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: Databases & data
2,461 results · page 58 of 83
- View details
snowflake-create-taskSkillDatabases & data
Consult Snowflake CREATE TASK parameter reference before generating any CREATE TASK DDL.
Ready to connect★ 77
- View details
snowflake-create-userSkillDatabases & data
Consult Snowflake CREATE USER parameter reference before generating any CREATE USER DDL.
Ready to connect★ 77
- View details
snowflake-create-viewSkillDatabases & data
Consult Snowflake CREATE VIEW parameter reference before generating any CREATE VIEW DDL.
Ready to connect★ 77
- View details
snowflake-create-warehouseSkillDatabases & data
Consult Snowflake CREATE WAREHOUSE parameter reference before generating any CREATE WAREHOUSE DDL.
Ready to connect★ 77
- View details
snowflake-data-analystSkillDatabases & data
Business rules and domain knowledge for answering natural-language data questions accurately against Snowflake.
Ready to connect★ 77
- View details
snowflake-naming-conventionsSkillDatabases & data
Enforces Snowflake object naming conventions before generating any DDL statement.
Ready to connect★ 77
- View details
streamSkillDatabases & data
Designing ETL/ELT pipelines, visualizing data flows, selecting batch/streaming approaches, and architecting Kafka/Airflow/dbt systems. Use when building data pipelines or managing data quality.
Ready to connect★ 77
- View details
technical-debtSkillDatabases & data
Technical debt inventory, prioritization, and audit for PHP/Laravel (MySQL) and Node/TypeScript/React projects. Use when assessing code health, identifying refactoring candidates, planning debt paydown, or auditing a codebase for accumulated debt. Triggers on "audit technical debt", "find tech debt"
Ready to connect★ 76
- View details
tunerSkillDatabases & data
Tuning database queries via EXPLAIN ANALYZE, query plan optimization, index recommendations, and slow query detection. Not for schema/migrations (Schema) or non-DB performance (Bolt).
Ready to connect★ 77
- View details
- View details
emblem-market-researchSkillDatabases & data
Crypto market intelligence via EmblemAI. Trending tokens, on-chain analytics, derivatives data, and smart money tracking from CoinGecko, CoinGlass, Birdeye, and Nansen. Use when the user wants market data, trending tokens, derivatives analytics, or on-chain intelligence.
Ready to connect★ 76
- View details
nansenSkillDatabases & data
Expert assistant for Nansen API — Smart Money analytics, wallet profiling, token intelligence across 37 blockchains (EVM + Solana + Bitcoin + Hyperliquid + more).
Ready to connect★ 76
- View details
xspoonai-official-database-migration-assistantSkillDatabases & data
Skills for Crypto
Ready to connect★ 76
- View details
financial-data-analysis-agentSkillDatabases & data
Use when analysts, finance teams, or operators need to clean financial datasets, check data quality, analyze revenue, margin, cash flow, customer value, anomalies, or trends, and produce traceable management-ready insights with confidence caveats.
Ready to connect★ 75
- View details
fix-merkle-root-mismatchSkillDatabases & data
Apply fixes for merkle root mismatch issues in the relayer database. Use after running /investigate-merkle-root-mismatch to investigate and identify the mismatched entries. Requires user confirmation before any database modifications.
Ready to connect★ 75
- View details
pr-sql-reviewerSkillDatabases & data
Use when the parent pipeline routes a sql-related PR review request. Reads the diff and emits structured sqlFindings using the sql specialist heuristics.
Ready to connect★ 75
- View details
diagnosing-analyticsSkillDatabases & data
Use when checking TraceDecay adoption or telemetry health — usage analytics, silent hooks, stale hook logs, or empty analytics tables. Uses the analytics, doctor, and sessions CLI, never raw database queries.
Ready to connect★ 74
- View details
introspecting-tracedecay-usageSkillDatabases & data
TraceDecay Dev: Use when turning TraceDecay's own analytics, session history, automation runs, managed skills, memory facts, diagnostics, or code-health signals into repo improvements, evals, or bundled skill updates.
Ready to connect★ 74
- View details
paper-initSkillDatabases & data
Builds a self-contained paper-context bundle for implementing a research paper — sources, transcription, figures, references (blocking citations fetched), an implementation spec with the reported results, open questions, dataset provenance — under paper/, with datasets in a gitignored data/. Warns w
Ready to connect★ 74
- View details
self-improving-from-usage-logsSkillDatabases & data
TraceDecay Dev: Use when mining TraceDecay session logs, analytics, diagnostics, automation artifacts, or agent transcripts to improve TraceDecay code, tools, or packaged skills.
Ready to connect★ 74
- View details
yandex-metrikaSkillDatabases & data
Use when working with Yandex Metrika (Yandex Metrica) analytics - retrieving traffic stats, managing counters and goals via API, setting up tracking code in web projects, building reports, analyzing conversions, or debugging counter issues. Triggers on mentions of Yandex Metrika, Metrica, web analyt
Ready to connect★ 74
- View details
api-designSkillDatabases & data
Guide API design following REST, GraphQL, and gRPC best practices. Use when: designing APIs, reviewing endpoints, API versioning decisions. Not for: verifying a running API against its consumers — use /contract-test; schema design behind the API — use /database. Keywords: API, REST, GraphQL, gRPC, e
Ready to connect★ 73
- View details
api-usageSkillDatabases & data
VScripts API usage conventions and workflows for Windy10v10AI (ApiClient, retry mechanism, Analytics event collection and sending patterns).
Ready to connect★ 73
- View details
ares-debugSkillDatabases & data
Diagnose a stuck, slow, or broken Ares operation by triangulating across three data sources — SSM (live ares logs + Redis on EC2), Grafana Loki (historical logs via mcp__grafana__query_loki_logs), and OTEL traces in Tempo. Use when an operation is hung/wedged, a worker keeps crashing, the orchestrat
Ready to connect★ 73
- View details
automation-ci-helperSkillDatabases & data
Instructions for managing CI pipelines, GitHub Actions workflows, Airflow DAGs, and automation scripts in the insurance analytics project.
Ready to connect★ 73
- View details
bear-querySkillDatabases & data
Query the Bear EHR database using the semantic layer. Use when asked about clients, billing, appointments, insurance, clinical data, procedures, scheduling, programs, staff, vitals, diagnoses, revenue, claims, or any data question about the Bear application.
Ready to connect★ 73
- View details
buildai-databaseSkillDatabases & data
Query the BuildAI PostgreSQL database (read-only). Returns results as JSON for construction project data — projects, RFIs, submittals, budgets, change orders, daily logs, punch lists, insurance, vendors, pay applications.
Ready to connect★ 73
- View details
claims-precedentsSkillDatabases & data
Database of insurance claim precedents and comparable settlements for evaluating claim values
Ready to connect★ 73
- View details
claims-workflowSkillDatabases & data
Analyze insurance claims workflow systems for intake optimization, adjudication rules, subrogation, litigation management, and settlement analytics. Use when: 'audit claims process', 'review FNOL workflow', 'evaluate claims automation', 'check subrogation recovery', 'assess claims fraud detection',
Ready to connect★ 73
- View details
cortex-importSkillDatabases & data
Import memories from other AI memory systems into Cortex. Supports claude-mem (SQLite), Claude Desktop sessions, ChatGPT web export (JSON), Gemini Takeout (JSON), Cursor conversations, and Claude Code JSONL. Use when the user says 'import from claude-mem', 'migrate memories', 'import ChatGPT history
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.