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 35 of 80
- View details
testdriver:debugging-with-screenshotsSkillMonitoring & ops
Diagnose failing tests with screenshots, replays, and logs
Ready to connect★ 242
- View details
a-share-alpha-decaySkillMonitoring & ops
A-share Alpha decay / factor crowding analysis. Triggered when the user says "Alpha衰减", "alpha decay", "因子拥挤", "策略容量", "因子失效", "XX因子还有效吗", "crowding", or "策略拥挤". Analyzes the decay trend of a factor's/strategy's Alpha over time, factor crowding metrics, and strategy capacity limits. Supports a resea
Ready to connect★ 242
- View details
a-share-anomaly-detectionSkillMonitoring & ops
Anomaly detection / unusual-activity monitoring for A-share price and volume. Triggered when the user says "异常检测", "异动", "anomaly", "量价异常", "异常波动", "XX有异动". Quantitatively detects anomalies in stock price and trading volume. Supports formal and brief styles.
Ready to connect★ 242
- View details
a-share-black-swanSkillMonitoring & ops
A-share black swan alerts / extreme event analysis. Triggered when the user says "黑天鹅", "black swan", "极端事件", "尾部事件", "灰犀牛", "突发风险", or "系统崩溃". Retrieves data based on cn-stock-data to monitor and provide early warnings for potential black swan events. Supports two output styles: formal/brief.
Ready to connect★ 242
- View details
a-share-drawdown-analysisSkillMonitoring & ops
A-share drawdown analysis / max drawdown quantification / drawdown statistics. Triggered when the user says "回撤", "drawdown", "最大回撤", "回撤分析", "回撤统计", "历史回撤", "水下曲线", "亏了多少", "从高点跌了多少", "回撤修复", "回撤天数". MUST USE when user asks about drawdown metrics, max drawdown calculation, or historical drawdown an
Ready to connect★ 242
- View details
a-share-factor-analysisSkillMonitoring & ops
A-share single-factor research / IC testing. Triggered when the user says "因子分析", "单因子", "IC", "IR", "因子检验", "factor analysis", "因子有效性", "XX因子表现怎么样", "因子IC", "因子收益", "因子衰减", "quintile分析". Uses cn-stock-data to fetch market and financial data for the stock pool, and computes quantitative metrics such
Ready to connect★ 242
- View details
a-share-margin-riskSkillMonitoring & ops
A-share margin risk / leverage monitoring. Triggered when the user says "保证金", "margin", "杠杆", "爆仓", "追保", "维持担保比例", "强平", or "杠杆率". Uses cn-stock-data to fetch data and monitor margin and leverage risk. Supports both formal and brief output styles.
Ready to connect★ 242
- View details
a-share-risk-alertSkillMonitoring & ops
A-share risk alert / ST alert / delisting risk screening. Triggered when the user says "风险预警" (risk alert), "有没有风险" (any risks?), "会不会ST" (will it get ST'd?), "退市风险" (delisting risk), "爆雷" or "暴雷" (blowup), "风险排查" (risk screening), "XX安全吗" (is XX safe?), "财务造假" (financial fraud), or "审计意见" (audit op
Ready to connect★ 242
- View details
alphafoldSkillMonitoring & ops
Use when running AlphaFold2 predictions on custom protein sequences, validating designed sequences via self-consistency, predicting binder-target complexes, or interpreting AF2 confidence metrics (pLDDT, pTM, ipTM).
Ready to connect★ 242
- View details
dftSkillMonitoring & ops
Submit, monitor, and retrieve DFT calculations on Artemis/SLURM via DREAMS framework
Ready to connect★ 242
- View details
geometry-generatorSkillMonitoring & ops
Generate parametric bioinspired ribbed membrane STL geometry via LLM-guided design. Takes a spec JSON (from StructureAnalyst/PropertyPredictor upstream artifacts), calls the LLM with a structured CAD prompt to produce design parameters, then builds a triangulated STL mesh in Python. Returns artifact
Ready to connect★ 242
- View details
hpcSkillMonitoring & ops
SLURM HPC job management on Artemis — write submission scripts, submit jobs, monitor status, retrieve results
Ready to connect★ 242
- View details
autoresearch-loopSkillMonitoring & ops
Domain-agnostic metric-driven improvement loop, generalizing Karpathy's autoresearch. Use when you want an agent to discover what to measure for a project/goal, then run a keep-or-revert experiment loop that proposes changes, measures them against an objective, keeps wins, discards regressions, and
Ready to connect★ 241
- View details
checking-code-qualitySkillMonitoring & ops
Checks code quality metrics including complexity, duplication, naming conventions, and function length. Use when running quality gates, reviewing code smells, or checking lint rules. Automatically triggered on complex modules or post-refactor.
Ready to connect★ 240
- View details
task-orchestratorSkillMonitoring & ops
Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large projects with multiple issues/tasks that need coordinated parallel execution.
Ready to connect★ 241
- View details
ralphSkillMonitoring & ops
Iterative measurement-driven improvement loop. Measure, profile, mutate, re-measure, commit. Works for performance, bundle size, complexity, test coverage — anything quantifiable. Use when the user wants to systematically improve a metric through repeated cycles of profiling and targeted changes.
Ready to connect★ 240
- View details
levyra-android-reverse-engineeringSkillMonitoring & ops
Mandatory Levyra workflow for lawful Android artifact decompilation, APK/XAPK/AAB/DEX/JAR/AAR analysis, API extraction, compiled call-flow tracing, obfuscation analysis, and authorized dynamic diagnostics.
Ready to connect★ 237
- View details
levyra-context-efficiencySkillMonitoring & ops
Use for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup, cross-domain exploration, or useful cross-session retrieval. Reduce token waste without reducing engineering rigor.
Ready to connect★ 237
- View details
levyra-security-reviewSkillMonitoring & ops
Perform an evidence-based Levyra security review and Codex Security workflow covering threat modeling, attack paths, validation, remediation, revalidation, secrets, provider URLs, redirects, SSRF, MIME confusion, permissions, privacy, logging, workflows, dependency changes, update verification, and
Ready to connect★ 237
- View details
smell-checkSkillMonitoring & ops
Runs a smell-first audit on a user-chosen path set: measures structure metrics, applies a named size profile, and reports code smells and test smells with evidence strength. Use for smell audit, code smell scan, whole-repo audit, tech debt scan, test smell check, maintainability audit, or duplicatio
Ready to connect★ 237
- View details
apple-higSkillMonitoring & ops
Lets your agent look up Apple's official interface design guidelines when building or reviewing apps.
Ready to connect★ 236
- View details
xcode-controlSkillMonitoring & ops
Control the running Xcode session to build, clean, test, run, and inspect build logs or errors via AppleScript. Use as a direct CLI replacement for the Xcode MCP bridge when developing swmpc, widgets, or schemes in an open Xcode workspace.
Ready to connect★ 236
- View details
education-data-source-fsaSkillMonitoring & ops
FSA — Title IV aid at institution level (~5,500 institutions, 1999-2021). Pell Grants, Direct/PLUS loans, campus-based aid, financial responsibility scores, 90/10 metrics. Use for aid distribution, loan volume, or for-profit analysis. By unitid.
Ready to connect★ 235
- View details
scikit-learnSkillMonitoring & ops
Machine learning: clustering, PCA/t-SNE/UMAP, classification, prediction regression (Ridge/Lasso/ensemble), cross-validation, Pipelines. For unsupervised analysis, classification, or prediction. For econometric regression use pyfixest/statsmodels. R equivalent: tidymodels (use when execution languag
Ready to connect★ 235
- View details
asymmetric-ability-commit-evade-impact-proofSkillMonitoring & ops
Create original short videos using the 速度对蛮力的非对称证明｜重击承诺、连续闪避与环境撞击 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.
Ready to connect★ 225
- View details
asymmetric-route-cost-overtake-proofSkillMonitoring & ops
Create original short videos using the 外线超车证明｜并排行驶、较长路线与车头领先 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.
Ready to connect★ 225
- View details
asymmetric-scale-evasion-exchangeSkillMonitoring & ops
Create original short videos using the 巨体攻防｜共享空间中的连续闪避 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.
Ready to connect★ 225
- View details
better-auth-security-best-practicesSkillMonitoring & ops
Configure rate limiting, manage auth secrets, set up CSRF protection, define trusted origins, secure sessions and cookies, encrypt OAuth tokens, track IP addresses, and implement audit logging for Better Auth. Use when users need to secure their auth setup, prevent brute force attacks, or harden a B
Ready to connect★ 230
- View details
breach-resistance-with-asymmetric-forceSkillMonitoring & ops
Create original short videos using the 非对称突破｜密集阻力到空间制度改变 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.
Ready to connect★ 225
- View details
fiction-to-production-layer-monitor-revealSkillMonitoring & ops
Create original short videos using the 叙事拆幕｜情绪场景连续退到片场与监看层 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects and surfaces.
Ready to connect★ 225
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.