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 50 of 79
- View details
funnel-reporterSkillMonitoring & ops
End-to-end SaaS funnel reporting pulling live data from Humblytics API. Reports on traffic sources, page performance, signups, conversions, and (only when a revenue connector is attached, else 0) trial activations and revenue metrics. Use when checking funnel metrics, building reports, analyzing tra
Ready to connect★ 84
- View details
investigateSkillMonitoring & ops
Iron Law debugging — systematic root cause investigation before any fixes. Scope lock, pattern classification, hypothesis testing with 3-strike rule, structured DEBUG REPORT. Use when debugging, fixing bugs, or tracing unexpected behavior. Triggers on "debug this", "fix this bug", "why is this broke
Ready to connect★ 84
- View details
ioc-threat-huntSkillMonitoring & ops
Use when sweeping organizational logs and telemetry for specific indicators
Ready to connect★ 84
- View details
malware-incident-responseSkillMonitoring & ops
Use when coordinating response and remediation for advanced malware infections.
Ready to connect★ 84
- View details
malware-triageSkillMonitoring & ops
Use when analyzing malware detection alerts, isolating infected endpoints,
Ready to connect★ 84
- View details
scheduleSkillMonitoring & ops
Schedule recurring Claude/Codex agent jobs on the user's Outpost — structured checklist requirements, dm alert profile, status-aware list from hq-pro. Alias: /job (deprecated).
Ready to connect★ 84
- View details
- View details
triage-alertsSkillMonitoring & ops
Use when evaluating and categorizing incoming security alerts to determine
Ready to connect★ 84
- View details
competitor-watchSkillMonitoring & ops
Competitive intelligence, competitor tracking, market radar, weekly competitive digest, competitor deep dive, new entrant detection, watchlist. Logs every sighting of a tracked competitor or market shift that crossed your screen (posts, screenshots, demos, community threads, calls), ranks by velocit
Ready to connect★ 83
- View details
custom-distance-metricsSkillMonitoring & ops
Define custom distance/similarity metrics for clustering and ML algorithms. Use when working with DBSCAN, sklearn, or scipy distance functions with application-specific metrics.
Ready to connect★ 83
- View details
dbscan-custom-metricSkillMonitoring & ops
Run DBSCAN clustering with a custom distance metric using sklearn, including how to define weighted Euclidean metrics and extract cluster centroids.
Ready to connect★ 83
- View details
dbscan-custom-metricsSkillMonitoring & ops
Implement DBSCAN clustering with custom distance metrics using scikit-learn's pairwise_distances.
Ready to connect★ 83
- View details
exploded-view-illustrationSkillMonitoring & ops
Techniques for drawing isometric or orthographic exploded-view hardware diagrams programmatically using Pillow, with annotation leader lines and layer separation.
Ready to connect★ 83
- View details
geopandas-distance-analysisSkillMonitoring & ops
Calculate distances between geospatial points and boundaries using GeoPandas with proper metric projections (EPSG:4087).
Ready to connect★ 83
- View details
github-metrics-processingSkillMonitoring & ops
Process GitHub API data to calculate PR/issue metrics including merge time averages, author rankings, and bug categorization.
Ready to connect★ 83
- View details
glm-calibrationSkillMonitoring & ops
Calibration guidance for GLM tasks. Often most effective after glm-basics has clarified the setup; glm-output is the companion skill for exact final metric computation.
Ready to connect★ 83
- View details
ideateSkillMonitoring & ops
Take a fuzzy idea (or an existing thing you want to improve) through a disciplined funnel — explore → pressure-test → converge — and produce one living CONCEPT_BRIEF.md: a locked concept + phased roadmap. Acts as a blunt, honest co-founder (permission to overrule you), forces a success metric and a
Ready to connect★ 83
- View details
kanban-flow-stingerSkillMonitoring & ops
Kanban method specialist: WIP limit design and enforcement, flow-metric calculation (cycle time, lead time, throughput, flow efficiency), Little's Law diagnostics, visual-board design, class-of-service policies, cumulative-flow-diagram interpretation, and tool-specific implementation (Linear, Jira,
Ready to connect★ 83
- View details
kn-gameSkillMonitoring & ops
Turns stories or themes into game-style narrative videos. Use when the user mentions HD-2D, GBA, SNES, pixel RPG, live HUD, PS1 low-poly, voxel, isometric CRPG, cel-shading, visual novel, or arcade fighting; selects one of eleven game profiles and narrative mechanics.
Ready to connect★ 83
- View details
learning-capturerSkillMonitoring & ops
"Stop re-debugging the same wall, capture what I learned, log this fix, add
Ready to connect★ 83
- View details
model-calibrationSkillMonitoring & ops
Calculating RMSE metrics and parameter calibration for lake model validation
Ready to connect★ 83
- View details
pillow-technical-drawingSkillMonitoring & ops
Creating technical diagrams and exploded-view illustrations using Python Pillow with geometric primitives and text annotations.
Ready to connect★ 83
- View details
project-interview-skillSkillMonitoring & ops
Generates 导学.md and 面经.md in the project root; big-tech engineering-oriented, first-person spoken style (each answer ≥150 characters, complete STAR), one-sentence resume summary, repo-relative-path reading guide, and quantified metrics merged at the end (to be measured + how to measure). Triggers: 面
Ready to connect★ 83
- View details
auto-loopSkillMonitoring & ops
TDD-based autonomous development loop with checkpoint recovery and observability changelog
Ready to connect★ 82
- View details
case-studiesSkillMonitoring & ops
Use when turning one named customer's measured win into a case study, or the attributed testimonial quote that travels with it — consent-cleared, metrics-anchored proof for the next skeptical buyer. NOT the deck that sells the vision to a room (that is `pitch-deck`), NOT thought-leadership with no s
Ready to connect★ 82
- View details
changelogSkillMonitoring & ops
View and manage the runtime changelog for observability
Ready to connect★ 82
- View details
kpi-frameworkSkillMonitoring & ops
Use when a team must decide what to measure before building anything — picking one north-star metric, separating leading input drivers from lagging outputs, adding guardrails so a number cannot be gamed, and setting a target that is not arbitrary. NOT the live dashboard that displays them (that is `
Ready to connect★ 82
- View details
machine-learningSkillMonitoring & ops
Use when predicting a column from rows of tabular features with classic models — scikit-learn pipelines, RandomForest, XGBoost/LightGBM, leak-free cross-validation, metrics for imbalanced classes, or a model that aced CV then collapsed in production. NOT PyTorch neural nets (that is `deep-learning`)
Ready to connect★ 82
- View details
monitoringSkillMonitoring & ops
Use when setting up uptime and health monitoring, alerts, or on-call basics for a service already in production, so you learn it is down before customers do — health and readiness probes, alerting on SLO error-budget burn rather than raw counts, curing alert fatigue, on-call rotation with escalation
Ready to connect★ 82
- View details
go-middlewareSkillMonitoring & ops
Idiomatic Go HTTP middleware patterns with context propagation, structured logging via slog, centralized error handling, and panic recovery. Use when writing middleware, adding request tracing, or implementing cross-cutting concerns.
Ready to connect★ 81
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.