research-agent-optimization
Optimize the research agent for rate limit handling, API call efficiency, web search integration fixes, and improved streaming UX with granular progress updates and source attribution.
Explorez des skills pour le développement, le contenu, les données et la productivité. Comparez les descriptions et dépôts.
Optimize the research agent for rate limit handling, API call efficiency, web search integration fixes, and improved streaming UX with granular progress updates and source attribution.
Creates new skill YAML definitions in the canonical format. Use when the user wants to create a new skill, command, or workflow for the AI config transpiler.
Design AI characters and personas with structured definitions. Use when creating chatbot personalities, AI assistants, or roleplay characters.
Provides MLflow documentation covering Tracking, Projects, Models, and Registry. Use when the user asks about MLflow features, APIs, implementation, or debugging.
Process audiobooks from the inbox: transcribe to text and organize audio for voice training.
Manage database schema changes with version control. Use when modifying DB schema, adding tables/columns, or setting up new projects. Covers Prisma, Drizzle, and migration best practices.
PostgreSQL database schema, table structures, relationships, and migration rules. Use this skill when working with SQLAlchemy models, Alembic migrations, or database design.
Prepare context for compaction. Run before /compact to ensure critical state survives.
Execute plan in batches with review checkpoints. Use when partner provides a complete implementation plan to execute with controlled batches and architect review between batches.
Resume spec implementation from checkpoint. Use when continuing task-dispatch after context limit or session break.
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
MongoDB database exploration, querying, and debugging using MCP tools. Use when writing aggregation pipelines, analyzing schemas, debugging data issues, or exploring collections in ShipitSmarter databases.
A specialized guide for Serverless Postgres development, enforcing connection pooling, schema-as-code, and MCP-driven database inspection.
Used for resolving schema conflicts by keeping the more recent timestamp
Read the csv open data file and process to know the first 5 items by cost. Use when the user need to process the file and get the first 5 items
Update the account's searchable description in Qdrant after state changes. Keeps search results accurate.
Manage database schemas, Drizzle ORM, migrations, and data modeling. Use when creating tables, modifying columns, or planning database changes.
Safely extend or refine AFI signal schemas and closely-related validators in afi-core, while preserving determinism, respecting PoI/PoInsight design, and obeying the AFI Droid Charter and AFI Core AGENTS.md bou...
Safely update the core data schema and types. Use when changing data models, adding fields, or modifying the report structure.
PostgreSQL patterns for reviewing migrations and writing efficient queries. Use when reviewing Alembic migrations, optimizing queries, or debugging database issues.
Comprehensive guide for using BigQuery CLI (bq) to query and inspect tables in Monzo's BigQuery projects, with emphasis on data sensitivity and INFORMATION_SCHEMA queries.
Comprehensive guide for Drizzle ORM database migrations with PostgreSQL. Use when adding/modifying database columns, creating migrations, updating schemas, or working with Drizzle schema definitions. Includes m...
Persistent state management using AgentDB (DuckDB) for workflow analytics and checkpoints. Provides read-only analytics cache synchronized from TODO_*.md files, enabling: - Complex dependency graph queries - H...
Expert guidance for Prisma ORM v7 (7.0+). Use when working with Prisma schema files, migrations, Prisma Client queries, database setup, or when the user mentions Prisma, schema.prisma, @prisma/client, database...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.