Observability

Read your own agent telemetry from ClawMetry (waste, progress, cost) and act on it before finishing a task.

vivekchand/clawmetry

Walks a contributor through adding a new HTTP framework integration to the evlog logging package: middleware source, build entry, exports, tests, example app and docs.

evloghq/evlog

Instruments code so production behavior is visible and diagnosable.

dzhalaevd/Donatello

Evaluate and score agent behavior against a golden reference.

agentevals-dev/agentevals

Propose an improved version of a prompt registered in a self-hosted AgentX (AgentX-trace-eval) instance, using real low-rated evaluation results as evidence, then publish it as a new version once…

AgentX-ai/AgentX-Trace-Eval

Best-practices reference for preparing and instrumenting applications on Temps.

gotempsh/temps

Comprehensive backend development guide for Litefuse's Next.js 14/tRPC/Express/TypeScript monorepo.

litefuse/litefuse

Redis observability guidance — which metrics to monitor (memory, connections, hit ratio, ops/sec, rejected connections), which built-in commands to reach for during incident triage (SLOWLOG, INFO…

redis/agent-skills

Investigates incidents and production problems with hypothesis-driven debugging, queries Axiom observability data when available, and keeps secrets out of commands and output.

openclaw/clawhub

Monitor approved eBPF, Linux, observability, and AI-infrastructure communities through watchlist-opted-in read-only Slack archives plus ordinary visible browser UI, turn the strongest daily…

eunomia-bpf/eunomia.dev

A skill your agent uses when adding, reviewing, or refactoring backend code in Rift's TanStack Start app that should follow apps/start/BACKENDEFFECTPLAYBOOK.md.

Compound-inc/rift

Salesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows.

Jaganpro/sf-skills

Debugs a single Linux host or container runtime at the kernel level with the standalone ig binary and eBPF gadgets, read-only and without Kubernetes.

inspektor-gadget/inspektor-gadget

Writes Terraform alerting policies for AI agents that emit OpenTelemetry metrics, covering reliability, cost, safety, security and quality signals on Google Cloud.

google/skills

Add lightweight runtime telemetry and debug instrumentation to macOS apps, then verify those events after building and running.

robinebers/openusage

Entry point for AI-agent work on AWS: pick a runtime, plan a migration for existing workloads, and build an executable POC — one phased flow.

aws/agent-toolkit-for-aws

Develops Go microservices with Kratos v2 following official design philosophy, DDD/Clean Architecture layout, Protobuf API, error/config/middleware patterns, and observability.

aide-family/moon

Scaffold a new SkyWalking Python instrumentation plugin with all required files (plugin code, tests, docker-compose, expected data, services)

apache/skywalking-python

A skill your agent uses when building, debugging, reviewing, or documenting Flue agents, workflows, channels, skills, tools, sandboxes, targets, routing, persistence, observability, or CLI usage…

shadcn-labs/agentcn

How to log in the y5 compositor. An agent skill from y5-snowies/nourish.

y5-snowies/nourish

AWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale.

zxkane/aws-skills

Monitor hosts, Docker containers, Kubernetes clusters, database/queue/cache servers, and cloud-provider metrics with Pydantic Logfire — no application code required.

pydantic/skills

Full Sentry SDK setup for Elixir. An agent skill from getsentry/sentry-for-ai.

getsentry/sentry-for-ai

Walks through adding a new rule or framework adapter to `evlog map` in @evlog/cli, from the rule source and registry to types, tests, docs and the published skill.

evloghq/evlog

Adds logging to fp-go functional pipelines with Tap operators, entry and exit logs and error context, so that logging never changes the value or error flowing through.

IBM/fp-go

Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP.

PostHog/posthog

Operate Temps through the pinned @temps-sdk/cli package with bunx or npx.

gotempsh/temps

Naming conventions for SGLang speculative decoding identifiers.

sgl-project/sglang

Comprehensive Rust coding guidelines with 265 rules across 26 categories.

JMBeresford/retrom

Build production-ready AI agent backends using the CloudBase Agent Python SDK — create agents with LangGraph/CrewAI/LlamaIndex, serve them via FastAPI with AG-UI protocol streaming +…

TencentCloudBase/CloudBase-AI-Toolkit

Adds Pydantic Logfire tracing, logging and metrics to Python, JavaScript or TypeScript and Rust projects, with the correct setup order and library extras.

basicmachines-co/basic-memory

Debug deployed Cloudflare Workers using the cfobservability MCP, Wrangler, D1/R2 state, repo evidence, and safe live reproduction.

Consensys/c0

Reviews and authors Cloudflare Workers code against production best practices.

hodgef/apiker

Build Docker test images and run SkyWalking Python plugin/unit/e2e tests locally, mirroring the CI pipeline

apache/skywalking-python

A skill your agent uses when adding Spring AI-specific model observations, token usage, latency, externally configured cost attribution, advisor telemetry, or protected prompt and completion logging.

rrezartprebreza/spring-boot-skills

AWS cost optimization, monitoring, and operational excellence expert.

zxkane/aws-skills

Set up crash instrumentation with actionable context. An agent skill from nexus-labs-automation/mobile-observability.

nexus-labs-automation/mobile-observability

Diagnose and fix scope or continuation lifecycle failures in dd-trace-java instrumentation tests.

DataDog/dd-trace-java

Bootstrap a reproducible LLM Observability experiment through the Python ddtrace SDK or the Node dd-trace SDK.

datadog-labs/agent-skills

A skill your agent uses when building production services, pipelines, or automation that needs to be debugged, monitored, or audited.

aiming-lab/MetaClaw

A skill your agent uses when migrating applications, examples, integrations, documentation, manifests, or repository code from NeMo Flow to NeMo Relay across Python, Rust, Node.js, Go, C FFI, CLI…

NVIDIA/NeMo-Relay

Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records.

QoderAI/better-harness

AnyRobot 前端开发核心指南：提供 JavaScript + React + shadcn/ui 开发的精简实用规范和最佳实践。

opsrobot-ai/opsrobot

Build custom OpenTelemetry Collector distributions with OCB (OpenTelemetry Collector Builder).

ollygarden/opentelemetry-agent-skills

Productize a working prototype by adding a bounded set of explicitly requested operational or product services.

Dimon94/skills

Debug and inspect LLM/AI agent traces using PostHog's MCP tools.

PostHog/posthog

Set up a Claude Code workspace for a new or existing project, informed by hindsight from the user's whole session history.

Eigenwise/eigenwise-toolshed

当需要为 funboost 创建 Consumer 或 Publisher 的 Mixin 扩展类时使用。触发场景：添加监控、熔断、限流、链路追踪等横切关注点，编写自定义前置/后置处理钩子。关键词：mixin, consumeroverridecls, publisheroverridecls, ConsumerMixin, 自定义消费者, hook, 拦截器, 熔断器, 监控…

ydf0509/funboost