Results for “metaskill”

Create or update Cursor agent skills (SKILL.md). Use when authoring a new skill, updating an existing skill, or asking about SKILL.md structure and best practices.

Turn a weak/cheap "Flash" model into a "Pro" performer by wrapping HKUDS UpSkill — captures agent session failures, has a strong Teacher model analyze them and draft a skill, then validates it against the weak Student model in a closed Ralph Loop (up to 3 rounds) before storing it for automatic reuse. Use when the user wants to install UpSkill, run `/upskill-init`, `/upskill-configure`, `/upskill-build`, `/upskill-run`, `/upskill-list`, `/upskill-status`, `/upskill-mode`, `/upskill-model`, `/upskill-remove`, or `/upskill-uninstall`, wants a cheap model to perform closer to a Pro model without switching, or wants a good session (success or failure) distilled into a validated skill. Triggers on: upskill, up-skill, flash to pro, teacher student distillation, ralph loop skill validation, distill agent failures into skills. Routes skill-quality ratcheting to `skill-autoresearch`, scaffolding to `write-a-skill`, and spec-compliance rewrites to `skill-standardization`.

当用户想测试或复盘某个 skill 的实际执行效果时使用——如“测一下这个 skill”“看看 agent 是否按 skill 执行”“生成 skill 覆盖率或溯源报告”。在隔离沙箱中发起一次 headless 盲测，逐步骤溯源并产出中文复盘报告。不要用于编写新 skill、调试业务代码、代码审查，或复盘当前会话已经发生的执行。

Manages personal local Agent Skill files by detecting reusable material, searching for similar skills, and creating or updating SKILL.md folders after user approval.

Train unsupervised machine learning models on genomic interval data from BED files, including region embeddings, single-cell ATAC-seq analysis, and consensus peak building.

Guides machine learning development with experiment tracking, hyperparameter optimization, model registry, and MLOps pipeline integration.

Analyze recent screen activity via a local screenpipe daemon, detect repeated research workflows, and draft new skills or composition recipes for uncovered patterns.

Score a clinical ASR manifest against a chosen NIM, produce a five-section KER leaderboard, and route the user via a post-eval decision tree.

Scaffolds new agent skills conforming to the Agent Skills specification and dotnet/skills repository conventions, generating SKILL.md files with proper frontmatter and directory structures.

Automates the full lifecycle of agent skills: extracts reusable constraints from user feedback, merges preferences with version bumps, and retrieves relevant skills for new tasks.

Post-train LLMs with reinforcement learning using the slime framework, which integrates Megatron-LM for training and SGLang for rollout generation.

Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.