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 54 of 81
- View details
code-refactoring-advisorSkillMonitoring & ops
Enterprise code refactoring advisor that detects code smells, anti-patterns, and complexity issues with specific refactoring recommendations, test generation, and maintainability metrics
Ready to connect★ 76
- View details
defiSkillMonitoring & ops
Interact with DeFi protocols on MAINNET via the ChainGPT plugin. Aave V3 (supply/borrow/repay/withdraw + health-factor monitoring across 7 chains), Lido stETH staking, EigenLayer restaking. Yield discovery: Pendle yield-trading markets (PT/YT), Morpho Blue lending markets + MetaMorpho vaults. Custod
Ready to connect★ 76
- View details
defi-safety-shieldSkillMonitoring & ops
Comprehensive DeFi safety monitoring - scan tokens for risks, detect phishing, audit wallet approvals, and score protocol safety
Ready to connect★ 76
- View details
emblem-memecoin-scoutSkillMonitoring & ops
Memecoin discovery and risk assessment via EmblemAI. Trending memecoins on Solana, Base, and Hedera. Pump.fun and LaunchLab new token alerts, Clanker discovery, rug-pull detection, holder analysis, and smart money tracking. Use when the user wants to find new memecoins, check if a token is a rug pul
Ready to connect★ 76
- View details
hyperliquidSkillMonitoring & ops
Read live Hyperliquid mainnet data via the ChainGPT plugin. Markets / mids / orderbook / wallet account state / fills / funding-rate history. Use for perp position monitoring, market scanning, account auditing, and funding-rate analysis. Read-only in v1.6 — signed order placement (EIP-712 L1 actions
Ready to connect★ 76
- View details
privacy-layerSkillMonitoring & ops
Privacy-preserving operations for crypto agents. Covers ZK-SNARK private transfers via Railgun Protocol, shielded balances, network egress monitoring, and confidential transaction patterns. Use when asked about private transfers, shielded transactions, or agent privacy.
Ready to connect★ 76
- View details
debug-rpc-providerSkillMonitoring & ops
Debug RPC provider health issues for a chain. Use when alerts mention RPC failures, high latency, stale blocks, or provider errors. Diagnoses the issue and recommends fixes.
Ready to connect★ 75
- View details
debug-validator-checkpoint-inconsistencySkillMonitoring & ops
Debug validator checkpoint inconsistencies where some validators are behind others. Use when alerts mention "checkpoint inconsistency", "validators behind", or "inconsistent latest checkpoints", or when asked to debug validator sets, investigate validator delays, or troubleshoot metadata fetch failu
Ready to connect★ 75
- View details
investigate-merkle-root-mismatchSkillMonitoring & ops
Investigate merkle root mismatch alerts between relayer and validators. Use when alerts mention "merkle root mismatch", "checkpoint root does not match canonical root", or when asked to debug relayer merkle tree issues for a chain. This skill only investigates - use /fix-merkle-root-mismatch to appl
Ready to connect★ 75
- View details
pr-logging-reviewerSkillMonitoring & ops
Use when the parent pipeline routes a logging-related PR review request. Reads the diff and emits structured loggingFindings using the logging specialist heuristics.
Ready to connect★ 75
- View details
pr-metrics-reviewerSkillMonitoring & ops
Use when the parent pipeline routes a metrics-related PR review request. Reads the diff and emits structured metricsFindings using the metrics specialist heuristics.
Ready to connect★ 75
- View details
pr-observability-reviewerSkillMonitoring & ops
Use when the parent pipeline routes a observability-related PR review request. Reads the diff and emits structured observabilityFindings using the observability specialist heuristics.
Ready to connect★ 75
- View details
pr-tracing-reviewerSkillMonitoring & ops
Use when the parent pipeline routes a tracing-related PR review request. Reads the diff and emits structured tracingFindings using the tracing specialist heuristics.
Ready to connect★ 75
- View details
warp-key-value-expansionSkillMonitoring & ops
Canonical legend for expanding a `<KEY_<PROTOCOL>_VALUE>` placeholder into a shell substitution based on the key-context artifact's `source` field, plus the mandatory `pnpm --silent` rule that keeps the resolved key out of logs and the display-the-key-name-before-CONFIRM disclosure. Referenced by ev
Ready to connect★ 75
- View details
sdlc-bug-reportSkillMonitoring & ops
Workflow for analyzing bug reports, tracing root causes, and generating structured bug-fix implementation plans with rollback strategies.
Ready to connect★ 73
- View details
tdd-bug-reportSkillMonitoring & ops
Workflow for analyzing bug reports, tracing root causes, and generating structured bug-fix implementation plans enforcing the Prove-It pattern (failing regression test first) with rollback strategies.
Ready to connect★ 73
- View details
tracedecay-dev-sweepSkillMonitoring & ops
TraceDecay Dev: Use for a full introspection-and-improvement pass over TraceDecay itself — triggers every dev skill in dependency order (diagnostics gate, evidence sweep across usage/logs/automation/hints/code-health, synthesis, fixes, verification). Use when asked to 'improve tracedecay from its ow
Ready to connect★ 74
- View details
tracing-functionsSkillMonitoring & ops
Use when the task is call-relationship shaped: "who calls X", "what does X call", "trace this", references before a rename, shortest path, recursion, or hubs. Trigger before grepping a function name — grep misses dynamic dispatch. Do NOT use to locate a symbol (tracedecay:exploring-code).
Ready to connect★ 74
- View details
analyzing-catastrophe-riskSkillMonitoring & ops
Structures catastrophe risk assessment with model output interpretation and accumulation monitoring. Use when analyzing cat risk, interpreting cat model results, or managing cat exposure.
Ready to connect★ 73
- View details
analyzing-insurance-financialsSkillMonitoring & ops
Structures insurance company financial analysis with combined ratio, reserve adequacy, and capital metrics. Use when analyzing insurance financials, evaluating combined ratios, or assessing reserve strength.
Ready to connect★ 73
- View details
anti-fraud-screeningSkillMonitoring & ops
Use this skill when the user needs insurance fraud risk screening. Suitable for scenarios such as application fraud identification, claims fraud alerts, and suspicious behavior analysis.
Ready to connect★ 73
- View details
arckit-uae-pdplSkillMonitoring & ops
[COMMUNITY] Generate a UAE PDPL (Federal Decree-Law 45/2021) compliance assessment including DPIA, lawful-basis register, data-subject-rights procedure, and cross-border transfer log. Anchored on the UAE Data Office statutory framework.
Ready to connect★ 73
- View details
ares-grafanaSkillMonitoring & ops
Reference for Grafana dashboards and specific Loki queries used to monitor and debug Ares operations via the grafana MCP server. Use when you need to handily check operation health, errors, agent restarts, or loot discovery.
Ready to connect★ 73
- View details
bankruptcy-monitor-qccSkillMonitoring & ops
Bankruptcy warning and bankruptcy reorganization monitoring SKILL · Qichacha MCP V2.0 enhanced edition. A continuous monitoring tool for bankruptcy risk of key customers, debtors, and guarantors, covering two sub-scenarios: 'bankruptcy early warning' (ex-ante identification) and 'bankruptcy reorgani
Ready to connect★ 73
- View details
breach-credit-monitorSkillMonitoring & ops
Coordinates credit monitoring and identity theft protection services for individuals affected by a data breach. Covers vendor selection criteria, enrollment logistics, coverage duration (12-24 months), identity theft insurance options, communication to affected individuals, and enrollment rate track
Ready to connect★ 73
- View details
discoverSkillMonitoring & ops
[UDS] Assess project health, architecture, and risks before adding features to an existing codebase. Use when: onboarding to an unfamiliar or legacy project, sizing risk before starting a feature, building a risk register. Not for: ongoing metric tracking on a codebase you already know — use /metric
Ready to connect★ 73
- View details
durableSkillMonitoring & ops
[UDS] Guide fault-tolerant workflow design with checkpoints, retry policies, and rollback plans. Use when: a long-running workflow keeps failing partway, designing checkpoint granularity, choosing a retry or backoff strategy. Not for: responding to a production incident already in progress — use /in
Ready to connect★ 73
- View details
error-code-guideSkillMonitoring & ops
Design consistent error codes following the PREFIX_CATEGORY_NUMBER format. Use when: defining error codes, creating error handling, designing APIs. Not for: log format and levels — use /logging-guide; handling errors that already reached production — use /incident. Keywords: error code, error handli
Ready to connect★ 73
- View details
investigation-memo-zhou210712SkillMonitoring & ops
Drafts or updates an investigation memo from the investigation log. Use when the investigation has progressed enough to write a first draft of the memo, or when new data has been added and the existing draft needs updating.
Ready to connect★ 73
- View details
leave-tracker-zhou210712SkillMonitoring & ops
Check leaves in progress, with deadline alerts and decisions that need to be made. Presents only the leaves that need action and explains why—not a status dashboard. Recommended to run weekly, or whenever a lawyer needs to know which leaves have upcoming approvals, certifications, or expiration dead
Ready to connect★ 73
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.