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
2,430 results · page 68 of 81
- View details
llama-cppSkillMonitoring & ops
Run GGUF models directly, load LoRA adapters, benchmark inference speed, and serve models via llama-server using llama.cpp. Includes Qwen 3.5 serve scripts (9B dense + F16, 35B MoE) with asymmetric KV cache and thinking mode. Secondary to Ollama; use when needing direct model control or LoRA hot-loa
Ready to connect
- View details
run-servicesSkillMonitoring & ops
Start / stop / debug multiple microservices of go-hichat-api. Triggered when the user mentions services, running the backend, viewing logs, or stopping services.
Ready to connect
- View details
runtime-triageSkillMonitoring & ops
Triage a JellyRock runtime failure (crash, freeze, unexpected behavior) from a pasted Roku log / crash report end-to-end. Parses the log, classifies the failure category (render-thread-crash / task-crash / api-error / registry-corruption / nav-error / unknown), maps to the probable code area, writes
Ready to connect
- View details
sprite-forgeSkillMonitoring & ops
Generate game sprites, SVG characters, ASCII art, animated mascots, and isometric turnarounds from images or descriptions. Five output modes: SVG characters, game sprite sheets with atlas metadata, 8-way isometric turnarounds, ASCII/Unicode terminal art, GSAP-animated mascots. Triggers on sprite, pi
Ready to connect
- View details
tdmcp-bridge-endpointSkillMonitoring & ops
Build a tdmcp TouchDesigner-bridge vertical slice the house way — promote an op from /api/exec to a first-class REST endpoint (e.g. POST /api/connect, GET /api/logs, node_detail flags), add its typed method in src/td-client/touchDesignerClient.ts, its Zod envelope in src/td-client/validators.ts, rew
Ready to connect
- View details
cypress-tapSkillMonitoring & ops
Drives a running Cypress open-mode session through `cypress tap` to run and rerun specs, wait for fresh results, inspect reporter and command logs, and query or rewind the app under test through DOM, accessibility, styles, and snapshots. Use when authoring or debugging Cypress e2e or component specs
Ready to connect
- View details
rootnode-domain-software-engineeringSkillMonitoring & ops
Specialized software engineering prompt methodology for Claude. Use when building prompts for system design, code review, incident response, security analysis, API design, architecture decisions, RFCs, ADRs, runbooks, or technical leadership. Trigger on: "build a prompt for code review," "system des
Ready to connect
- View details
acronisSkillMonitoring & ops
The first real CLI for the Acronis Cyber Protect Cloud platform - every tenant, agent, and usage metric mirrored locally, with cross-tenant rollups no single API call returns. Trigger phrases: `acronis backup health across tenants`, `find offline acronis agents`, `acronis usage and billing report`
Ready to connect
- View details
Ahrefs Backlink Content PlannerSkillMonitoring & ops
Leverages Ahrefs REST API v3 to identify content gap opportunities through competing domain analysis. Pulls referring domains data, anchor text distributions, and DR metrics to prioritize content creation for link-worthy topics.
Ready to connect
- View details
Ansible Playbook Diagnostics RunnerSkillMonitoring & ops
Runs Ansible diagnostic playbooks using ansible-runner and the Ansible Collections ecosystem (ansible.builtin, community.general). Captures system health, service status, and log analysis across inventory hosts.
Ready to connect
- View details
Apache Kafka Consumer Lag RunbookSkillMonitoring & ops
Diagnoses Kafka consumer group lag using the Kafka AdminClient API and JMX metrics exposed via the Confluent Metrics API. Identifies slow consumers, topic partition hotspots, and broker rebalance storms that contribute to lag growth. Provides a step-by-step runbook to tune fetch.min.bytes, max.poll.
Ready to connect
- View details
ArgoCD Application Sync MonitorSkillMonitoring & ops
Monitors ArgoCD application sync status via the ArgoCD REST API and argocd CLI. Detects OutOfSync conditions, tracks sync wave progress, and alerts on failed sync operations with detailed resource diff analysis using argocd app diff.
Ready to connect
- View details
crowdstrikeSkillMonitoring & ops
Every CrowdStrike Falcon MSP operation, plus a Flight-Control-aware local store that answers fleet-wide questions across all your tenants at once - something no other Falcon tool (including the official MCP server) does. Trigger phrases: `check crowdstrike alerts across all tenants`, `show stale f
Ready to connect
- View details
gradientSkillMonitoring & ops
The Synthesize partner API from the terminal - every endpoint, plus a usage-push ledger, billing drift detection, and alert-to-ticket tracing no other Gradient tool has. Trigger phrases: `push usage counts to gradient`, `sync usage to synthesize`, `check my synthesize integration status`, `find unma
Ready to connect
- View details
huntressSkillMonitoring & ops
Every Huntress endpoint, plus fleet-wide incident, coverage, and billing rollups the API can't. Trigger phrases: `show me all critical huntress incidents`, `huntress coverage gaps across my orgs`, `huntress blast radius for this IP`, `reconcile huntress billing`, `huntress agent health report`, `use
Ready to connect
- View details
skykickSkillMonitoring & ops
Fleet-wide M365 backup assurance for SkyKick Cloud Backup - posture, stale snapshots, and coverage gaps no portal or wrapper can show. Trigger phrases: `check skykick backups`, `which customers aren't backed up`, `stale skykick snapshots`, `skykick fleet health`, `skykick backup alerts`, `audit m365
Ready to connect
- View details
threatlockerSkillMonitoring & ops
Every ThreatLocker Portal API feature, plus the write operations the read-only tools lack and a cross-tenant offline store no other ThreatLocker tool has. Trigger phrases: `triage threatlocker approvals`, `approve this hash across all tenants`, `export the threatlocker audit log`, `which threatlocke
Ready to connect
- View details
alert-analysisSkillMonitoring & ops
Analyze operational alerts including severity assessment, pattern recognition, noise reduction, alert correlation, grouping, suppression rules, and root cause indicators
Ready to connect
- View details
artSkillMonitoring & ops
Make procedural isometric art that reads as designed rather than as programmer output — buildings, trees, towers, terrain shading, palettes, day and night. Use when drawing a building, sprite, tree, tower or any object in an isometric game, when the art looks flat, gray, muddy, toy-like or like plac
Ready to connect
- View details
article-generationSkillMonitoring & ops
Generate knowledge articles from resolved incidents, problem records, and change implementations with proper KB structure including symptoms, cause, resolution, and related articles
Ready to connect
- View details
bodySkillMonitoring & ops
Body metrics: weight, blood pressure, BMI, body composition. Trends and correlations with WHOOP. Triggers: «вес», «давление», «BMI», «взвесился», «измерил давление», «body metrics»
Ready to connect
- View details
cisco-intersight-setupSkillMonitoring & ops
Use when configuring or validating Cisco Intersight audit, inventory, alarm, or metrics inputs in Splunk.
Ready to connect
- View details
content-recommendationSkillMonitoring & ops
Recommend relevant knowledge articles based on incident or case context by matching keywords, categories, and historical resolution patterns to surface the most useful articles
Ready to connect
- View details
daySkillMonitoring & ops
Starts a work session with health-os: delta since last time, data integrity check, alerts, and 2–3 recommendations for today. Not for a full status snapshot — use /status for that. Not for ending a session — use /wrap-up for that. Triggers: "day", "начнём день", "стартуем", "что сегодня", "с чего на
Ready to connect
- View details
fleet-waveSkillMonitoring & ops
Run ONE wave of N fak-guarded ultracode sessions against the top open issues under a closing target and a wall-clock deadline — price, render fuel, launch, monitor, reconcile from git, release. N defaults to 30 (30...
Ready to connect
- View details
gap-analysisSkillMonitoring & ops
Analyze knowledge gaps by examining incident and case patterns without matching KB articles, identify topics needing new articles, track failed searches, and prioritize article creation
Ready to connect
- View details
generate-talking-pointsSkillMonitoring & ops
Generate manager talking points for employee reviews, 1:1 meetings, and performance discussions based on talent profiles, goals, feedback, and performance metrics
Ready to connect
- View details
health-safety-summarizationSkillMonitoring & ops
Summarize Health and Safety incidents with injury details, root cause analysis, OSHA reporting requirements, corrective actions, and workplace hazard tracking
Ready to connect
- View details
incident-lifecycleSkillMonitoring & ops
Complete incident lifecycle management from creation through resolution and closure
Ready to connect
- View details
incident-triageSkillMonitoring & ops
Triage, prioritize, and assign incidents by impact, urgency, category, escalation risk, ownership, and SLA exposure.
Ready to connect
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.
54,764 of the 55,196 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.