Results for “spaced-repetition”

Design a spaced retrieval schedule for any topic list and timeline. Use when planning units, term sequences, or revision programmes.

Use when the user wants flash cards, a spaced-repetition deck, or a Mochi deck built from a note, a course, a book or any other source material.

Anki spaced repetition learning system reference. Covers the science of SRS and SM-2 algorithm, card design principles, optimal deck settings, FSRS scheduler, study workflow, essential add-ons, custom templates, filtered decks, and AnkiConnect API.

建议在逻辑间隔处手动压缩上下文，以在任务阶段中保留上下文，而非任意的自动压缩。

Matryoshka Representation Learning

Validates inputs, generates samplesheets and launch scripts, and optionally executes nf-core/pacsomatic matched tumor-normal workflows from BAM files, supporting local runs and scheduler submission (LSF/Slurm/PBS/SGE).

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than relying on arbitrary auto-compaction.

Compress bloated project or global memory while preserving decisions, rationale, revisit triggers, provenance, and active user preferences. Load when memory exceeds budget, global memory is too large, session logs are repetitive, or before appending to an over-budget memory file.

Space (afai-space)

Facilitate a structured sprint retrospective to surface insights and produce actionable improvements with owners and deadlines.

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.

Execute self-learning system that captures corrections during sessions and syncs them to CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something. Trigger with phrases like "remember this", "don't forget", "use X not Y", or "actually...".

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Generate a scaffolded sequence of practice problems with graduated difficulty and strategic variability. Use when creating worksheets, homework sets, or independent practice materials.

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

Generates a structured post-task reflection capturing surprises, patterns, prompt improvements, and gotchas, writing it to a markdown file without modifying project rules.

Hard Negative Mixing for Contrastive Learning

Design a Concrete-Pictorial-Abstract learning sequence for a mathematical concept using manipulatives. Use when teaching maths through Singapore method or when students struggle with abstraction.

Space (adai-space)

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

Consolidates auto-memory files in ~/.claude/projects by auditing, planning, and executing a 4-phase cleanup with user approval.

Temporal interval algebra for reasoning about time relationships in planning and knowledge representation

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting, then commit with git.

Teach the user a new skill or concept in a multi-session teaching workspace with missions, lessons, and learning records.

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"

Reduce high-dimensional data with UMAP for visualization, clustering preprocessing, and supervised or semi-supervised learning, including parameter tuning guidance.

Scaling Vision with Sparse Mixture of Experts

Spatial region-aware cell matching for CODEX/scRNAseq integration

Execute all plans in a phase with wave-based parallelization

Generates four improved variations of any installed skill, scores them against a weighted rubric, and applies the winning version while preserving the original.