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
2,408 results · page 57 of 81
- View details
matrix-github-projectSkillMonitoring & ops
Clone, verify, reuse, and change GitHub repositories in observable project-scoped terminal tabs on a Matrix OS cloud computer. Use when a user supplies a GitHub repository, asks to continue work in an existing checkout, wants a Matrix app checkout, or requests code changes and validation on Matrix.
Ready to connect★ 67
- View details
orchestrate-problem-prsSkillMonitoring & ops
Decompose a structured or unstructured problem report into independently scoped workstreams, assign one subagent per accepted problem for read-only root-cause analysis, gate isolated draft PR implementation on evidence and a written plan, and shepherd every PR through worktree-pr-monitor. Use when a
Ready to connect★ 67
- View details
oversight-teamSkillMonitoring & ops
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn)
Ready to connect★ 67
- View details
requirements-writerSkillMonitoring & ops
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
Ready to connect★ 67
- View details
sre-reviewSkillMonitoring & ops
Evaluate operational readiness: SLOs, alerting, runbooks, and rollback plan before launch. Use when reviewing a feature for production readiness.
Ready to connect★ 67
- View details
worktree-pr-monitorSkillMonitoring & ops
Create or continue an isolated Matrix OS worktree PR, validate it, push it, monitor CI and GitHub review feedback, iterate until the latest trusted Greptile result is 5/5, then add ready-for-ci and wait for triggered CI to pass before pinging completion. Use when asked to run a worktree to PR to mon
Ready to connect★ 67
- View details
analyze-growthSkillMonitoring & ops
Growth analysis workflow — chain AARRR analysis, data reporting, growth strategy, and iteration planning Use when: Analyzing growth metrics, planning growth initiatives, or optimizing product performance
Ready to connect★ 66
- View details
- View details
bash-loggingSkillMonitoring & ops
This skill should be used when the user asks to "add logging to bash script", "colorize output", "implement log levels", "CI/CD sections", "terminal colors in bash", or mentions logging functions, emoji output, collapsible CI sections, or shlocksmith.
Ready to connect★ 66
- View details
create-backlog-itemSkillMonitoring & ops
Creates a new backlog item and routes through the work-backlog-item create workflow. Use when the user asks to add a backlog item, log a task, capture a feature request, or track a work item.
Ready to connect★ 66
- View details
enterprise-spring-xmlSkillMonitoring & ops
Dasel v3 selectors for Spring bean factory XML — use when querying any Spring ApplicationContext XML for bean discovery, dependency wiring, JMS destination mapping, property injection extraction, or cross-bean reference tracing. Load this skill before writing dasel selectors against Spring bean XML
Ready to connect★ 66
- View details
incident-handoffSkillMonitoring & ops
Summarize open incidents from the pager rotation and produce a morning handoff report. Use when the user asks for an incident summary, a handoff report, or the current pager status. Includes links to each incident, the owning team, current severity, and the latest status update for every open incide
Ready to connect★ 66
- View details
linear-walkthroughSkillMonitoring & ops
Produces a structured, end-to-end linear walkthrough of an unfamiliar codebase by orchestrating parallel subagents across four phases — discovery, tracing, validation, and synthesis. Use when onboarding to a new repository, understanding execution paths from entry points, generating navigable codeba
Ready to connect★ 66
- View details
log-analyzerSkillMonitoring & ops
Parse application logs, surface error clusters, and summarize failure patterns
Ready to connect★ 66
- View details
lov-checkpoint-listSkillMonitoring & ops
Summarizes checkpoints, time ranges, and evolution records from Git and project logs. Supports explicit input and result read-back. Use to list a project checkpoint.
Ready to connect★ 66
- View details
lov-fix-by-add-logSkillMonitoring & ops
Add minimal diagnostic logging for hard-to-reproduce issues and use the actual output to locate the root cause. Supports explicit inputs and result read-back. Use to debug a problem with targeted
Ready to connect★ 66
- View details
lov-human-writingSkillMonitoring & ops
Improve manuscripts using an authorial ledger, chapter-level audits, and 30 surface-level Chinese metrics, preserving genuine judgment while locating over-explanation, single-thread causality, and forced closure. Use when users say “去 AI 味”, “保留我的判断”, or "humanize this Chinese draft".
Ready to connect★ 66
- View details
lov-png2svgSkillMonitoring & ops
Convert PNG images to high-quality SVG with optional white-background removal, vtracer spline vectorization, and svgo compression. Use when the user asks for "PNG to SVG", "png2svg", "转 SVG", "矢量化", "去白底", logo tracing, or converting raster icons into editable vector assets.
Ready to connect★ 66
- View details
- View details
pm-aarrrSkillMonitoring & ops
Use when: the product has launched and you need to analyze user growth, develop growth strategies, diagnose product health, or optimize each stage of AARRR. Do NOT use when: the product has not launched, or only a single-metric analysis is needed without the full funnel.
Ready to connect★ 66
- View details
pm-dataSkillMonitoring & ops
Use when: you need to design product data metrics, plan data tracking, build a data monitoring system, or perform data analysis and trend forecasting. Do NOT use when: data metrics are already defined, or only simple statistics are needed without a metrics system.
Ready to connect★ 66
- View details
pm-funnelSkillMonitoring & ops
Use when: you need to analyze user conversion funnels, diagnose drop-off causes, generate optimization suggestions, and improve user conversion rates. Do NOT use when: the user conversion path is already very clear, or only a single metric needs monitoring without full-funnel analysis.
Ready to connect★ 66
- View details
pm-growthSkillMonitoring & ops
Use when: you need to develop growth strategies, optimize growth metrics, break through growth bottlenecks, or design systematic growth plans. Do NOT use when: the product is still in the validation phase and not yet launched, or when only single-channel optimization is needed rather than a systemat
Ready to connect★ 66
- View details
pythonSkillMonitoring & ops
Python coding standards for HAEO — modern syntax, type hints, async patterns, error handling, logging, docstrings, and lint suppression rules. Use when writing or modifying any Python code in this repository.
Ready to connect★ 66
- View details
sgc-skill-distillerSkillMonitoring & ops
Use when the user wants to distill project experience, incident retrospectives, and validated processes into a creatable Agent Skill blueprint, clarifying user outcomes, trigger boundaries, private information boundaries, and acceptance criteria; trigger words include "把经验蒸馏成 skill" and "distill exp
Ready to connect★ 66
- View details
simulationsSkillMonitoring & ops
Design, create, run, monitor, and maintain Vapi Simulations for assistants and squads. Use for simulation personalities, scenarios, structured-output success criteria, simulations, suites, chat or voice runs, tool mocks, target variables, lifecycle webhooks, regression coverage, CI quality gates, ru
Ready to connect★ 66
- View details
- View details
write-postmortemSkillMonitoring & ops
Postmortem authoring for production incidents.
Ready to connect★ 66
- View details
desk-incident-responseSkillMonitoring & ops
What the desk does when something goes wrong on Hyperliquid - unknown send results, unexpected fills or positions, unprotected positions, stuck or orphaned orders, API outages, rate limiting, and suspected API wallet compromise. Contain first, reconcile from the exchange record, act only through app
Ready to connect★ 65
- View details
desk-monitoringSkillMonitoring & ops
How the desk watches markets and the account between trades using Grok Bot routines and WebSocket or polling watches - the desk brief, book checks, funding and price watches, alert conditions and what a watch may and may not do. Use when the user asks for briefings, alerts, "watch X" or scheduled ch
Ready to connect★ 65
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.
53,585 of the 54,017 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.