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
118
工具排名
Ranked by creation date, newest first; undated entries come last. 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
Description Evidence-driven evaluation, benchmarking, and verified repair for Agent Skills across Codex, Claude Code, Gemini CLI, and Antigravity.
github估算动量打开来源 ↗
安装
git clone https://github.com/MaxLaurieHutchinson/skill-evaluation-graph ~/.claude/skills/skill-evaluation-graph2GitHub 星标— - 2活跃
Run many AIs on one board and keep control of all of it. Deterministic code decides who acts — never a model. A privacy floor keeps sensitive work on your machine, your own tests decide what counts as done, and every action lands on a…
github实测增长打开来源 ↗
安装
git clone https://github.com/sandhusukhdeep2/sc-prism-releases ~/.claude/skills/sc-prism-releases1GitHub 星标稳定 - 30GitHub 星标稳定
- 4活跃
Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.
github实测增长打开来源 ↗
安装
git clone https://github.com/MrZoyo/deslop-GPT ~/.claude/skills/deslop-GPT87GitHub 星标+59 (+210.7 %) - 5活跃
dsh-plugins
智能体Generic DeepSeek Harness (dsh) plugins: A2A protocol server, session storage mirror, and Langfuse observability.
github实测增长打开来源 ↗
1GitHub 星标稳定 - 6活跃
Production reliability, benchmarking, and evaluation layer for MCP agent runtimes — protocol negotiation, A2A interop, circuit breakers, connection pooling, adaptive streaming, and autoscaling, with measured throughput/latency and a…
github实测增长打开来源 ↗
3GitHub 星标稳定 - 7活跃
Multi-agent quality gate skill for Claude Code that researches, reviews, tests and challenges AI-generated work before the final answer.
github实测增长打开来源 ↗
安装
git clone https://github.com/ma-nucho-pro/supervisor-skill-claude ~/.claude/skills/supervisor-skill-claude2GitHub 星标稳定 - 8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实测增长打开来源 ↗
安装
git clone https://github.com/NocodeMrLi/mini-program-engineering-skill-suite ~/.claude/skills/mini-program-engineering-skill-suite45GitHub 星标+6 (+15.4 %) - 9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 %) - 10活跃
Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory, and observability.
github实测增长打开来源 ↗
6GitHub 星标+1 (+20.0 %) - 11活跃
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
github实测增长打开来源 ↗
安装
git clone https://github.com/EverMind-AI/SkillCorpus ~/.claude/skills/SkillCorpus525GitHub 星标+199 (+61.0 %) - 12活跃
evoagent-os
智能体Local-first control plane for durable, governed agent teams: DAG orchestration, approvals, memory, signed skills, trace contracts, and realtime.
github实测增长打开来源 ↗
0GitHub 星标稳定 - 13活跃
Production patterns for agent orchestrators, harnesses, evals, MCP/A2A interoperability, memory, provider routing, and LLM usage metering.
github实测增长打开来源 ↗
安装
git clone https://github.com/ssheleg/agent-stack ~/.claude/skills/agent-stack2GitHub 星标+1 (+100.0 %) - 14活跃
Your LLM reviewer said APPROVE. Did it? A structured verdict contract: prompt rule + parser + exit-code gate in one stdlib file, with the 42 counterexamples that forced every line. Free, MIT.
github估算动量打开来源 ↗
安装
git clone https://github.com/tonydzi/verdict-contract ~/.claude/skills/verdict-contract2GitHub 星标— - 15活跃
Research-backed, eval-driven skills for AI agents
github实测增长打开来源 ↗
安装
git clone https://github.com/ZSeven-W/craft-skills ~/.claude/skills/craft-skills145GitHub 星标+9 (+6.6 %) - 16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 - 17活跃
Skill instalable para Claude Code que mide si tu agente cumple las reglas establecidas. Lee el historial de sesiones de tu disco y devuelve un porcentaje por regla de cumplimiento. Sin instalar nada, sin red, biblioteca estándar.
github实测增长打开来源 ↗
安装
/plugin marketplace add jleonceo/skill-adherencia-reglas1GitHub 星标稳定 - 18活跃
Mide si tu agente de IA cumple las reglas que le escribiste. Lee el historial local de Claude Code y devuelve un porcentaje por regla. Sin instalar nada, sin red, biblioteca estándar.
github实测增长打开来源 ↗
安装
git clone https://github.com/jleonceo/adherencia-reglas ~/.claude/skills/adherencia-reglas1GitHub 星标稳定 - 19活跃
VeriRun
其他Evidence-first infrastructure for reproducible, isolated executable evaluation and online rewards.
github实测增长打开来源 ↗
197GitHub 星标+81 (+69.8 %) - 20活跃
Claude Code skills where every entry ships receipts — accuracy-gated benchmarks against baseline and placebo, rejects published
github实测增长打开来源 ↗
安装
git clone https://github.com/sjh9714/skill-receipts ~/.claude/skills/skill-receipts2GitHub 星标稳定 - 21活跃
Deterministic crash tests for agent control planes: paired worlds, hard stops, budgets, scopes, approvals, and hash-linked receipts.
github实测增长打开来源 ↗
1GitHub 星标稳定 - 22活跃
🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams
github实测增长打开来源 ↗
安装
git clone https://github.com/tikalk/adlc-team-skills ~/.claude/skills/adlc-team-skills132GitHub 星标+1 (+0.76 %) - 23活跃
nudge
MCPA typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.
github实测增长打开来源 ↗
2GitHub 星标稳定
学习与参考资源
Ranked by creation date, newest first; undated entries come last. 这些资源可单独访问，不参与主要排名。
- 1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 - 2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 星标稳定