576 Plugins aus öffentlichen Claude Code marketplaces. Jedes bündelt Skills, Slash-Commands, Agents, Hooks oder MCP servers, die zusammen installiert werden.
Zeige 576 Plugins, die diesen Filtern entsprechen.
muto-atlasB7Kompirine/muto-atlas1
trtc-marketplaceTencent-RTC/agent-skills1
research-co-pilot-marketplaceMarazii/research-co-pilot1
ai-skillsAmey-Thakur/AI-SKILLS1Reiche das repo mit .claude-plugin/marketplace.json ein und wir listen jedes plugin auf.
Marketplace einreichenFast local search and 'git blame' for agent sessions.
4 macro-strategy skills: currency-analysis, leading-indicators, macro-regime, rate-cycle.
4 portfolio-strategy skills: long-short-construction, long-short-equity, portfolio-hedging, position-sizing.
Ground truth for FiveM/GTA V development. 24 offline data layers built from your own GTA V install and FiveM server: natives with apiset resolution and a Lua linter, archetypes, world placements, vanilla animation names, skeleton bone tags, vehicles, weapon components, peds, MLO interiors, embedded lights, weather timecycles, and your server's framework API. It checks your own files before the game sees them, decodes and edits prop lights against a measured vanilla reference, and covers parallax shaders and vanilla interior measurements. Nothing is guessed; a file that could not be inspected is never reported as clean.
developmentTRTC SDK integration assistant with knowledge base
Comprehensive research co-pilot — literature review, methodology, ethics review, data analysis, qualitative coding, brainstorming, manuscript drafting, replication design, grant writing, talk building, citations, survey design, and peer review.
research250 ready-to-run prompts as slash commands: summarize, tldr, explain, plan, goal, autoresearch, and more
Warn-only, zero-dependency runtime harness layer for Claude Code (companion to superpowers): persistent state, scope control (prompt + action side), Default-FAIL verification & coverage gates, entropy governance (golden-rules + drift detection), and first-class C/C++ engineering (CMake/Meson/Make/Bazel + clang-tidy + sanitizers).
Meta skills that operate on the skill system itself: skill review, session learning, cross-skill synthesis and output verification.
Start or continue a local knowledge workspace through one graph-routed entry.
Multi-model orchestration and advisor routing: tri-model review and canonical advisor routing.
developer toolsCoordination layer for multi-agent repositories. Gives task-pipeline runs leases with a TTL, race-free ID reservation, a cross-repo signal feed, an append-only run journal and a machine-generated read-only board. A lease is decided by a primitive that genuinely has compare-and-swap — an atomic file create on one machine, a pushed git ref across machines — never by the knowledge base, which loses concurrent writes; the store carries the record and the ID allocation, which is positional over the merged log. The knowledge backend is a pluggable adapter (Outline, filesystem) declaring its own capabilities and degrading out loud. Ships Claude Code hooks that deny edits to guarded registry files without a live lease.
developmentHelper skill and commands for installing and using the full Overdrive CLI skill system.
developer-toolsMemory-defragment/cleanup engine for agent memory, TWO lanes: class-B (memory + governance files) gets the semantic wash — a free mechanical Quick pass plus a code-enforced fidelity gate blocking any STRUCTURED-token drop by diff (links, dates, versions, frontmatter; prose fidelity is the paid semantic layer's job), consent-gated Full pass, every cut snapshot-backed (whole-run rollback); class-A (transcripts — the estate) gets byte-identity ULTRA archiving, never semantic-edited. Honest frame: slows how fast memory-overhead grows — it does not eliminate memory cost. Zero-dependency, offline, no API keys.
Exam coach for IELTS, TOEFL iBT and Cambridge B1-C2: original practice with criteria-based feedback, mistakes re-tested on fresh items, full-test reviews with an error catalog, and printable practice sheets. Local files only, original content only.
Error discovery for AI products: read real traces, name failure modes and success modes by stage, and turn the ones that matter into code checks and AI judges you can trust. Includes Eval Studio and a zero-dependency command-line tool.
Assess, design, and improve organizational practices for AI-powered products and AI-assisted product work.
productivitySelf-contained agentic development harness: one command runs the full feature pipeline with double review and security gates.
Coverage, security and code quality for coding agents.
Apache Magpie — adversarial review: runs other models' CLIs (Codex, Copilot, Antigravity, Pi, Grok, Goose, Claude) read-only over a change before its PR is created, and merges their findings. Runs from the installed plugin, so no repository needs a copy.
