lambdasec-skills
A collection of five Agent Skills that integrate open-source security and ML tools: Frame for code vulnerability scanning and fixing, adaptive-classifier for dynamic text classification, PTS for finding pivotal tokens that influence model behavior, mlx-optiq for running quantized models on Apple Silicon, and rsi-skill for measuring and optimizing prompts. The skills work across multiple agent platforms (Claude Code, Cursor, Copilot, and others) in standard Markdown format with no bundled code except rsi.py, which hill-climbs prompts against your chosen model endpoint.
Install
What it's made of
5 skills
- Commands
- 0
- Agents
- 0
- Skills
- 5
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- OptiQ Cloud
- External tools
- none
- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (lambdasec).