Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Improve Spark performance and diagnose slow data processing jobs. Covers partitioning, caching, shuffle optimization, and memory tuning to scale processing pipelines.
Addresses ten known training failure modes on NVIDIA DGX Spark. Supports checks before long GB10 jobs and diagnosis of startup failures, out-of-memory errors below 128GB, and mid-run slowdowns.
Supports spartan/ui development with headless Brain primitives and styled Helm components. Provides project context, component APIs, usage examples, and guidance for initialization and CLI generators.
Starts a specified number of parallel subagents to compete on a session task. Each agent runs in an isolated Git worktree within an initialized AgentHub session.
Turn vague intent into a precise, executable spec in five phases. (gstack)
Clarifies vague product ideas by asking questions about requirements and unresolved ambiguities. Produces a persisted specification with acceptance criteria for downstream planning, scaffolding, and test-driven development.
Acts as the sole editor of the repository's project specification. Supports creating or deriving specifications from code, amending sections, adding invariants, and recording bugs using FORMAT.md encoding and table rules.
Apply a specification-driven method before coding a large feature. Clarify requirements before proposing the document structure, then develop each section incrementally.
Hard readiness gate before implementation begins — cross-checks the constitution, feature spec, plan, and tasks for consistency, traceability, and unresolved ambiguity. Returns PASS or FAIL with specific findings. Load when the spec-driven-development orchestrator routes /analyze, when the user asks to cross-check spec vs plan, audit traceability, verify spec readiness, gate-check before implement…
Full lifecycle spec-driven development methodology across three gated phases - Requirements (EARS-format acceptance criteria), Design (architecture, data models, edge cases), and Tasks (phased implementation plan).
Turns new project ideas or ambiguous requirements into specifications and PRDs with clear objectives and scope. Decomposes requirements spanning independently testable capabilities into module capability maps.
Orchestrator for spec-driven development (SDD) — the discipline of writing executable specs before code, with a constitution above them and a hard cross-check gate before implementation. Mirrors GitHub Spec Kit / AWS Kiro slash-command shape. Routes /constitution, /specify, /clarify, /plan, /tasks, /analyze, /implement to the right leaf skill. Load when the user says "spec-driven development", "SD…
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name