AGENTIC MEMORY
Skills
Useful instructions for your AI. Search, read and use them through the same MCP connection.
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-optimization
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
spawn
Use to launch the competing agents for an initialized AgentHub session in isolated worktrees.
speak-summary
Convert text, markdown, or a summary produced by another skill into a listenable MP3 using local CPU-only neural text-to-speech. Rewrites written prose for the ear before synthesising. Use when the user asks to "read this out", "turn this into audio", "make an MP3", "I want to listen to this", "podcast version", or wants a spoken digest for a commute or breakfast.
spec-driven-development
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and scope, or when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a capability map of modules before specifying.
spec-driven-workflow
Use when a feature should be specified before coding (acceptance criteria, spec-first, tests from specs). Writes the spec with spec_generator.py, checks it with spec_validator.py and extracts tests with test_extractor.py.
spec-to-code-compliance
Check code against the documentation that specifies it - which requirements hold, which the code contradicts, which are absent, and what the code does that no document mentions. Use when comparing an implementation against a whitepaper, protocol spec, or design document.
spec-to-repo
Use when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I have requirements and need a codebase', or provides a natural-language project specification and expects a complete, runnable repository. Stack-agnostic: Next.js, FastAPI, Rails, Go, Rust, Flutter, and more.
speech
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.
spinning-up-deep-rl
Use when learning or applying deep RL from OpenAI's Spinning Up: MDPs, policy gradients, VPG, TRPO, PPO, DDPG, TD3, SAC, debugging RL code that fails silently, or multi-seed experiments. Indexes the 20 chapters for on-demand reading.
sponsor-finder
Find which of a GitHub repository's dependencies are sponsorable via GitHub Sponsors. Uses deps.dev API for dependency resolution across npm, PyPI, Cargo, Go, RubyGems, Maven, and NuGet. Checks npm funding metadata, FUNDING.yml files, and web search. Verifies every link. Shows direct and transitive dependencies with OSSF Scorecard health data. Invoke with /sponsor followed by a GitHub owner/repo (e.g. "/sponsor expressjs/express").
spring-boot-testing
Expert Spring Boot 4 testing specialist that selects the best Spring Boot testing techniques for your situation with Junit 6 and AssertJ.
sprint-health
Sprint health scoring and velocity analysis for agile teams. Usage: /sprint-health <analyze|velocity> [options]
sprint-plan
Capacity-gated sprint planning — runs capacity math, carry-over check, and a definition-of-ready gate before committing scope. Usage: /sprint-plan <goal> [capacity]
sql-code-review
Universal SQL code review assistant that performs comprehensive security, maintainability, and code quality analysis across all SQL databases (MySQL, PostgreSQL, SQL Server, Oracle). Focuses on SQL injection prevention, access control, code standards, and anti-pattern detection. Complements SQL optimization prompt for complete development coverage.
sql-database-assistant
Use for writing or optimizing SQL, exploring a schema, generating migrations or working with Prisma, Drizzle, TypeORM or SQLAlchemy. Analyzes queries with query_optimizer.py and schemas with schema_explorer.py.
sql-object-impact-analysis
Before modifying a table, column, stored procedure, view, or trigger in a legacy codebase, trace every place that references it — across other SQL objects (procs, views, triggers) AND application code (C#, Angular/TypeScript, JS, or any language in the repo) — and produce a structured blast-radius report so you know what breaks before you change it. Use when the user asks 'what uses this column/table/procedure', 'is it safe to change X', 'what depends on this', 'impact of renaming/dropping X', or before any schema/proc modification in an unfamiliar or legacy codebase. Not for privacy/PII exposure analysis (see data-breach-blast-radius) or query performance tuning (see sql-optimization).
sql-optimization
Universal SQL performance optimization assistant for comprehensive query tuning, indexing strategies, and database performance analysis across all SQL databases (MySQL, PostgreSQL, SQL Server, Oracle). Provides execution plan analysis, pagination optimization, batch operations, and performance monitoring guidance.
sql-optimization-patterns
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
sql-server-table-reconciliation
Use when: comparing SQL Server tables across instances, data migration validation, ETL verification, row mismatch detection, schema drift, reconciliation report, production vs staging comparison. Uses mssql-python driver with Apache Arrow for fast columnar data transfer and comparison.
sred-project-organizer
Take a list of projects and their related documentation, and organize them into the SRED format for submission.
sred-work-summary
Go back through the previous year of work and create a Notion doc that groups relevant links into projects that can then be documented as SRED projects.
Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.