All categories
Databases
SQL, NoSQL, schema design, migrations, ORMs, and database operations
- 4,325
- 181
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse databases skills
Showing 1,105–1,128 of 4,325 skills
- Mimicsql EvalEvaluates a model's ability to generate correct SQL queries from natural language clinical questions in the healthcare domain. It specifically probes retrieval-based reasoning, robustness to noisy or ambiguous medical terminology, and generalization under data scarcity conditions. Use when the user wants to benchmark on MIMICSQL, or asks about evaluating this task. Reports Execution Accuracy.Votes: 0GitHub stars: 3
- Llmidxadvis EvalEvaluates the effectiveness and efficiency of an LLM-based index recommendation system in selecting database indexes for given SQL workloads under varying storage constraints and schema generalization settings. Use when the user wants to benchmark on TPC-H, JOB, TPC-DS, SSAG, AMPS, or asks about evaluating this task. Reports Relative Workload Cost Reduction.Votes: 0GitHub stars: 3
- Indicdb EvalEvaluates cross-lingual semantic parsing and Text-to-SQL capabilities across Indian languages, probing a model's ability to link natural language queries to complex, high-join-depth relational schemas and generate syntactically and semantically correct SQL. Use when the user wants to benchmark on IndicDB, or asks about evaluating this task. Reports Execution Accuracy (EX).Votes: 0GitHub stars: 3
- Emr Agent EvalEvaluates an LLM-based agent's ability to automate cohort selection, feature extraction, and clinical code standardization across heterogeneous Electronic Medical Record (EMR) databases. It probes schema-aware SQL reasoning, iterative query planning, and robustness to unseen database structures without manual rule engineering. Use when the user wants to benchmark on MIMIC-III, eICU, SICdb, or asks about evaluating this task. Reports F1.Votes: 0GitHub stars: 3
- Cross Domain Text To Sql EvalEvaluates the reliability of cross-domain text-to-SQL benchmarks by exposing flaws in automated metrics like execution accuracy and exact set match, and by introducing human-in-the-loop validation to handle schema ambiguity and query equivalence. Use when the user wants to benchmark on Spider, Spider-DK, BIRD, or asks about evaluating this task. Reports Execution Accuracy.Votes: 0GitHub stars: 3
- Bird Critic EvalThis benchmark evaluates an LLM's ability to debug and fix real-world, user-reported SQL issues. It probes the model's capacity to identify logical, syntactic, and semantic flaws in existing queries and generate correct, functional SQL replacements across different database dialects and complexity levels. Use when the user wants to benchmark on BIRD-CRITIC, or asks about evaluating this task. Reports Success Rate (SR).Votes: 0GitHub stars: 3
- Database DesignDatabase design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.Votes: 0GitHub stars: 36
- ProteinmpnnDesign protein sequences using ProteinMPNN inverse folding. Use this skill when: (1) Designing sequences for RFdiffusion backbones, (2) Redesigning existing protein sequences, (3) Fixing specific residues while designing others, (4) Optimizing sequences for expression or stability, (5) Multi-state or negative design. For backbone generation, use rfdiffusion or bindcraft. For ligand-aware design, use ligandmpnn. For solubility optimization, use solublempnn.Votes: 0GitHub stars: 26
- Alphafold2 MultimerAlphaFold2 / AlphaFold-Multimer structure prediction for validation and confidence scoring. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm2-sequence-scoring. For QC thresholds, use protein-design-qc.Votes: 0GitHub stars: 26
- MetagenomicsShotgun metagenomics workflow with host-depletion-aware QC, taxonomic profiling, functional profiling, AMR follow-up, and reproducible community output tables.Votes: 0GitHub stars: 26
- Fastapi Async PatternsUse when FastAPI async patterns for building high-performance APIs. Use when handling concurrent requests and async operations.Votes: 0GitHub stars: 3
- Database MigrationsDatabase migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).Votes: 0GitHub stars: 3
- Postgres PatternsPostgreSQL patterns for query optimization, schema design, indexing, RLS, and connection pooling. Use when writing or reviewing SQL against the devskyy Postgres, choosing an index, diagnosing a slow query, or hardening database security. Do NOT use for versioning schema changes (that is database-migrations — Alembic owns every DDL change here), for Redis/cache semantics (redis-patterns), or for the container/compose layer around the database (docker-patterns).Votes: 0GitHub stars: 3
- Database MigrationsSafe schema and data migrations — expand/contract, concurrent indexes, batched backfills, rollback strategy — across PostgreSQL/MySQL and Alembic (this repo's canonical tool), Prisma, Drizzle, Kysely, Django, golang-migrate. Use when a model/table/column/index changes, a backfill is needed, or migration tooling is being set up or repaired. Do NOT use for query tuning and index *selection* on an unchanged schema (that is postgres-patterns), for Redis key/TTL design (redis-patterns), or for bri...Votes: 0GitHub stars: 3
- Consume FeedManage and run nightly ingestion of upstream feeds (RSS). GitHub and NVD support coming in Phase 2. Fetch updates, store summaries in ArangoDB, and integrate with Memory. Use this skill to "check for updates" or "add a new source" to the knowledge graph.Votes: 0GitHub stars: 6
- Team DevBE Dev (Backend Developer) agent. Reads BA + TechLead + PM artifacts and generates backend source code files, .env.example, and pr-description.md. No hardcoded credentials. Part of the Virtual Team Skill pipeline.Votes: 0GitHub stars: 19
- Team DevBE Dev (Backend Developer) agent. Reads BA + TechLead + PM artifacts and generates backend source code files, .env.example, and pr-description.md. No hardcoded credentials. Part of the Virtual Team Skill pipeline.Votes: 0GitHub stars: 19
- Team DevBE Dev (Backend Developer) agent. Reads BA + TechLead + PM artifacts and generates backend source code files, .env.example, and pr-description.md. No hardcoded credentials. Part of the Virtual Team Skill pipeline.Votes: 0GitHub stars: 19
- Java ModernizationModernizes Java applications by upgrading the Java version and updating dependencies to compatible versions — improving security, performance, and maintainability while keeping the project buildable at every step. Use this skill whenever the user wants to upgrade Java versions, migrate from javax to Jakarta EE, update Spring Boot, modernize dependencies, or do any kind of Java version migration — even if they phrase it as "upgrade to Java 21", "migrate to Spring Boot 3", "update dependencies...Votes: 0GitHub stars: 2
- Jade Recipe 8 11 Corba RemovalDeletes JADE's CORBA dependency instead of retrofitting it: the generated FIPA IDL stubs, the IIOP message transport protocol, and their build.xml wiring. Agent-mode recipe: the shard contract names the files; this document defines what is deleted, what is left alone, and how the leftover references are resolved.Votes: 0GitHub stars: 2
- Jade Recipe 1.7 Try With ResourcesConverts manual open/close resource management to Java 7 try-with-resources where — and only where — the resource genuinely implements Closeable/AutoCloseable, is closed unconditionally on every path, and is never touched again after the try. Agent-mode recipe: scripts/scan.py narrows the manifest's broad TRY_WITH_RESOURCES flags (0.6% precision) to a shortlist (~70% precision); this document defines the judgment calls the shortlist cannot make on its own.Votes: 0GitHub stars: 2
- Jade Core VerificationVerifies JADE migration correctness by semantic outcome matching instead of raw textual log diffing. Normalizes traces (strips timestamps, thread IDs, nonces), extracts agent lifecycle / ACL protocol / DF-AMS state events, and compares state outcomes under configurable tolerance. Produces diff and metrics artifacts. Run this as the final verification gate after all migration rules have been applied.Votes: 0GitHub stars: 2
- Jade Core Tooling ScoutDetects what can be auto-assisted by OpenRewrite, PMD, and Checkstyle before manual scanner work. Probes tool availability, runs each tool against the legacy workspace using a modern JDK, collects findings, and merges results into the breaking-changes manifest with provenance. Never rewrites code — discovery and reporting only.Votes: 0GitHub stars: 2
- Jade Core Rule DispatcherRoutes rule tasks to registry recipes via recipe-registry.json. Handles LOAD/MATCH/RECORD workflow but delegates all transform logic to recipe subprocesses. Contains ZERO version-specific or rule-specific transform code. Accepts one task at a time from the rule batch.Votes: 0GitHub stars: 2