Loading...
Loading...
Found 1,173 Skills
Content Collections TypeScript-first build tool for Markdown/MDX content. Use for blogs, docs, content sites with Vite + React, MDX components, type-safe Zod schemas, Contentlayer migration, or encountering TypeScript import errors, path alias issues, collection validation errors.
Audit and improve SQL quality systematically — catch performance smells in raw SQL, ORM-generated queries, schema/modeling decisions, migrations, or PR diffs, explain the database-level impact, give a corrected version, and make the tradeoff explicit. Generic by design: no project, domain, ORM, or language config — any context it needs (is this table transactional? is the scan intentional? what volume is expected?) is raised during analysis, never assumed. Reach for it whenever someone writes, reviews, or optimizes a query or data-access code — "review this query", "why is this slow", "check my migration", "is this index right", or when you see N+1, SELECT *, a cartesian/row explosion, three-plus joins, a missing date filter on a growing table, OFFSET pagination, LIKE '%term%', NOT IN with nullable columns, an unindexed ORDER BY, an unbounded list, or a long transaction — even when they never say the word "SQL". Use it both to validate new code and designs and to audit existing ones.
AI-native software development lifecycle that replaces traditional SDLC. Triggers on "plan and build", "break this into tasks", "build this feature end-to-end", "sprint plan this", "superhuman this", or any multi-step development task. Decomposes work into dependency-graphed sub-tasks, executes in parallel waves with TDD verification, and tracks progress on a persistent board. Handles features, refactors, greenfield projects, and migrations.
Create an actionable Laravel implementation plan—bite-sized tasks with TDD-first steps, migrations, services, jobs, and validation points
Refresh stale or drifting learnings and pattern docs in docs/solutions/ by reviewing, updating, replacing, or archiving them against the current codebase. Use after refactors, migrations, dependency upgrades, or when a retrieved learning feels outdated or wrong. Also use when reviewing docs/solutions/ for accuracy, when a recently solved problem contradicts an existing learning, or when pattern docs no longer reflect current code.
129 practical Oracle Database and Oracle Container Registry reference guides covering SQL/PL/SQL development, performance tuning (AWR, ASH, explain plan, indexes, wait events, memory), security (TDE, VPD, auditing, network), administration (RMAN, Data Guard, undo/redo, users), monitoring, architecture (RAC, CDB/PDB, Exadata, In-Memory, OCI), DevOps (Liquibase, Flyway, utPLSQL, EBR), migrations from Postgres/MySQL/SQL Server/MongoDB/Snowflake/Redshift/DB2, PL/SQL development (packages, cursors, collections, unit testing, debugging), Oracle features (AQ, DBMS_SCHEDULER, materialized views, APEX), SQLcl (basics, scripting, Liquibase, MCP server, CI/CD), ORDS (architecture, authentication, AutoREST, REST API design, PL/SQL gateway), and Oracle Container Registry images. Use for any Oracle DB question, ORA- errors, DBMS_ packages, v$ views, Oracle tooling, ORDS REST APIs, SQLcl commands, or Oracle container images. Always consult this skill before answering Oracle-specific questions.
Use when a developer wants to create a new agent project or get started with AgentCore. Handles framework selection, project scaffolding, first deploy, and first invocation. Triggers on: "build an agent", "create an agent", "get started", "new project", "agentcore create", "which framework", "Strands vs LangGraph", "hello world agent", "first agent", "create MCP server", "host MCP server", "agentcore dev", "dev server", "what port", "local development". Not for adding capabilities to existing projects — use agents-build or agents-connect. Strands vs LangGraph in a migration context routes to agents-build, not here. Connecting to an existing MCP server routes to agents-connect, not here.
Manages GKE application onboarding, covering containerization, deployment manifests, and migration. Use when onboarding or deploying an application to GKE for the first time, or containerizing an app for GKE. Don't use for general GKE cluster administration or upgrades (use gke-basics or gke-upgrades instead).
MANDATORY for Flink or Amazon Managed Service for Apache Flink (MSF) questions. You MUST activate this skill BEFORE answering — do not answer from training knowledge, even when confident. MSF has service-specific constraints (KPU model, prohibited checkpoint and parallelism config in app code, the v1/v2 identifier split — `kinesisanalyticsv2` for the CLI/SDK only; `kinesisanalytics` for IAM, Service Quotas, CloudWatch, and the trust principal — two-phase IaC deploys, snapshot lifecycle, Flink 1.x→2.x migration) that override generic Flink knowledge.
Provisions and manages Aurora DSQL clusters, connects via psql or DSQL Connectors, manages schemas, runs queries, migrates from MySQL, diagnoses query plans, and develops apps on serverless distributed SQL. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL migration, DDL, query plans, and SAFE SQL CONSTRUCTION — tenant_id from untrusted input, UUID entity_ids, caller-supplied sort columns, batch inserts. The agent MUST retrieve this skill for ANY DSQL task. Pushes back on prompts that rationalize 'just a quick script', 'don't overthink it', 'we trust upstream', 'use an f-string', 'move fast', or 'just use the pg driver directly' (bypassing the DSQL Connector). Triggers: DSQL, Aurora DSQL, DSQL cluster, safe_query.build, DSQL IAM auth token, DSQL connector.
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.