Plugin Claude Code
Marketplace for superpowers-ml: Superpowers core skills plus a conservative ML-research layer.
8 8d ago A
tokens not measured
original MIT
Plugin Claude Code
Superpowers core skills plus a conservative ML-research layer (verification rungs, experiment design, result review). Fork of obra/superpowers.
8 8d ago A
tokens not measured
original MIT
Instructions file CodexOpenCode
Instructions for pengzhangzhi/superpowers-ml, a project described as: Skills that make your AI agent do ML research like a skeptical scientist, not a hype machine.
8 8d ago A 4 tokens
copy · 100% MIT
Instructions file
Instructions for pengzhangzhi/superpowers-ml, covering superpowers-ml (fork), superpowers — contributor guidelines, if you are an ai agent, pull request requirements and what we will not accept.
8 8d ago A 1,882 tokens
copy · 91% MIT
Instructions file Gemini CLI
Instructions for pengzhangzhi/superpowers-ml, a project described as: Skills that make your AI agent do ML research like a skeptical scientist, not a hype machine.
8 8d ago A 27 tokens
copy · 100% MIT
SessionStart
06Hook
Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From pengzhangzhi/superpowers-ml.
8 8d ago A
tokens not measured
copy · 86% MIT
Skill Claude CodeCodex
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
8 8d ago A 37 tokens
original MIT
Skill Claude CodeCodex
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
8 8d ago A 26 tokens
copy · 91% MIT
Skill Claude CodeCodex
Use when you have a written implementation plan to execute in a separate session with review checkpoints.
8 8d ago A 22 tokens
copy · 88% MIT
Skill Claude CodeCodex
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.
8 8d ago A 44 tokens
copy · 94% MIT
Skill Claude CodeCodex
Use when turning a rough ML idea into a runnable experiment - define the experiment card (question, hypothesis, baseline, primary metric, budget, cheapest verification rung) before writing training code.
8 8d ago A 42 tokens
original MIT
Skill Claude CodeCodex
Use when planning how to verify an ML experiment cheaply before expensive runs - design the R0-R7 ladder from local sanity checks to full study, with promotion/stop criteria.
8 8d ago A 40 tokens
original MIT
Skill Claude CodeCodex
Use when concluding an ML experiment - produce a sober conclusion that separates confirmed results from exploratory observations and states the highest verified rung.
8 8d ago A 29 tokens
original MIT
Skill Claude CodeCodex
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
8 8d ago A 38 tokens
copy · 94% MIT
Skill Claude CodeCodex
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
8 8d ago A 22 tokens
copy · 77% MIT
Skill Claude CodeCodex
Use when executing implementation plans with independent tasks in the current session.
8 8d ago A 17 tokens
copy · 97% MIT
Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
8 8d ago A 21 tokens
copy · 84% MIT
Skill Claude CodeCodex
Use when implementing any feature or bugfix, before writing implementation code.
8 8d ago A 17 tokens
copy · 89% MIT
Skill Claude CodeCodex
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.
8 8d ago A 36 tokens
copy · 91% MIT
Skill Claude CodeCodex
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions.
8 8d ago A 29 tokens
copy · 91% MIT
Skill Claude CodeCodex
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
8 8d ago A 43 tokens
original MIT
Skill Claude CodeCodex
Use when you have a spec or requirements for a multi-step task, before touching code.
8 8d ago A 21 tokens
original MIT
Skill Claude CodeCodex
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
8 8d ago A 20 tokens
copy · 80% MIT