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
2,394 results · page 79 of 80
- View details
data-seedingSkillDatabases & data
Create or update database seed scripts for development and testing environments. Use when setting up test data, initializing development databases, creating demo environments, resetting to known state, or generating realistic sample data.
Ready to connect
- View details
database-securitySkillDatabases & data
Lets your agent run authorized security checks on databases like PostgreSQL, MySQL, and Redis to find exposure and misconfigurations.
Ready to connect
- View details
dbt-custom-generic-testSkillDatabases & data
Implement or refactor a dbt custom generic data test using this package’s patterns (test block, adapter.dispatch, BigQuery-only implementations, macro property YAML, integration_tests fixtures). Use when adding a new generic test, splitting test/query/validation macros, fixing undefined test_* macro
Ready to connect
- View details
devlab-dao-sql-compatSkillDatabases & data
General-purpose SQL dialect compatibility check and systematic fix workflow for the DAO layer. Supports four persistence frameworks: MyBatis/JPA/MyBatis-Plus/SQLAlchemy. Scans source code to identify risks of mixing Oracle/PostgreSQL/MySQL dialects, automatically fixes 80% of common pitfalls, with t
Ready to connect
- View details
devlab-db-data-migrationSkillDatabases & data
Expert skill for safe database data-layer migrations. Covers the full safe workflow for schema evolution (adding columns / changing constraints / creating indexes) and data migration: backup → idempotency checks → migration → verification → rollback on failure. Use when a project needs to alter exis
Ready to connect
- View details
diag-mysql-deadlockSkillDatabases & data
Full-chain MySQL deadlock diagnostics. Captures InnoDB deadlock status, parses lock chains (who holds what, who waits on what), classifies deadlock patterns (AB-BA / Gap Lock / FK cascade / Auto-Inc), finds current lock waits and long-running transactions, and outputs a structured report with fix re
Ready to connect
- View details
diag-mysql-replicationSkillDatabases & data
Full-chain diagnosis of MySQL primary-replica replication lag. Checks replication status, identifies the root cause of lag (large transactions / network / replica load / binlog format / parallel replication configuration), and outputs a structured report with fix recommendations. Supports async, sem
Ready to connect
- View details
diag-mysql-slow-querySkillDatabases & data
End-to-end diagnosis of MySQL slow queries. Enable/analyze the slow query log, identify Top-N slow SQL, inspect execution plans with EXPLAIN, detect missing indexes, full table scans, large result sets, and lock waits, then output a structured report with optimization suggestions. Supports MySQL 5.7
Ready to connect
- View details
error-handling-securitySkillDatabases & data
Decide what an error tells the client and what stays server-side: no stack traces, SQL, or paths in responses, no silent suppression, and no distinction between outcomes that would reveal protected state. Use when generating HTTP, GraphQL, or RPC error handlers, exception, panic, or rescue blocks, o
Ready to connect
- View details
geo-data-engineeringSkillDatabases & data
Always invoke when geospatial data must be acquired, prepared, repaired, scaled, or moved through a repeatable pipeline. Covers open-data/OSM/STAC acquisition, spatial formats, CRS transforms, quality checks, and batch ETL architecture for growing or recurring joins. Invoke alongside PostGIS for dat
Ready to connect
- View details
infra-ragflow-opsSkillDatabases & data
RAGFlow platform operations skill. Triggered whenever the user mentions RAGFlow, ragflowctl, knowledge bases, datasets, RAGFlow model/vector store/object storage dependencies, or RAGFlow health checks.
Ready to connect
- View details
instrument-product-analyticsSkillDatabases & data
Add PostHog product analytics events to track user behavior. Use after implementing new features or reviewing PRs to ensure meaningful user actions are captured. Also handles initial PostHog SDK setup if not yet installed.
Ready to connect
- View details
jsf-frontend-eventsSkillDatabases & data
Handle the JetSmartFilters frontend AJAX lifecycle and reinitialize behavior after provider DOM replacement. Use when JavaScript must react when filtering starts, rendered content updates, loading ends, or JSF initializes; when integrating sliders, galleries, analytics, accessibility, or other widge
Ready to connect
- View details
llm-analytics-setupSkillDatabases & data
PostHog LLM analytics for all supported providers
Ready to connect
- View details
lw-lms-backend-extendSkillDatabases & data
Backend extension contract for LW LMS v1.6.0. Use when extending enrollment, access, source-scoped revocation, progress, certificates, automation, analytics, settings tabs, companion-plugin logic, `lw_lms_after_grant`, `lw_lms_after_revoke`, `lw_lms_pre_grant`, `lw_lms_has_course_access`, `AccessChe
Ready to connect
- View details
mcp-builderSkillDatabases & data
Build a Model Context Protocol (MCP) server so an AI client can call your tools/resources: design tool schemas, pick a transport, handle errors, and test it. For exposing an API, database, or service to Claude and other clients.
Ready to connect
- View details
ml-engineeringSkillDatabases & data
Use when working on the silken_net ML surface — the TinyML acoustic model + log-mel DSP front-end (firmware/common/logmel*, tools/ml/), model training / dataset / INT8 export, or golden-vector parity. ⛔ The backend Rumale stress-index ML was REMOVED 2026-09-05 (У-ВЕЙ) — the skill records where it we
Ready to connect
- View details
mlops-automationSkillDatabases & data
Automate an MLOps project with mise tasks, lefthook hooks, Docker images, GitHub Actions, and MLflow tracking on a SQL backend. Use when adding a task runner, git hooks, CI/CD, or experiment tracking to a working package.
Ready to connect
- View details
mlops-observabilitySkillDatabases & data
Make an ML system a glass box with reproducible runs, MLflow dataset lineage, drift monitoring, alerting, and SHAP explanations. Use when a deployed model needs traceability, monitoring, alerting, or explanation.
Ready to connect
- View details
mlops-prototypingSkillDatabases & data
Structure reproducible Jupyter notebooks with a fixed section layout, hoisted configuration, and leakage-free scikit-learn pipelines. Use when exploring a dataset, training a first model, or preparing a notebook for promotion.
Ready to connect
- View details
movement-trajectorySkillDatabases & data
Movement and trajectory analytics from GPS/GNSS tracks: cleaning, stop/trip detection, road-network map matching, speed/direction, flow aggregation, and origin-destination construction. Use for fleets, human mobility, animal tracking, AIS, or sports tracks. Trigger on GPS points, GPX, trajectories,
Ready to connect
- View details
onec-extension-validateSkillDatabases & data
Validate a named 1C:Enterprise configuration extension through BSL module checks, full configuration checks, applicability checks, database update, and database `.cfe` verification. Use after creating or modifying an extension, when diagnosing why an extension cannot be applied, or before declaring
Ready to connect
- View details
postgis-spatial-sqlSkillDatabases & data
Invoke whenever spatial SQL or its execution backend is the decision: PostGIS, DuckDB Spatial, SpatiaLite, ST_* functions, recurring spatial joins, concurrent/growing workloads, or large GeoParquet queries. Covers backend selection, schemas, GiST/BRIN indexes, KNN, geometry versus geography, correct
Ready to connect
- View details
public-mongodb-expert-baseSkillDatabases & data
MongoDB knowledge base. Covers Document Model, Aggregation Pipeline, Indexes, Replica Sets, and Change Streams. Intended to be inherited by devlab-mongodb-usage via extends.
Ready to connect
- View details
public-mysql-expert-baseSkillDatabases & data
MySQL/InnoDB knowledge base. Covers schema design, indexing strategies, query tuning, transactions and locks, partitioning, and operations. Intended for devlab-middleware-expert to inherit via extends.
Ready to connect
- View details
public-nl2sql-expert-baseSkillDatabases & data
NL2SQL/Text2SQL knowledge base (for inheritance by extends). Aggregates deep knowledge and pitfalls on the two-stage architecture, query type classification, field/term mapping, condition and metric extraction, multi-table JOIN reasoning, and SQL correctness and evaluation. Typically inherited by de
Ready to connect
- View details
public-oracle-expert-baseSkillDatabases & data
Oracle knowledge base. Covers Connection Types, JDBC Driver, Connection Pool, LOB Handling, Character Set, and SQL Dialect. Intended for devlab-oracle-usage to inherit via extends.
Ready to connect
- View details
public-postgres-expert-baseSkillDatabases & data
PostgreSQL knowledge base. Covers Schema Design, Indexing (B-Tree/GIN/GiST/BRIN), JSONB, Partitioning, Extensions. Intended for devlab-postgres-usage to inherit via extends.
Ready to connect
- View details
public-redis-expert-baseSkillDatabases & data
Redis knowledge base. Covers data structure selection, key naming, connection pools and Pipelines, cluster and replica reads, TTL and eviction policies. Intended to be inherited via extends by devlab-redis-usage.
Ready to connect
- View details
sddSkillDatabases & data
Create a Software Design Document (SDD) defining component architecture, data contracts, API schemas, and platform compatibility before planning. Use in Tier 3 (Full Pipeline) or when modifying interfaces, hooks, databases, or multi-platform contracts.
Ready to connect
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.
53,585 of the 54,017 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.