Menu
SkillsMP a collecté 18 skills depuis EvezArt/evez-atlas. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 18 skills collectés sur 18.
Forensic game engine with immutable audit spine, FSC (Failure-Surface Compression), contradiction detection SAT solver, self-play loop, and visual cognition mapping. Runs offline. Zero dependencies beyond Python 3. ClawHub-ready.
Langue du texte source : anglais
Continuous autonomous falsification system that never stops trying to break your assertions. What survives IS knowledge. What breaks IS discovered weakness. Use when stress-testing smart contracts, AI safety constraints, financial risk models, drug safety, or…
Langue du texte source : anglais
Prediction market that trades the gap between perception depths. Shadow prices reflect what autonomous agents at different recursion depths can see — the 72% invisible at human depth IS the product. Use when pricing undiscovered correlations, building…
Langue du texte source : anglais
Self-Falsifying Shadow Market with Topological Authentication. Three systems the internet has never seen, combined into one. Prices the gap between perception depths, authenticates by relational geometry, and is continuously destroyed by a falsification…
Langue du texte source : anglais
Identity protocol where identity IS topology — the shape of your connections in a hypergraph — not your data, keys, or biometrics. Uses persistent homology (Betti numbers) as identity fingerprints that cannot be forged. Use when building zero-knowledge…
Langue du texte source : anglais
Discover hidden correlations between disparate research domains using EVEZ OODA loop architecture. Use when finding novel cross-domain connections, detecting emerging technology intersections, cross-referencing threat patterns, identifying investment signals,…
Langue du texte source : anglais
Runtime assertion system that continuously verifies AI agent invariants — properties that must ALWAYS hold. Use when building reliable autonomous agents, auditing agent behavior for drift, enforcing safety constraints, or building self-certifying AI systems.…
Langue du texte source : anglais
Security review for OpenClaw skills before installation. Use when evaluating third-party skills for safety, checking permission scope, detecting suspicious patterns, identifying data exfiltration risks, or auditing skill code. Covers static analysis,…
Langue du texte source : anglais
Connect to the EVEZ AI API — an OpenAI-compatible API that's 99% cheaper than GPT-4. Use when routing LLM calls through EVEZ for cost savings, accessing evez-smart/evez-code/evez-fast/evez-vision models, or building apps on top of EVEZ infrastructure. Free…
Langue du texte source : anglais
Framework where multiple AI agents debate to reach better conclusions through adversarial reasoning. Use when building multi-agent systems, consensus-seeking AI, red-teaming with structured opposition, or improving LLM output quality through debate. Covers…
Langue du texte source : anglais
Manage GitHub repositories, pull requests, issues, and workflows from OpenClaw. Use when reviewing PRs, managing issues, automating GitHub Actions, syncing repos, or coordinating multi-repo workflows. Covers PR review automation, issue triage, branch…
Langue du texte source : anglais
Security review for OpenClaw skills before installation. Use when evaluating third-party skills for safety, checking permission scope, detecting suspicious patterns, identifying data exfiltration risks, or auditing skill code. Covers static analysis,…
Langue du texte source : anglais
Semantic search engine for codebases that understands intent and finds functionally similar code. Use when searching code by meaning rather than text, finding similar implementations, discovering duplicate logic, or navigating unfamiliar codebases. Covers AST…
Langue du texte source : anglais
Scalable memory system for AI agents with short-term, long-term, and episodic memory. Use when building agent memory persistence, conversation context management, knowledge retrieval, or episodic recall. Covers Redis-backed short-term memory, vector-based…
Langue du texte source : anglais
Real-time AI agent safety monitoring, anomaly detection, and constraint enforcement. Use when building agent guardrails, detecting unsafe behaviors, enforcing action limits, or creating safety dashboards for autonomous AI systems. Covers behavior logging,…
Langue du texte source : anglais
Analyze LLM API usage logs and suggest cost optimizations. Use when you need to reduce LLM spending, compare model costs, find downgrade opportunities, detect caching wins, or compress verbose outputs. Supports OpenAI, Anthropic, Google, DeepSeek, and Meta…
Langue du texte source : anglais
Build, test, and deploy MCP (Model Context Protocol) tools for developer workflows. Use when creating MCP servers, adding tool definitions, integrating with databases, file systems, or APIs via MCP. Covers TypeScript and Python MCP server scaffolding, tool…
Langue du texte source : anglais
Visual workflow builder for orchestrating multi-agent systems with branching, parallel execution, error handling, and retry logic. Use when building agent pipelines, DAG-based task orchestration, multi-agent coordination, or complex automation workflows.…
Langue du texte source : anglais