22 Plugins aus öffentlichen Claude Code marketplaces. Jedes bündelt Skills, Slash-Commands, Agents, Hooks oder MCP servers, die zusammen installiert werden.
Zeige 22 Plugins, die diesen Filtern entsprechen.
agent-powerupsyeaight7/agent-powerups2
testland-qatestland/qa2
agricidaniel-claude-obsidianAgriciDaniel/claude-obsidian1
aiwgjmagly/aiwg1Reiche das repo mit .claude-plugin/marketplace.json ein und wir listen jedes plugin auf.
Marketplace einreichenEval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
Founder-mode executive team plugin: 13 cs-* C-suite agents (CFO, CMO, CRO, CPO, COO, CHRO, CISO, Chief of Staff, General Counsel, Chief Data Officer, Chief AI Officer, Chief Customer Officer, VP of Engineering) with distinct cognitive voices, plus 21 /c-level-agents:* slash commands — forcing-question office hours (CFO/CMO/CPO/CRO/CTO/CISO/GC/CDO/CAIO/CCO/VPE reviews), strategic sprint pipeline (brief → boardroom → decide → execute → post-mortem), and meta routing (/c-level-agents:founder-mode auto-router, /cs-onboard, /c-level-agents:cross-eval multi-model consensus, /c-level-agents:freeze cooldown lock). Wraps the 33 c-level skills with cognitive gearing, persona voice, and artifact-driven handoffs. The business-domain answer to YC Garry Tan's gstack.
Multi-agent collaboration — spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any task that benefits from diverse solutions. 7 slash commands (/hub-init, /agenthub:spawn, /hub-status, /agenthub:eval, /agenthub:merge, /agenthub:board, /hub-run), agent templates, DAG-based orchestration, LLM judge mode, message board coordination.
Autonomous experiment loop — optimize any file by a measurable metric. 5 slash commands (/autoresearch-agent:setup, /ar-run, /ar-loop, /ar-status, /ar-resume), 8 built-in evaluators, configurable loop intervals (10min to monthly).
Static lint for Claude Code plugins and skills, with experimental LLM scoring for skills
Local-first Agent Skills package and Claude Code plugin for source-cited Obsidian knowledge bases. Includes recoverable transactions, deterministic lint and retrieval, provenance ledgers, explicit vault adoption, offline-first capture foundations, and methodology modes.
Prove an agent, prompt, model or tool change did not make the agent worse. Three deterministic stdlib scripts: a trajectory checker that grades tool-call paths (strict / unordered / subset / superset match modes, argument matching, forbidden tools that block in every mode, call ceilings); a flake detector that classifies each case as stable or flaky from repeated trials and reports pass@k and pass^k with Wilson intervals; and a paired regression gate that averages trials per case, tests per-case differences with a t-based CI and an exact one-sided McNemar test, and blocks the merge on a significant drop, a critical-case regression, a dropped case, or a quarantine entry without owner and expiry. Ships cs-eval-gatekeeper agent, /cs-agent-evals and /cs-eval-gate commands, 3 references, and a CI job example.
Tools, skills, and CLI extensions for designing and productionizing LLM inference pipelines. Pattern-guided, slim by default, eval-first.
Multi-agent orchestration subset: search competing plans and ship one selected repo change through the Suede Thought Graph DAG (suede-graph-flo-xr), coordinate build lanes with quality gates and a signed handoff (suede-agent-teams), route cross-surface work end to end (suede-workflow-skills), and turn AI features into eval specs and acceptance gates (suede-ai-eval).
Evaluate prompts and skills through parallel execution comparison in git worktrees
Design data, retrieval, AI runtime, model tooling and agent operations.
Tools from the agents course: audit your context, write done as a script, bootstrap your eval suite, and a loop critic agent.
All 30 maintainer skills and 9 agent profiles: humanize and localize prose, triage, reproduce and verify bugs, review PRs, debug ML training, profile performance, bisect regressions, audit CVEs, generate changelogs, evaluate SemVer version bumps, isolate scratchpads, fix type errors, isolate faults, conduct adversarial reviews, route architect-editor edits, generate conventional commits, resolve merge conflicts, prune context, and prepare releases.
productivityML pipeline design, experiment tracking, model evaluation, training debugging, and reproducibility.
developer toolsThe full cap-evolve skill library: intake, implement-and-check, evaluate, diagnose, gate, baseline, finalize, report; capability/algorithm/optimizer skills; and an autonomous orchestrate skill.
LLM and prompt evaluation with Promptfoo, DeepEval and Ragas, Giskard vulnerability scans, Langfuse tracing, and golden-dataset regression suites. Audits eval suites for methodology errors. Agents (prompt-eval-reviewer, llm-red-team-planner) review an eval suite and plan adversarial probe campaigns across the OWASP LLM Top 10.
ai-mlSearch-first codebase understanding, context retrieval, mapping, pattern detection, and living project intelligence.
developer toolsAutonomous optimization loop — iterates on prompts, skills, templates, or code overnight. Two evaluation modes: deterministic (eval.py with proxy heuristics) for mechanical checks, or AI judge (LLM rubric scoring) for creative/subjective quality. Uses 4-way agent separation for unbiased evaluation.
The SDLC as a guarded graph, with the milestone loop delegated to a milestone agent per milestone (per worktree under strategy C) whose bundle the orchestrator verifies against git before recording it. A run is one gitignored directory — state, per-milestone journals, and with --trace every state it passed through. Ships a run reviewer that turns a finished run into the evals it should have had, and an advisory onboarding skill that reports which third-party tools this session can invoke and what a run does without each. Command-invoked.
workflowCache testing across browser, CDN, proxy, application and data-store layers: Redis, CDN purges, Varnish VTC tests, and cache-key collision audits. Covers RFC 9111 HTTP caching, Cloudflare / Fastly / CloudFront purge APIs, browser Cache-Control tests, and cache-coherence patterns with stampede and stale-while-revalidate references. A detector agent (cache-key-collision-detector) finds keys missing a tenant, user or locale discriminator.
backend-distributed
