公開されている Claude Code marketplace からの 60 件のプラグインです。それぞれにスキル、スラッシュコマンド、エージェント、フック、MCP サーバーがまとめてインストールされます。
これらのフィルターに一致するプラグインを 60 件表示しています。
research-agent-skillsKalarisLabs/research-agent-skills2
copilot-primitives-claudegbb-acelerators/awesome-harness-primitives2
claude-code-workflowswshobson/agents1
pm-claude-skillsmohitagw15856/pm-claude-skills1.claude-plugin/marketplace.json を含むリポジトリを提出すると、すべての plugin を掲載します。
marketplace を提出するCurate auto-memory, promote learnings to CLAUDE.md and rules, extract patterns into skills. Ships 5 slash commands (/si:memory-review, /si:promote, /si:extract, /si:memory-status, /si:remember) and 2 sub-agents (memory-analyst, skill-extractor).
ML model training pipelines, hyperparameter tuning, model deployment automation, experiment tracking, and MLOps workflows
Learning & mastery skills: build a roadmap for any skill, remember what you read and study (spaced repetition, active reading), learn by doing, break plateaus, and map your knowledge gaps.
Study companion for the Deep Learning textbook by Goodfellow, Bengio & Courville (MIT Press, 2016), free to read at deeplearningbook.org. Twenty chapter files, a glossary, patterns and a cheatsheet index the whole book, and a delta reference dates it against 2026 practice with per-claim confidence levels: double descent qualifying the U-curve, AdamW splitting weight decay from L2, transformers displacing Chapter 10's recurrence, diffusion growing out of Chapter 18's score matching. Four stdlib tools make it executable — a prerequisite-closed reading-path planner that refuses goals the book does not cover, a training diagnostic running Chapter 11's rules in priority order so a NaN is never reported as overfitting, a capacity planner that ranks 'shrink the model' last when overparameterized, and a parameter/FLOP/activation-memory calculator that refuses a stack whose shapes do not connect. A companion, not a compilation: the book is copyrighted, so nothing here reproduces its text.
Two-loop skill pipeline for Claude Code. Inner loop (plan-interview, intent-framed-agent, session-context, context-surfing, verify-gate, self-healing, simplify-and-harden) catches failures in-session — including active runtime recovery via self-healing when a command, test, build, helper, env, or external service fails mid-task. Outer loop (learning-aggregator, self-improvement, eval-creator, pre-flight-check) captures recurring patterns, promotes them to CLAUDE.md as permanent rules with human approval, and turns failures into regression tests. The harness gets stronger with every cycle.
Twelve-skill bundle covering the American Educational Research Journal (AERJ) manuscript lifecycle across quantitative, qualitative, and mixed-methods education research and the journal's two sections (Social and Institutional Analysis; Teaching, Learning, and Human Development).
academicTwelve COLT-specific skills for learning-theory conference strategy, grounded in the COLT 2026 Call for Papers, learningtheory.org conference pages, and PMLR proceedings volumes checked on 2026-07-08.
academicTwelve CoRL-specific skills for robot-learning conference strategy, grounded in the official CoRL 2026 author, reviewer, and rebuttal instructions, the OpenReview group, and PMLR proceedings volumes.
academicTwelve MLSys-specific skills for machine-learning-and-systems conference submission strategy, grounded in the official MLSys 2026 Call for Research Papers, Industrial Track CFP, Call for Artifact Evaluations, and dates/organization pages.
academicNightly offline self-evolution for this repo's Claude agent: harvests past Claude Code sessions (read-only), mines recurring tasks, replays them offline on your own API budget, and consolidates learnings into validated CLAUDE.md memory and SKILL.md skills behind a held-out gate, staged for review (never auto-applied). Verbatim vendor of microsoft/SkillOpt's stdlib-only skillopt_sleep engine + Claude Code plugin surface (MIT).
Machine learning experiments, training, evaluation and reproducible papers.
researchMachine learning and statistics (scikit-learn, PyTorch, transformers, SHAP) (22 skills)
Data analysis, statistics and machine learning libraries.
researchExplain technical sources with source-grounded analogies and learner checks.
Train and optimize machine learning models with automated workflows
Ten source-backed skills for structure, prompting, verification, delegation, reusable workflows, and learning.
Self-Learning Multi-agent orchestration framework for spec-driven development and automated verification. With smarter tool calling and leaner context.
Teach and coach rather than deliver answers: Socratic mentoring for juniors, study modes, understanding checks, critical thinking and devil's advocate review, self-learning architecture paths, and scientific paper research.
Diagnosis-first learning tutor skills: 零基础讲解、卡点诊断、解题引导、错题复盘、单词深挖、背诵抽测、学习计划。
ML pipeline design, experiment tracking, model evaluation, training debugging, and reproducibility.
developer tools
