Claude Code eklentileri
Genel Claude Code pazaryerlerinden 6.108 eklenti. Her biri birlikte yüklenen beceriler, eğik çizgi komutları, ajanlar, kancalar veya MCP sunucuları içerir.
Genel Claude Code pazaryerlerinden 6.108 eklenti. Her biri birlikte yüklenen beceriler, eğik çizgi komutları, ajanlar, kancalar veya MCP sunucuları içerir.
.claude-plugin/marketplace.json içeren depoyu gönderin, biz de her plugini listeleyelim.
Marketplace gönderSafely reclaim disk space on a Mac: survey usage, auto-clear only pure caches, Trash anything riskier (reversible), ask before anything expensive, log every deletion.
productivityTimed online-assessment simulations with a deterministic timer and hidden-test grading, plus an interview mode. Original questions only.
productivityPre-launch security audit for web apps. Runs OWASP checks via shell scripts, then AI analyzes findings.
securityExhaustive code review and security audit checklist for any language: root-cause facets from real vulnerabilities, 46 general dimensions, 78 specialties by target type, 33 language and format tables including configuration, regex and GPU programs, execution environment checks, threat model and report format. Markdown only, read-only by default.
securityEvidence-backed writing principles and repository engineering for predictable, composable agent skills / 有证据支撑的可预测、可组合 Agent Skill 写作原则与仓库工程
workflowState machine design, changeset writing, engineering writing, and component API design skills.
engineeringThe rep's daily loop: pre-call briefs, pipeline hygiene, account snapshots, post-call follow-ups.
Build valid, fair educational assessments for any subject and grade: guided mode selection, test blueprint and topics-by-Bloom matrix, item drafting by format rules, per-item passports, a review checklist, and post-administration psychometrics (P-value, D-index, Rit, distractor analysis). Every generated item is flagged for mandatory human expert review.
The paper's canonical 7-role Data Journalist Agent pipeline
Consolidate scattered project markdown files into a single canonical CLAUDE.md, with a pinned PROGRESS block at the top.
documentationPressure-test research claims with falsifiable verifier plans, AI-lab workflow patterns, medical evidence certainty, proof ladders, and proof ledgers.
researchAgent Alchemy Git Tools — git utilities for version control
Edit Russian text using Ilyakhov's information style. Removes stop-words, cliches, bureaucratic language. Replaces with concrete facts and numbers.
Task lifecycle skills: /next, /done, /save, /task
engram + skillet MCP servers and toolkit skills (local memory, skill management, agent tracing) — everything runs on your machine.
productivityWarm, intentionally-imperfect 'naive design' as an agent skill — childlike doodles, crayon/marker/riso texture, lowercase friendly type. Self-contained, and a disciplined complement to design-engineering.
One-page Harvard-format resume aimed at a specific job, hackathon or fellowship posting, with a fitter that keeps it to a page and a guard that fails the build if tailoring inflates a date or a title.
Generic Claude Code skill for building, debugging, and extending Supernote e-ink device plugins with the sn-plugin-lib SDK (React Native + Android).
Opinionated lint rules for rejecting low-evidence Python patterns, with opt-in Pydantic and FastAPI groups and a skill that scans or installs them.
Discover, lint, format, and validate BIRD 2/3 projects with parser-backed diagnostics.
development