Genel Claude Code pazaryerlerinden 69 eklenti. Her biri birlikte yüklenen beceriler, eğik çizgi komutları, ajanlar, kancalar veya MCP sunucuları içerir.
Bu filtrelere uyan 69 eklenti gösteriliyor.
claude-code-skillsalirezarezvani/claude-skills3
research-agent-skillsKalarisLabs/research-agent-skills2
claude-code-workflowswshobson/agents1
pm-claude-skillsmohitagw15856/pm-claude-skills1.claude-plugin/marketplace.json içeren depoyu gönderin, biz de her plugini listeleyelim.
Marketplace gönderCurate 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).
SQL, analytics, datasets, models and machine-learning workflows.
Machine learning experiments, training, evaluation and reproducible papers.
researchMachine learning and statistics (scikit-learn, PyTorch, transformers, SHAP) (22 skills)
32 skills for running a support desk, from the hard reply to the bot handoff: hard conversations, workload and staffing, roles, metrics and coaching, escalations and incidents, learning from tickets, answers and knowledge, service design, and AI and bots, safely.
productivity31 skills for deciding what to build, what to drop and whether it worked: prioritising and saying no, setting direction, discovering what customers need, defining the work, deciding and aligning, launching, and measuring and learning.
productivity41 skills for the documents product people write, from the first brief to the post-launch review: setting up your voice and templates, discovering, shaping the vision, defining the work, deciding, aligning, reporting up, shipping and learning, running the team, and reviewing and editing. Each skill produces one finished document with a named reader and a length budget.
productivityThe Complete Claude Guide for L&D: 40 Claude skills for the whole L&D job, in eight stages: diagnose the need with the request triage, the performance gap and the action map; work with the experts through the interview, the task breakdown and the review plan; design the learning with objectives, an evaluation plan, a design document and a curriculum map; build and test scenarios, a storyboard, a knowledge check, the check of an AI draft and a learner walkthrough; run the room with a session plan, slides, a facilitator guide and a pilot; carry it into work with a job aid, spaced practice and a manager briefing; measure what changed with a feedback form, an ROI estimate and the one-page report; and lead L&D through the year plan and the business case. For L&D managers and specialists, instructional designers, trainers and facilitators, and L&D leaders. Claude drafts and checks, people decide: nothing a learner does in training is used to grade, rank or build a case against them.
productivityClaude for Instructional Designers: 32 Claude skills for building one course from the request to the release, in eight stages: scope the course with the brief, the learner analysis, an action mapping session and an estimate the sponsor signs; get the content from experts with the interview script, the source triage and the review plan; design it with measurable objectives, the design document, the course map and the assessment blueprint; write the branching scenarios, the storyboard, video scripts, questions and job aids; build a practice activity, slides, a short series or a live session moved on screen; check accuracy, whether it teaches, accessibility, your own run-through, the expert round and a learner pilot; ship with a sign-off record and a release note and read the data; then keep your own practice in order. For instructional designers, learning experience designers, e-learning developers and the L&D person who builds courses alone. Claude drafts and checks; you decide what the
productivityData analysis, statistics and machine learning libraries.
researchExplain technical sources with source-grounded analogies and learner checks.
