工具说明为英文。
LLM 可观测性
LLM 应用的监控、追踪、评估和质量管理。
用途
活跃度
排序方式
122
工具排名
Ranked by normalized popularity across sources. 原始值保留各自的数据窗口；计算变化需要 7 天内至少两次测量。
- 1活跃
Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product…
github估算动量打开来源 ↗
安装
git clone https://github.com/NocodeMrLi/mini-program-engineering-skill-suite ~/.claude/skills/mini-program-engineering-skill-suite39GitHub 星标— - 2活跃
Real-time execution trace and cost intelligence for Claude Code
github实测增长打开来源 ↗
安装
/plugin marketplace add DeibyGS/claudestat34GitHub 星标+1 (+3.0 %) - 3活跃
Make Claude Opus 4.8 behave like Claude Fable 5 — doctrine output style, drift-catching hooks, and an eval loop against golden Fable transcripts. Claude Code plugin.
github实测增长打开来源 ↗
安装
/plugin marketplace add rennf93/opus-fable-playbook33GitHub 星标稳定 - 4休眠
🔍 AI observability skill for Claude Code. Debug LangChain/LangGraph agents by fetching execution traces from LangSmith Studio directly in your terminal.
github实测增长打开来源 ↗
安装
git clone https://github.com/OthmanAdi/langsmith-fetch-skill ~/.claude/skills/langsmith-fetch-skill27GitHub 星标稳定 - 5休眠
astragraph
智能体Policy-enforced observability and fail-closed guardrails for MCP/A2A multi-agent systems.
github实测增长打开来源 ↗
26GitHub 星标稳定 - 6活跃
Sentry instrumentation skill for system-behavior tracking
github实测增长打开来源 ↗
安装
git clone https://github.com/tortastudios/sentry-instrumentation ~/.claude/skills/sentry-instrumentation24GitHub 星标稳定 - 7活跃
Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.
github实测增长打开来源 ↗
22GitHub 星标+2 (+10.0 %) - 8活跃
Log Claude Code sessions to Opik, the open-source LLM observability and evaluation platform, built by Comet. Tracing, evaluation, and skills for observable AI applications.
github实测增长打开来源 ↗
22GitHub 星标+1 (+4.8 %) - 9活跃
untell
其他AI-detector auditing toolkit: measures how often a detector flags genuine human writing, how stable its verdict is across seeds, and whether that verdict survives meaning-preserving edits. Detector-in-the-loop measurement harness. Claude…
github实测增长打开来源 ↗
18GitHub 星标稳定 - 10活跃
rashomon
技能Measure prompt and skill improvements with blind A/B comparison.
github实测增长打开来源 ↗
安装
/plugin marketplace add shinpr/rashomon18GitHub 星标稳定 - 11活跃
Two Claude Code skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique to catch hallucinations), plus a fixture-based eval suite.
github实测增长打开来源 ↗
安装
/plugin marketplace add prime-radiant-inc/parallel-adversarial-review17GitHub 星标稳定 - 12休眠
MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations
mcp实测增长打开来源 ↗
安装
claude mcp add mcp-as-a-judge -- uvx mcp-as-a-judge17GitHub 星标稳定 - 13活跃
Make Claude write clearly, for everyone.
github实测增长打开来源 ↗
安装
/plugin marketplace add stefanobaghino/simple-output-styles16GitHub 星标稳定 - 14活跃
adl-cli
其他A command-line tool to scaffold and manage enterprise-ready AI Agents powered by the A2A (Agent-to-Agent) protocol
github实测增长打开来源 ↗
14GitHub 星标+1 (+7.7 %) - 15活跃
Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper (audit/elevate READMEs and make a repo open-source-ready).
github实测增长打开来源 ↗
安装
/plugin marketplace add GiustoPiedimonte/agentic-engineering-marketplace13GitHub 星标稳定 - 16休眠
A Claude Code skill that adds a rubric-based eval layer to any agent project. Framework-agnostic — generates rubric, test cases, judge prompt, and harness. Returns a weighted score plus a judge-leniency signal.
github实测增长打开来源 ↗
13GitHub 星标稳定 - 17活跃
Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.
mcp实测增长打开来源 ↗
安装
claude mcp add mcp-server -- npx @spanlens/mcp-server12GitHub 星标稳定 - 18活跃
Production-grade AI coding rules for Cursor and Claude Code. 15 rules + 9 doc templates + skills + agents + MCP setup. Drop into any project.
github实测增长打开来源 ↗
安装
git clone https://github.com/aiagentwithdhruv/ai-dev-stack ~/.claude/skills/ai-dev-stack10GitHub 星标+1 (+11.1 %) - 19活跃
Audit which Claude Code skills you actually use — surface dead installs and hallucinated invocations from your session logs.
github实测增长打开来源 ↗
安装
/plugin marketplace add sfrangulov/skill-graveyard10GitHub 星标+1 (+11.1 %) - 20活跃
bakeoff
技能Turn one decision into a judged tournament of solutions, then pick the best — a Claude Code skill that generates candidates, auto-derives the rubric, judges independently, and returns a defensible winner.
github实测增长打开来源 ↗
安装
/plugin marketplace add CoriChui/bakeoff10GitHub 星标稳定 - 21活跃
galdor
其他A Go-native framework for LLM agents, with OpenTelemetry observability built in.
github实测增长打开来源 ↗
10GitHub 星标稳定 - 22休眠
Local open-source dev tool to debug, secure, and evaluate LLM agents. Provides static analysis, dynamic security checks, and runtime monitoring - integrates with Cursor and Claude Code.
github实测增长打开来源 ↗
安装
/plugin marketplace add cylestio/agent-inspector9GitHub 星标稳定
学习与参考资源
Ranked by normalized popularity across sources. 这些资源可单独访问，不参与主要排名。
- 1活跃打开来源 ↗
50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.
github安装
资源实测增长git clone https://github.com/ContextJet-ai/awesome-llm-observability ~/.claude/skills/awesome-llm-observability32GitHub 星标+2 (+6.7 %) - 2活跃打开来源 ↗
My complete journey to becoming an Agentic AI Engineer through structured learning, projects, experiments, and production-ready implementations of modern AI systems.
github资源实测增长18GitHub 星标稳定 - 3活跃打开来源 ↗
Documentation-discovery telemetry for Claude Code — heat/cold maps, health grade, evidence-backed router fixes. 100% local, zero tokens. /tt
github安装
资源实测增长/plugin marketplace add Hedde/trigger_tree14GitHub 星标+1 (+7.7 %)