Claude Skills Supercharged — Development skill for Claude Code
A "supercharged" implementation of Claude Code Skills – using Haiku prompt analysis/critical skill scoring and skill auto-injection for friction-free, context-driven workflows.
How to install Claude Skills Supercharged
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open jefflester/claude-skills-supercharged and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Skills Supercharged does
[](https://github.com/jefflester/claude-skills-supercharged) [](https://www.typescriptlang.org/) [](LICENSE) [](https://code.claude.com/docs/en/skills)
Alternatives in Development
- Resume Work From A Handoff Document — You are tasked with resuming work from a handoff document through an interactive process 10k ★
- Crypto Research Haiku Command — Execute lightweight cryptocurrency research by calling only haiku versions of crypto analysis agents in parall 3.4k ★
- Maestro Learn — User-invoked learning toolkit — guided reading, investigation, pattern extraction, or second opinions 530 ★
README
Claude Skills Supercharged
[](https://github.com/jefflester/claude-skills-supercharged) [](https://www.typescriptlang.org/) [](LICENSE) [](https://code.claude.com/docs/en/skills)
**AI-powered skill auto-injection system for [Claude Code Skills](https://code.claude.com/docs/en/skills)**
**Stop manually invoking skills.** Let AI detect what you need and inject it automatically with 95%+ accuracy. The system analyzes your prompts using Claude Haiku 4.5, assigns confidence scores, and intelligently loads the right context—every time.
💡 **Credit:** Base reference architecture from [@diet103](https://github.com/diet103)'s [claude-code-infrastructure-showcase](https://github.com/diet103/claude-code-infrastructure-showcase)
📊 Performance at a Glance
| Metric | Value |
|---|---|
| ✅ Test Coverage | All tests passing |
| ⚡ Response Time | <10ms (cached) / ~200ms (first call) |
| 💰 Monthly Cost | $1-2 @ 100 prompts/day |
| 🎯 Accuracy | 95%+ skill detection rate |
🎯 Why This?
**The Problem:** Manually loading skills is tedious, error-prone, and breaks your flow. You forget which skills exist, waste time invoking them, and lose context between conversations.
**The Solution:** This system uses AI to automatically:
- 🔍 Analyze your prompt intent with Claude Haiku 4.5
- 📊 Score each skill's relevance (0.0-1.0 confidence)
- 🚀 Inject high-confidence skills (>0.65) into context automatically
- 💾 Cache results for 1 hour to reduce costs
- 🔗 Track loaded skills per session (no duplicates)
**Before:** "Let me manually load python-best-practices... wait, was it python-style? Let me check..."
**After:** Just say "help me write Python code" and the right skills load automatically. 🎉
📑 Table of Contents
...
Related Skills
Qimpl
Context-aware autonomous implementation session driven by a work file
Agent Relay Auto
A protocol-driven orchestration framework for reliable multi-agent collaboration, context handoff, and automat
Harvest
Harvest friction events from observation logs into typed instincts (env_issue, permission_block, wrong_approac
Plan Auto Context Enhanced
Create implementation plans with automatic context selection. Just describe what you want to build in natural
Cua Hunt
Hunt Computer-Use-Agent (CUA) prompt-injection surface — instructions planted in CUA-readable DOM channels (hi
Openapis
Free Claude API + free OpenAI API in one unified proxy. Drop-in compatible with Anthropic SDK, OpenAI SDK, Cla
Related Agents
Documenter
Documentation update agent for 3-Tier Documentation System. Auto-syncs CLAUDE.md, CONTEXT.md files, and docs/a
Fleet Implement Cheap
Bulk or low-stakes implementation on budget or free models: mechanical edits, boilerplate, and large repetitiv
Prompt Forager
Context-starved prompt forager for diversity injection. Receives ONE line (a purpose) and deliberately nothing