents: when to split, .claude/agents files, tools, model tiers, and a routing test.
Multi-Agent Workflow Design with Handoff Contracts
Get a buildable agent workflow spec: split verdict, pattern, typed handoff contracts, failure rules, model tiers, and a cost budget.
Claude Power-User Coaching: One Tip Per Turn
Spots the Claude features and prompt habits you're missing in your actual work and coaches one concrete, copyable fix at a time.
Overnight Skill Optimizer (Eval-Driven)
Improve a skill overnight against your evals: one change per step, held-out set, noise-aware keep or revert, locked evals, hard caps.
LLM Call Pattern Selector
Pick the call architecture for an LLM feature: single call, chain, or router, output enforcement, cache layout, and injection handling.
Wiki Decision Log
Keep an append-only, greppable log and dated decision records, and answer why a decision was made or what changed since.
Wiki Structure Linter
Script-backed structure check for a markdown wiki: broken links and anchors, orphans, name clashes, index drift, bad frontmatter.
Wiki Contradiction and Staleness Audit
Find contradictions, superseded and stale claims, and uncited statements in a wiki, with quoted evidence and a fix for each.
Overnight Ralph Loop Runner
Run a Ralph loop overnight safely: sandbox, branch checkpoints, iteration, time, and spend caps, no pushes, and a morning review.
Bulk Wiki Import
Migrate a Confluence, Notion, help-center, or PDF corpus into a markdown wiki in resumable, deduplicated batches.
Cross-Session Agent Memory with Hybrid Retrieval
Build or fix automatic coding-agent memory: hook capture, typed memory units, vector + keyword + graph retrieval, budgeted injection.
LLM API Cost Reduction: Caching, Routing, Token Budgets
Breaks your LLM bill down per call site, then ranks fixes like output trimming, caching, batch, and routing by savings and risk.
Claude Skill Build and Launch
Turn an idea into a complete Claude skill with scoped triggers, acceptance tests, installation steps, and an agent launch plan.
Agent Rule Memory and Correction Log
Make a long-running agent keep the rules you teach it: capture corrections instantly, reload past compaction, and test each rule.
Claude Code Session Handoff
Write a verified handoff so a fresh session, subagent, or teammate can continue coding work cold: state, dead ends, next step.
Multi-Model Second Opinion Council
Get blind second opinions from Gemini, GPT, or any OpenRouter model, then synthesize one answer that states what changed and why.
Installed Skills Environment Check
Find why installed skills fail on this machine: missing CLIs, unset env vars, disconnected MCP servers, script permissions, name clashes.
Multi-Skill Slash Command Workflows
Build one Claude Code slash command that chains installed skills with checked handoffs, context isolation, and safe restarts.
Supermemory Cross-Session Recall
Store, retrieve, and correct project facts and preferences through Supermemory with scoped recall and verified writes.
Skill Failure-to-Fix Loop
Turn a skill's real-world failure into a regression test, find the root cause, patch the smallest fix, and re-run until all cases pass.
Cross-Agent Shared Fix Map
Set up and run a shared fix map so every Claude agent checks verified past solutions before debugging and logs new ones after.
Production Prompt Versioning and Eval Gates
Version, eval-gate, A/B test, and roll back production prompts so a wording or model change never silently breaks your AI feature.
Knowledge and Skill Improvement Loop
Turn stale knowledge, weak skills, session mistakes, and personal feedback into traceable updates with regression checks.
Critic Subagent Review Gate
Add an independent critic subagent that reviews copy, research, or code with severity-rated fix notes and a capped revision gate.
Fable 5 Multi-Agent Build Orchestration
Run multi-step builds with Fable 5 sub-agents using contract-first briefs, file ownership, model routing, and verified merges.
Wiki Source Ingest
Fold one article, paper, or transcript into your wiki: cited source page, surgical page updates, conflicts kept, index and log updated.
SOP to Claude Skill Conversion
Turn an SOP or process transcript into a self-contained Claude skill with scoped triggers, traceable rules, and runnable test cases.
All ai & agents skills
- Agent Architecture, Tool Schemas, and Run-Log Diagnosis
- Fresh-Context Task Orchestrator
- Scheduled Agent Jobs and Heartbeats
- Prompt Template Builder
- Tool-Output Compactor for Claude Code
- Claude Skill Reviewer
- AgentHub Board: Claims, Handoffs, Conflict Checks
- Reusable Task Prompt Builder
- Wiki Query with Citations
- Claude Code Project Memory and Handoffs
- LLM Wiki Initializer
- Human-Sounding Replies for Hard Conversations
- Prompt Optimization with Task Evals
- Rough Ask to Tool-Ready Prompt
- Agent Skill Authoring and Testing
- Long-Session Agent Context Engineering
- Multi-Agent Coordination Protocol
- Agent Loop Pattern Library
- Custom Skill Authoring and Test Loop
- Planner-Worker Model Tiering
- Session Learning with Held-Out Validation
- Role Interview and Master Prompt Builder
- Wiki Librarian: Merge, Split, Rename
- Lean SKILL.md Refactor
- Sonar Web Search for Agents (via OpenRouter)
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.