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
2,391 results · page 29 of 80
- View details
tailwind-v4-shadcnSkillMonitoring & ops
Set up Tailwind v4 with shadcn/ui using @theme inline pattern and CSS variable architecture. Four-step pattern: CSS variables, Tailwind mapping, base styles, automatic dark mode. Prevents 8 documented errors.
Ready to connect★ 391
- View details
tiptapSkillMonitoring & ops
Tiptap rich text editor for React and Next.js. Use when building or modifying rich text editors, @tiptap extensions, StarterKit, collaboration, comments, Content AI, import/export, or Pro extensions in this monorepo.
Ready to connect★ 391
- View details
turborepoSkillMonitoring & ops
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries.
Ready to connect★ 391
- View details
typescript-expertSkillMonitoring & ops
Lets your agent answer TypeScript and JavaScript questions and help with code optimization and migrations.
Ready to connect★ 391
- View details
api-ok-but-ignoredSkillMonitoring & ops
A remote write can answer "ok" and still have discarded what you sent, saying so only in a secondary field riding along with the success. Model accepted-but-discarded as its own outcome, read that field on every write, and log a discard loudly. Reach for it when a submission reports success on every
Ready to connect★ 315
- View details
curl-logger-ktor-pluginSkillMonitoring & ops
A client plugin that logs every outgoing request as one paste-ready curl command — POSIX single-quoting so a body full of quotes, dollars or newlines survives the shell, the whole command in a single log call, a redaction list, and a body read that does not consume a one-shot channel. Use when you w
Ready to connect★ 315
- View details
figure-it-outSkillMonitoring & ops
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migrati
Ready to connect★ 390
- View details
guard-on-every-trigger-pathSkillMonitoring & ops
Keep the start conditions of a feature that fires from two entry points — typically a polling loop and an end-of-item callback — identical on both paths, because a condition added to only one of them is dead code that produces no error, no log and no crash. Use when a newly added guard, exclusion or
Ready to connect★ 315
- View details
hoist-the-flag-not-the-animationSkillMonitoring & ops
Share the boolean that drives a fade, never the tween that runs it — each look derives its own curve, so one can go asymmetric (fast in, slow out) without changing how the other feels; covers why a symmetric linear fade over a bright backdrop makes container-backed controls read as the wrong colour,
Ready to connect★ 315
- View details
kmp-logger-facadeSkillMonitoring & ops
Put one small logging object in the shared module between every call site and the logging library, so a chatty subsystem can be silenced in one line and the library can be replaced without touching call sites. Covers the muted-tag set, a level-as-a-value enum for callers that pick severity at runtim
Ready to connect★ 315
- View details
login-state-fans-out-to-settingsSkillMonitoring & ops
Logging out must reset every setting that depended on being logged in, at the logout choke point itself — otherwise a gated switch stays on for a service you are no longer authenticated to and silently no-ops forever, or errors on every tick. Use when a feature toggle is stuck on, cannot be switched
Ready to connect★ 315
- View details
recallSkillMonitoring & ops
Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before start
Ready to connect★ 390
- View details
show-me-your-workSkillMonitoring & ops
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human review
Ready to connect★ 390
- View details
backfillSkillMonitoring & ops
Reconstruct an OKF bundle by event-sourcing a repository's history (git log and Claude session transcripts). Use when creating an `.okf/` bundle for an existing repository that predates this skill, or when resuming an interrupted backfill session. Triggers on: "reconstruct the OKF bundle", "backfill
Ready to connect★ 384
- View details
n8n-workflow-automationSkillMonitoring & ops
Designs and outputs n8n workflow JSON with robust triggers, idempotency, error handling, logging, retries, and human-in-the-loop review queues. Use when you need an auditable automation that won’t silently fail.
Ready to connect★ 383
- View details
parallel-dispatchSkillMonitoring & ops
Parallel execution engine for dispatching worker agents. Used by conductor-orchestrator to spawn multiple workers simultaneously from DAG parallel groups. Handles dispatch, monitoring, aggregation, and failure recovery.
Ready to connect★ 377
- View details
equity-researcherSkillMonitoring & ops
Institutional-grade investment research report generation skill. Covers listed companies in China A-shares, Hong Kong stocks, and US stocks. Output modes: 1) Investment Snapshot: 3-5 pages, including company overview, key financial metrics, valuation multiples, investment thesis, and risk factors; 2
Ready to connect★ 354
- View details
contactsSkillMonitoring & ops
Access phone contacts and call log. Use for looking up contact info or checking recent calls.
Ready to connect★ 372
- View details
locationSkillMonitoring & ops
Get device location via GPS or network. Use for location-aware actions, finding nearby places, or logging position.
Ready to connect★ 372
- View details
oneclickvirtSkillMonitoring & ops
OneClickVirt operations skill for managing containers, virtual machines, provider nodes, health checks, and metrics through MCP.
Ready to connect★ 371
- View details
fundamentalsSkillMonitoring & ops
Get fundamental financial data including financials, earnings, and key metrics. Use when user asks about financials, earnings, revenue, profit, balance sheet, income statement, or company fundamentals.
Ready to connect★ 364
- View details
ib-stop-lossSkillMonitoring & ops
Downside stop-loss management for PMCC, naked LEAPS, and stock positions in IB. Computes stop prices, detects alerts, and places conditional combo orders. Dry-run by default. Requires TWS or IB Gateway running locally.
Ready to connect★ 364
- View details
risk-assessmentSkillMonitoring & ops
Assess risk metrics for a stock or position including volatility, beta, VaR, and drawdown analysis. Use when user asks about risk, volatility, beta, VaR, value at risk, drawdown, or position sizing.
Ready to connect★ 364
- View details
crypto-analysisSkillMonitoring & ops
Use when assessing cryptography — TLS/PKI auditing, RSA/ECC key attacks, ECDSA nonce lattice recovery, symmetric/AEAD misuse, JWT/JOSE forgery, hash cracking, post-quantum migration review
Ready to connect★ 363
- View details
geopandas-geospatialSkillMonitoring & ops
Geospatial vector analysis extending pandas. Read/write spatial formats (Shapefile, GeoJSON, GeoPackage, Parquet, PostGIS), CRS handling, geometric ops (buffer, simplify, centroid, affine), spatial analysis (joins, overlays, dissolve, clipping, distance), visualization (choropleth, interactive maps,
Ready to connect★ 363
- View details
mobile-pentestSkillMonitoring & ops
Use when pentesting an Android/iOS app — Frida 17 instrumentation, SSL-pinning & root/jailbreak bypass, Android 14/15 CA injection, exported-component/content-provider abuse, deep-link/WebView chains, biometric bypass, Flutter/React-Native RE
Ready to connect★ 363
- View details
scikit-image-processingSkillMonitoring & ops
Python image processing for microscopy and bioimage analysis. Read/write images, filter (Gaussian, median, LoG), segment (thresholding, watershed, active contours), measure region properties, detect features. SciPy/NumPy ecosystem. Use OpenCV for real-time video; CellPose for DL cell segmentation; n
Ready to connect★ 363
- View details
spikeinterface-electrophysiologySkillMonitoring & ops
Unified Python framework for extracellular electrophysiology. Load 20+ formats (SpikeGLX, OpenEphys, NWB, Intan, Maxwell, Blackrock), preprocess, run 10+ sorters (Kilosort4, SpykingCircus2, Tridesclous, MountainSort5) via one API, compute quality metrics (SNR, ISI, firing rate), compare sorters, exp
Ready to connect★ 363
- View details
umap-learnSkillMonitoring & ops
Lets your agent run UMAP to reduce high-dimensional data to 2D or 3D embeddings for clustering or visualization.
Ready to connect★ 363
- View details
Pair ProgrammingSkillMonitoring & ops
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performanc
Ready to connect★ 357
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.
53,462 of the 53,895 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.