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 60 of 81
- View details
cv-arcface-metric-learningSkillMonitoring & ops
ArcFace angular margin loss layer for learning discriminative embeddings — used in image retrieval, product matching, and face recognition
Ready to connect★ 61
- View details
cv-detectron2-custom-data-mapperSkillMonitoring & ops
Custom Detectron2 data mapper with photometric augmentations that properly transforms images, bounding boxes, and instance masks in sync
Ready to connect★ 61
- View details
cv-differentiable-soft-f1-lossSkillMonitoring & ops
Use a soft macro-F1 loss `1 − mean(2·tp / (2·tp + fp + fn))` computed from raw sigmoid probabilities (no thresholding) as a direct training objective for multi-label classification, optionally combined with BCE — closes the gap between training surrogate and the F1 metric the leaderboard scores
Ready to connect★ 61
- View details
cv-heavy-augmentation-pipelineSkillMonitoring & ops
Comprehensive albumentations augmentation combining geometric, photometric, noise, blur, and cutout transforms for robust CV training.
Ready to connect★ 61
- View details
cv-iou-weighted-assignment-metricSkillMonitoring & ops
Evaluation scorer that merges predictions with GT per frame, takes top-IoU match per GT, and computes weighted accuracy with IoU threshold gate
Ready to connect★ 61
- View details
cv-lap-hard-negative-miningSkillMonitoring & ops
Use linear assignment problem (LAP/lapjv) on a score matrix to select globally optimal hard-negative pairs for metric learning
Ready to connect★ 61
- View details
cv-learned-distance-metricSkillMonitoring & ops
Trainable nonlinear distance metric that transforms (v1-v2) and (v1-v2)^2 through a linear layer before computing squared norm
Ready to connect★ 61
- View details
cv-levenshtein-distance-metricSkillMonitoring & ops
Evaluates image-to-sequence models using mean Levenshtein edit distance between predicted and ground-truth strings.
Ready to connect★ 61
- View details
cv-middle-mip-std-volume-projectionSkillMonitoring & ops
Compress a 3D medical volume into a 3-channel 2D image by stacking the middle slice, the max-intensity projection across depth, and the per-pixel std across depth — a poor-man's volumetric encoding that lets any pretrained 3-channel 2D CNN ingest a whole series in a single forward pass
Ready to connect★ 61
- View details
cv-multi-scale-patch-training-pyramidSkillMonitoring & ops
Generate count-regression training patches at a geometric pyramid of image scales (0.9^k) so one CNN handles within- and between-image object-size variation without explicit anchors
Ready to connect★ 61
- View details
cv-separable-temporal-spectral-cnnSkillMonitoring & ops
2D CNN with asymmetric kernels — temporal convolutions (Nx1) then spectral convolutions (1xM) — to decouple time and feature extraction
Ready to connect★ 61
- View details
fred-performance-reviewerSkillMonitoring & ops
Review FRED changes for runtime performance, concurrency, and async correctness as an independent, skeptical senior reviewer. Use when reviewing anything on the agent execution loop, LLM call sites, tool invocation, KPI/log emission, middleware, shared clients (HTTP/model/DB), caches, or any code th
Ready to connect★ 61
- View details
live-observability-sessionSkillMonitoring & ops
Start Fred's backends and watch their logs/metrics/audit trail live while the developer drives the frontend/chat by hand. Use for manual observability or KPI test campaigns, or to diagnose a "does X actually log/emit/audit correctly" question against the three-stream model in OBSERVABILITY-AND-AUDIT
Ready to connect★ 61
- View details
longbridge-intelSkillMonitoring & ops
Market intelligence: strategy screener, popularity rankings, top movers with news correlation, quote anomalies, index/ETF constituent stocks, morning briefings, catalyst monitoring for watchlist, event-driven strategies, ETF fund flows, sector rotation, market microstructure, supply chain analysis,
Ready to connect★ 60
- View details
longbridge-watchlistSkillMonitoring & ops
Watchlist group management (list/create/rename/delete/add/remove symbols), price alerts (list/add/delete), and community stock lists (sharelist: list/detail/create/delete/manage) via Longbridge. Mutating operations require explicit user confirmation (dry-run protocol). Triggers: "自选股", "添加自选", "删除自选
Ready to connect★ 60
- View details
monitoring-specialistSkillMonitoring & ops
System monitoring, alerting, and observability implementation
Ready to connect★ 61
- View details
Complete Rust DevelopmentSkillMonitoring & ops
A comprehensive skill for Rust development that combines error handling, testing, and logging patterns. Demonstrates the 'includes' composition feature by merging content from multiple standalone skills.
Ready to connect★ 60
- View details
Logging PatternsSkillMonitoring & ops
Common logging patterns and practices. This skill is designed to be included in composite skills via the 'includes' feature.
Ready to connect★ 60
- View details
quant-analysisSkillMonitoring & ops
Quantitative finance analysis including portfolio optimization, risk modeling, and time series econometrics using jupyter_execute
Ready to connect★ 60
- View details
scoringSkillMonitoring & ops
Quantitative scoring framework for measuring audit quality with objective metrics to evaluate performance, track improvement over time, and identify areas needing attention. Use when benchmarking audit thoroughness, comparing engagement quality, or building quality gates into CI pipelines.
Ready to connect★ 60
- View details
syncfusion-maui-radial-gaugeSkillMonitoring & ops
Implements Syncfusion .NET MAUI Radial Gauge (SfRadialGauge) components. Use when working with radial gauges, circular gauges, speedometers, temperature monitors, meter gauges, or circular data visualization in .NET MAUI applications. This skill covers installation, axis configuration, ranges, point
Ready to connect★ 60
- View details
prioritizeSkillMonitoring & ops
Identify what to work on next. Reconciles candidate work against already-merged code BEFORE ranking, so stale/shipped ideas are dropped. Use when asked what to work on next, how to prioritize the backlog, or to triage ideas/tasks/incidents into a ranked shortlist.
Ready to connect★ 59
- View details
second-brain-graphSkillMonitoring & ops
Analyse the vault's link graph and report on its shape: orphan rate, average degree, components, hubs, bridges and clusters, with what each number means for retrieval. Use this skill when the user asks about the health or structure of their graph, wants metrics, asks which pages are most connected o
Ready to connect★ 57
- View details
second-brain-metricsSkillMonitoring & ops
Record a dated snapshot of the vault's health numbers and compare against previous snapshots so trends are visible. Use this skill for a monthly or quarterly check, when the user asks whether the vault is improving, or asks to track its numbers over time. Do NOT use for a one-off graph analysis, whi
Ready to connect★ 57
- View details
- View details
wrds-schemaSkillMonitoring & ops
Use this skill at the start of a session when working with WRDS data (CRSP, OptionMetrics, Compustat, TAQ). It pre-loads schema knowledge — table names, column names, join keys, data types, and common gotchas — so you can write correct queries without exploratory round-trips. Invoke when the user me
Ready to connect★ 59
- View details
ads-optimizerSkillMonitoring & ops
Facebook Ads optimization expert. Use for analyzing metrics, Health Score, ad-eater detection, and budget recommendations.
Ready to connect★ 58
- View details
agent-friendly-commandsSkillMonitoring & ops
Use these when you want low-noise lint/test output (good for LLM/CI logs) while staying aligned with repo policy.
Ready to connect★ 58
- View details
agent-lifecycle-managementSkillMonitoring & ops
Manage agent fleet through CRUD operations and lifecycle patterns. Use when creating, commanding, monitoring, or deleting agents in multi-agent systems, or implementing proper resource cleanup.
Ready to connect★ 58
- View details
agent-performanceSkillMonitoring & ops
Track and report agent invocation metrics including usage counts, success/failure rates, and completion times. Use for understanding which agents are utilized, identifying underused agents, and optimizing agent delegation patterns.
Ready to connect★ 58
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.