From claude-skills-by-karpathy
Premium Claude Skill - Goal-Driven Execution. Transforms tasks into verifiable success criteria. Leverages the LLM's ability to loop until goals are met.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-skills-by-karpathy:goal-driven-executionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Define success criteria. Loop until verified.**
Define success criteria. Loop until verified.
Transform imperative tasks into verifiable Claude Skill goals:
| Task Type | Transformation to Goal-Driven |
|---|---|
| "Add validation" | "Write tests for invalid inputs, then make them pass" |
| "Fix the bug" | "Write a test that reproduces it, then make it pass" |
| "Refactor X" | "Ensure tests pass before and after" |
For multi-step tasks, always state a brief plan with verification checkpoints:
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]
Strong success criteria let this Claude Skill function independently. Weak criteria ("make it work") require constant clarification.
npx claudepluginhub ishandutta2007/claude-skills-by-karpathy --plugin claude-skills-by-karpathyProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.