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 12 of 79
- View details
reviewSkillMonitoring & ops
Lets your agent review code changes on a branch against repo standards, the linked issue, and bug risks.
Ready to connect★ 2k
- View details
specSkillMonitoring & ops
Lets your agent turn a rough idea or issue into a written spec with goals and acceptance criteria before coding.
Ready to connect★ 2k
- View details
test-guidelinesSkillMonitoring & ops
Lets your agent write Jest tests for Sentry React Native following the project's naming, structure, and mocking conventions.
Ready to connect★ 2k
- View details
robustmq-metricsSkillMonitoring & ops
Lets your agent design and add metrics and Grafana dashboards for RobustMQ services.
Ready to connect★ 2k
- View details
context-engineeringSkillMonitoring & ops
Lets your agent monitor its context window usage and stay within a token budget while working.
Ready to connect★ 2k
- View details
context-preservationSkillMonitoring & ops
Lets your agent save and restore its task state when its memory window fills up so work continues smoothly.
Ready to connect★ 2k
- View details
debugging-patternsSkillMonitoring & ops
Gives your agent step-by-step debugging methods like log-first analysis and git bisect to find the root cause of failures.
Ready to connect★ 2k
- View details
error-loggingSkillMonitoring & ops
Lets your agent follow structured workflows step by step so complex tasks stay on track.
Ready to connect★ 2k
- View details
hook-managementSkillMonitoring & ops
Lets your agent turn monitoring hooks on and off, check their status, and see how fast they run.
Ready to connect★ 2k
- View details
issue-trackingSkillMonitoring & ops
Lets your agent track issues in git-backed storage and monitor their progress over time.
Ready to connect★ 2k
- View details
patrol-monitoringSkillMonitoring & ops
Lets your agent watch other agents for stalls or hangs and automatically recover them when stuck.
Ready to connect★ 2k
- View details
pr-shepherdingSkillMonitoring & ops
Lets your agent track pull requests from creation to merge, watching CI, reviews, and merge readiness.
Ready to connect★ 2k
- View details
test-enforcementSkillMonitoring & ops
Lets your agent run automated test validation, check coverage, and report code quality metrics.
Ready to connect★ 2k
- View details
verification-before-completionSkillMonitoring & ops
Makes your agent verify every claim with real evidence like logs, test results, or exit codes before saying a task is done.
Ready to connect★ 2k
- View details
incident-investigationSkillMonitoring & ops
Lets your agent investigate alerts, error spikes, and slowness by tracing root causes across logs, traces, and metrics.
Ready to connect★ 2k
- View details
maple-java-styleSkillMonitoring & ops
Guides your agent to set up Java apps to send traces, metrics, and logs in a standard format.
Ready to connect★ 2k
- View details
maple-kotlin-styleSkillMonitoring & ops
Guides your agent to set up Kotlin app telemetry with OpenTelemetry so traces, metrics, and logs export to a backend.
Ready to connect★ 2k
- View details
maple-onboardSkillMonitoring & ops
Lets your agent set up OpenTelemetry tracing, logging, and metrics across all services in your repo.
Ready to connect★ 2k
- View details
maple-onboarding-styleSkillMonitoring & ops
Lets your agent follow Maple's OpenTelemetry setup style when adding tracing and metrics to code.
Ready to connect★ 2k
- View details
maple-python-styleSkillMonitoring & ops
Lets your agent follow a shared style guide for adding OpenTelemetry tracing and logging to Python code.
Ready to connect★ 2k
- View details
maple-rust-styleSkillMonitoring & ops
Lets your agent set up Rust code with OpenTelemetry tracing that sends telemetry data to Maple.
Ready to connect★ 2k
- View details
hot-updater-agentSkillMonitoring & ops
Lets your agent run, monitor, and diagnose HotUpdater E2E test jobs from a local CLI dashboard.
Ready to connect★ 2k
- View details
bruin-semantic-layerSkillMonitoring & ops
Lets your agent create and edit Bruin semantic layer models, defining metrics, dimensions, joins, and queries in YAML.
Ready to connect★ 2k
- View details
dual-side-debugSkillMonitoring & ops
Inspect uniclipboard logs from BOTH the macOS host and the mounted Windows peer when debugging cross-platform sync, pairing, transfer, or daemon issues. Use whenever the user asks to "check logs", "see what's happening on both sides", or describes a symptom that involves the Windows peer (e.g. "Wind
Ready to connect★ 2k
- View details
ios-log-diagnoseSkillMonitoring & ops
Drive the UniClipboard iOS app in a simulator and read its OSLog yourself to diagnose a mobile-sync bug, instead of asking the user to paste logs. Use when debugging why the iOS sync engine or M5 reducer did something, reproducing an iOS sync / clipboard bug on the simulator, or whenever you'd other
Ready to connect★ 2k
- View details
pr-greenlightSkillMonitoring & ops
Agent Loop that runs local pre-flight CI checks, auto-fixes issues, creates/pushes the PR, monitors CI, and loops until all checks pass. Replaces the manual chain of preflight → create-pr → babysit-pr.
Ready to connect★ 2k
- View details
tracing-best-practicesSkillMonitoring & ops
TRIGGER when writing, modifying, or reviewing any Rust code that involves tracing, logging, spans, events, #[instrument], tracing::info/debug/warn/error, subscriber initialization, or tokio::spawn with context propagation. Enforces project tracing standards.
Ready to connect★ 2k
- View details
root-cause-tracingSkillMonitoring & ops
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
Ready to connect★ 2k
- View details
tooluniverse-immune-repertoire-analysisSkillMonitoring & ops
TCR/BCR repertoire analysis — V(D)J segment usage, CDR3 sequence diversity, clonality scoring, antigen specificity matching to IEDB, public-clone identification. Use for adaptive immune response characterization, post-treatment immune monitoring, antigen-specific clone tracking, and clonal-expansion
Ready to connect★ 2k
- View details
mps-distribution-buildSkillMonitoring & ops
Use when bundling a new plain Java/Kotlin plugin into MPS distribution archives, debugging packaging/layout issues in `build/mps*.xml`, tracing where per-plugin artefacts end up, or editing `plugins/mps-build/solutions/mpsBuild/models/build.mps` (the source of truth that generates every `build/mps*.
Ready to connect★ 2k
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.