Claude Code eklentileri
Genel Claude Code pazaryerlerinden 23 eklenti. Her biri birlikte yüklenen beceriler, eğik çizgi komutları, ajanlar, kancalar veya MCP sunucuları içerir.
Bu filtrelere uyan 23 eklenti gösteriliyor.
Genel Claude Code pazaryerlerinden 23 eklenti. Her biri birlikte yüklenen beceriler, eğik çizgi komutları, ajanlar, kancalar veya MCP sunucuları içerir.
Bu filtrelere uyan 23 eklenti gösteriliyor.
.claude-plugin/marketplace.json içeren depoyu gönderin, biz de her plugini listeleyelim.
Marketplace gönderActive coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, simplify, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check command, and pre-commit hook. All stdlib-only.
Turn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task plan (refusing vague goals with forcing questions), and a JSON-backed loop controller drives execute->verify->close with retry caps, controller-run verification (no verification theater), human escalation on exhausted budgets, and a close gate that refuses while any task is unverified or unwaived. Ships 3 stdlib Python tools, 18 committed per-domain harness manifests + JSON schema, 3 references citing the 2024-2026 agent-harness canon (Anthropic long-running harnesses, verifier's law, SWE-agent, Ralph loop, Cognition), harness-runner agent + /cs-harness command. Use when an agent or subagent should pick up a goal, define its tasks, complete and verify them, and close the loop.
Skills, rules, hooks, agents and output styles for Claude Code: test-gated landing for parallel agent work, framework knowledge with staleness verifiers, and security checks aimed at the agent itself
The Fable Workflow: think (fable-method), act (fable-loop), prove (fable-judge), grow (fable-domain). A problem-solving loop, its orchestration, an adversarial work-verifier, and a domain-adapter generator, with the eval that keeps them honest.
Hook-based security firewall and supply-chain verifier for Claude Code skills, MCPs and agents. Gates destructive git, secret and credential reads, exfiltration, download-and-run, self-tampering and Solana on-chain actions; grades and pins skill packs.
Adversarial verification for AI-generated legal content with systematic fact-checking, source validation, and quality control. Use when verifying legal documents, fact-checking regulatory content, performing red team review, or quality assurance before distribution to clients or stakeholders.
Cross-stack motion & design-system direction: an orchestration router, a motion-quality audit skill, cinematic R3F look-dev, seven specialist motion subagents (including a runtime-proof verifier), and a director output style.
Single-command autonomous delivery orchestrator — the build stage of the *-it lifecycle (plan-it plans it, build-it builds it); formerly fable-it. Model-adaptive for Sonnet 5 and Opus 4.8. Hand it a goal and a numbered Definition of Done and it runs the whole job to completion, conducting launch/iterate/full-qa/chrome-cdp with a 5-gate catalog, disk-backed run state, an evidence ledger (VERIFIED = lookup), a fresh-context verifier, and an honest per-criterion report.
Complete AI-augmented engineering framework: Requirements traceability (REQ-XXXX), independent Build Agent + Red Team Verifier, multi-cycle lifecycle management, compliance-ready artifacts (ISO 9001, ISO 27001, GxP)
Install, operate, and troubleshoot Unsloth Core, Studio, and Desktop for local inference and model training. Use for Unsloth environment setup, LoRA/QLoRA supervised fine-tuning, coding specialization, verifier audits, chat templates, GRPO and preference training, vision and audio workflows, decision models, local coding agents and tools, dynamic quantization, checkpoint recovery, multi-GPU training, and model export to GGUF or serving engines. Do not use for framework-neutral ML strategy or operating a standalone inference server unrelated to Unsloth.
Catch security issues, unsafe agent patterns, and hallucinated tools before code ships
Remediate existing PDFs: auto-tag with PDF/UA semantic structure via the Nutrient DWS Accessibility API, then check the result with the bundled verifier.
Doer to verifier-panel to consensus delivery verification for any artifact (code slices, plans, documents, audits). An orchestrator freezes acceptance criteria before implementation, dispatches a doer, then convenes a context-walled panel of independent verifiers — including an adversary with a must-oppose mandate — for evidence-anchored review adjudicated to SHIP / SHIP_WITH_CAVEATS / ITERATE / BLOCK / ESCALATE. Platform-agnostic; degrades to sequential fresh-context sessions without subagents.
Defect management: severity vs priority classification, bug tracker workflows on Jira, Linear, GitHub Issues and Azure DevOps, and fix confirmation. Agents (ci-defect-filer, defect-fix-verifier) turn CI failures into deduplicated tracker bugs and re-run a defect's reproduction once a fix is claimed. Distinct from qa-bug-repro, which covers reproduction, report authoring, and the weekly defect review.
operations-resilienceTen skills forming a documentation chain: AGENTS.md entry point, PRD, technical specs, ADRs, implementation plans, status tracking with crash recovery, a git workflow with evidence-carrying PRs, an independent verification gate, gated documentation maintenance, and a brownfield onboarding on-ramp — plus a bundled verifier agent and router + run-loop drivers shipped as both commands and skills (works in Claude Code, GitHub Copilot CLI, and Codex). The harness layer for long-running, loop-driven development.
workflowsAI Evals for PMs: turn a product contract into a versioned four-surface suite covering outcomes, trajectories, end-to-end systems, and promised memory/state, with auditable PASS/FAIL/BLOCKED release evidence.
Public goal-contract-writer entrypoint for canonical Goal Contracts with paired fresh-subagent verifier and progress tracker runtime skills.
한글(.hwpx) 문서를 안 깨고 읽고 편집한다. 바이트 단위로 무손실인 raw-preserving 재압축, 렌더 기반 레이아웃·서식 감사, 구조 검증기를 함께 제공한다. Edit HWPX (Hangul) documents without corrupting them: byte-identical raw-preserving repack, render-level layout and typography audits, and a structural verifier.
productivityPressure-test research claims with falsifiable verifier plans, AI-lab workflow patterns, medical evidence certainty, proof ladders, and proof ledgers.
researchAuthor custom Model Advisor checks, run compliance reviews against industry standards (MISRA, MAB, ISO 26262, DO-178C, AUTOSAR, SLCI), author persistent, requirement-traceable Simulink Test cases, inject faults for robustness testing, perform safety analysis (FMEA, FHA, FTA), detect design errors with root cause analysis using Simulink Design Verifier, fix SLDV incompatibilities, explain missing coverage objectives, and collect quality metrics (maintainability, complexity, testing, coverage) using metric.Engine
development