Results for “lernplan”

Create implementation-ready engineering plans for WelineFramework. Use in Plan mode, or when the user requests detailed requirements, code modification points, task cards, test cases, acceptance criteria, risk and rollback design, or a handoff package for execution-oriented AI agents.

Create lesson plans with objectives, activities, and assessments. TRIGGERS - Use when user needs help with lesson-plan related tasks.

Design reading plans with retention strategies. TRIGGERS - Use when user needs help with reading-plan related tasks.

Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.

Alias for $plan --consensus

Create lesson plans with objectives, activities, and assessments. TRIGGERS - Use when user needs help with lesson-plan related tasks.

Alias for $plan --consensus

Build a personalized study plan with spaced-repetition scheduling toward a deadline and goal.

Audit a codebase for silent failures, swallowed exceptions, and observability gaps across Sentry and Langfuse, then produce a phased fix plan. Use when the user says "errors aren't showing in Sentry", "things fail silently", "empty catch blocks", "add error handling", "check my Langfuse tracing", or is hardening.

Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.

Create a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature, task, or multi-step implementation — especially before executing with do.

Redesign a blocked topic sequence into an interleaved plan with mixed practice across related topics. Use when planning units, homework schedules, or revision programmes.

Produces a one-page lean canvas across nine interlocking blocks (problem, customer, UVP, solution, channels, revenue, cost, metrics, unfair advantage) with optional inline HTML and SVG visual rendering. Use when framing a new product thesis, stress-testing an existing strategy, comparing strategic options side-by-side, or aligning a team on business-model assumptions. Works as a strategic hub that cross-links to deeper PM skills without duplicating them.

Creates actionable work plans through interactive interviews, direct planning, consensus loops, or plan review, with quality gates and optional multi-agent deliberation.

Full autonomous research workflow — brainstorm, plan, implement, review, and document

Large Language Model development, training, fine-tuning, and deployment best practices.

从 PAPER_PLAN 起草 LaTeX 论文：逐 section 从 wiki 取材撰写 + 生成 figures/tables + BibTeX 验证 + de-AI polish

Turn a theory-first research idea into a proof-oriented research plan. Use after idea-creator-analysis, or when the user asks for theorem targets, assumptions, proof obligations, impossibility routes, analysis validation, or a non-experimental plan.

Run Karpathy-style autonomous ML search on a real training repo: choose the right mode (setup, program.md, bounded loop, results interpretation, or constrained-hardware adaptation), preserve the immutable prepare.py / 300-second / val_bpb contract, and route prompt/skill eval work away to LangSmith, Promptfoo, Braintrust, or skill-autoresearch.

Create structured plans for multi-step tasks -- software features, research workflows, events, study plans, or any goal that benefits from breakdown. Also deepens existing plans with interactive sub-agent review. Use when the user says 'plan this', 'create a plan', 'how should we build', 'break this down', or when a brainstorm doc is ready for planning. Use 'deepen the plan' or 'deepening pass' for the deepening flow. For exploratory requests, prefer ce-brainstorm first.

Strategic planning with optional interview workflow

Continues deep iteration on an existing planning document: detects explicit file-loading intent, provides status summaries, and supports on-demand in-depth exploration.

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

Guides a structured planning pipeline for coding tasks, from scoping and research to plan creation, review, and handoff.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

LaCLIP: Improving CLIP Training with Language Rewrites

Strategic planning with optional interview workflow

Design grading plans. TRIGGERS - Use when user needs help with grading-plan related tasks.

Iterates through pending development plans in .cursor/plans, implementing tasks, running self-tests, reviewing code, committing locally, and moving completed plans to docs/plans/done.

Eng manager-mode plan review. (gstack)

Stop vibe-coding with a spec → plan → TDD loop before writing a line. Use for any non-trivial feature, refactor, or bug fix on web, React Native, or Capacitor. Use when asked to "build", "implement", "add a feature", "this keeps breaking", "do it properly", or when LLM output keeps being wrong.

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution

Local RAG indexing with 97% storage reduction via anchor-based lazy recomputation. Graph-based selective embedding storage for memory-efficient semantic code search.

Scaling Instruction-Finetuned Language Models

Design lean startup experiments (pretotypes) for a new product by creating XYZ hypotheses and suggesting low-effort validation methods like landing pages, explainer videos, and pre-orders.