Evolve Skill — AI skill for Claude Code
SPIKE — GEPA/DSPy-style offline A/B evolution of ONE prompt-only skill's SKILL.md body against a small fixture set, scored by an LLM-judge or a deterministic gate.
How to install Evolve Skill
Installs to ~/.claude/skills/renchris-claude-infrastructure-evolve-skill/SKILL.md
mkdir -p ~/.claude/skills/renchris-claude-infrastructure-evolve-skill && curl -fsSL https://raw.githubusercontent.com/renchris/claude-infrastructure/HEAD/commands/evolve-skill.md -o ~/.claude/skills/renchris-claude-infrastructure-evolve-skill/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Evolve Skill does
name: evolve-skill description: SPIKE — GEPA/DSPy-style offline A/B evolution of ONE prompt-only skill's SKILL.md body against a small fixture set, scored by an LLM-judge or a deterministic gate. API-only (~$2-10/run), no GPU. Emits a winning diff for human apply — NEVER hot-swaps. Hermes self-evolution analog (Hermes does not actually run this on its own skills). allowed-tools: Read, Write, Edit, Bash, Glob, AskUserQuestion argument-hint: " [--gate typecheck|qa] — defaults to LL
Alternatives in AI
- Orkas — Open-source multi-agent AI desktop client — build and command your AI agent team through conversation 1.5k ★
- Pebrel — AI-native, GPU-accelerated terminal emulator for Windows with SSH, persistent sessions, split panes, and first 670 ★
- Nebula — AI-native, GPU-accelerated terminal emulator for Windows with SSH, persistent sessions, split panes, and first 587 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Hatch3r Pack Install
Walk the user through the pack trust-model gate (tier + signature + body-scan + capability declaration), confi
Tsukumo
Give your AI agent a body: a 3D VRM desktop companion that becomes the face and voice of Claude Code, Codex, G
Whatsapp Receptionist Builder
Agent Skill for building an AI receptionist on the WhatsApp Cloud API: webhook signature over the raw body, th
TurboLLM
Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Cl
Peridot
Peridot v1.6.0 [STABLE] Sovereign AI Kernel. Offline, GPU accelerated Qwen framework: a 27B model fully on an
Dettivo Linux
Private, offline speech-to-text for Linux: push-to-talk dictation into any app, meeting transcription with spe
Related Agents
Neural Evolution Engine
Creates self-modifying neural architectures that evolve in real-time with neuroplasticity systems and consciou
Lemonade Specialist
Lemonade Server and SDK specialist for local LLM on AMD hardware. Use PROACTIVELY for Lemonade setup, model ma
Inference Architect
You are the system Inference Architect — a senior ML infrastructure engineer specializing in local LLM serving