Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Monitoring & ops
2,353 results · page 4 of 79
- View details
kubesphere-servicemeshSkillMonitoring & ops
Lets your agent install, check, and troubleshoot the KubeSphere service mesh with Istio, Kiali, and Jaeger.
Ready to connect★ 17k
- View details
whizard-loggingSkillMonitoring & ops
Lets your agent install, configure, and query logs from KubeSphere's WizTelemetry logging extension.
Ready to connect★ 17k
- View details
whizard-telemetrySkillMonitoring & ops
Helps your agent install and configure the WizTelemetry observability backend for KubeSphere.
Ready to connect★ 17k
- View details
whizard-telemetry-rulerSkillMonitoring & ops
Lets your agent install, configure, and manage alerting rules for the KubeSphere WizTelemetry Ruler extension.
Ready to connect★ 17k
- View details
wiztelemetry-tracingSkillMonitoring & ops
Helps your agent install, configure, and query traces in the WizTelemetry Tracing extension for KubeSphere.
Ready to connect★ 17k
- View details
imperative-to-declarative-fletSkillMonitoring & ops
Convert an imperative Flet Python app in which controls are mutated and then page.update is called to declarative style using flet.component, flet.observable and state hooks.
Ready to connect★ 17k
- View details
Ahrefs AutomationSkillMonitoring & ops
Lets your agent look up SEO data like backlinks, keyword rankings, and domain metrics from Ahrefs.
Ready to connect★ 16k
- View details
datadog-logsSkillMonitoring & ops
Lets your agent search, filter, and summarize Datadog logs and export them as structured JSON from the command line.
Ready to connect★ 16k
- View details
pr-review-ci-fixSkillMonitoring & ops
Lets your agent review pull requests and automatically fix failing CI checks on GitHub or GitLab.
Ready to connect★ 16k
- View details
sentry-triageSkillMonitoring & ops
Lets your agent pull Sentry error details, map stack frames to local code, and propose fixes.
Ready to connect★ 16k
- View details
monitor-experimentSkillMonitoring & ops
Lets your agent check on running experiments, see their progress, and collect the results.
Ready to connect★ 16k
- View details
training-checkSkillMonitoring & ops
Lets your agent periodically check WandB training metrics to catch NaNs, diverging loss, or idle GPUs early.
Ready to connect★ 16k
- View details
cadSkillMonitoring & ops
Lets your agent create, edit, and check parametric CAD parts from text descriptions, images, or drawings.
Ready to connect★ 15k
- View details
benchmark-fp-fn-auditSkillMonitoring & ops
Lets your agent audit React Doctor's diagnostic results for false positives, false negatives, and gaps.
Ready to connect★ 15k
- View details
perftestSkillMonitoring & ops
Lets your agent run Firefox performance tests locally or in CI using mach commands.
Ready to connect★ 13k
- View details
evaluating-code-modelsSkillMonitoring & ops
Lets your agent test and compare code-generating models on standard benchmarks like HumanEval and MBPP.
Ready to connect★ 13k
- View details
experiment-tracking-swanlabSkillMonitoring & ops
Lets your agent log and track machine learning experiments with SwanLab runs and dashboards.
Ready to connect★ 13k
- View details
pyvene-interventionsSkillMonitoring & ops
Guides your agent in running causal experiments on PyTorch models, like tracing which parts cause a behavior.
Ready to connect★ 13k
- View details
tensorboardSkillMonitoring & ops
Lets your agent visualize machine learning training metrics, compare experiments, and profile model performance in TensorBoard.
Ready to connect★ 13k
- View details
weights-and-biasesSkillMonitoring & ops
Lets your agent log machine learning experiments, view training charts, run hyperparameter sweeps, and manage model registries.
Ready to connect★ 13k
- View details
e2eSkillMonitoring & ops
Lets your agent run end-to-end tests, check their status, and debug failures using logs.
Ready to connect★ 12k
- View details
loggingSkillMonitoring & ops
Teaches your agent how to write backend log messages when working on code.
Ready to connect★ 12k
- View details
pr-watchSkillMonitoring & ops
Take an open pull request to green — wait for CI, triage failing checks, and answer review-bot comments — using one backgrounded observation per cycle. Use when monitoring or babysitting a PR, waiting on checks or review bots, or addressing PR review feedback.
Ready to connect★ 12k
- View details
monitoring-expertSkillMonitoring & ops
Lets your agent set up monitoring dashboards, logging, alerts, and tracing for your applications.
Ready to connect★ 11k
- View details
sre-engineerSkillMonitoring & ops
Lets your agent define reliability goals, error budgets, incident procedures, and monitoring configs for production systems.
Ready to connect★ 11k
- View details
android-emulator-skillSkillMonitoring & ops
Lets your agent build, test, and automate Android apps in an emulator, navigating screens and reading logs.
Ready to connect★ 11k
- View details
hive.quality-monitorSkillMonitoring & ops
Lets your agent periodically check its own work quality so it catches slipping output before you do.
Ready to connect★ 11k
- View details
hive.terminal-tools-job-controlSkillMonitoring & ops
Teaches your agent to run long terminal commands in the background, stream their logs, and stop them safely.
Ready to connect★ 11k
- View details
alphafold2SkillMonitoring & ops
Lets your agent predict protein structures and check confidence metrics using AlphaFold2-style workflows.
Ready to connect★ 9k
- View details
autoresearchSkillMonitoring & ops
Lets your agent run bounded research experiments, testing hypotheses and keeping changes that improve benchmark results.
Ready to connect★ 9k
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
52,524 of the 52,958 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.