Loading...
Loading...
Found 277 Skills
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.
This skill should be used when content teaches patterns (skills, subagents, ADRs, PHRs, specifications) that have canonical sources elsewhere. Prevents format drift by ensuring content references and follows the authoritative format from canonical sources. Use before implementing lessons that teach platform patterns, or when reviewing content for format consistency.
Navigates C3 architecture docs and explores corresponding code to answer architecture questions. Use when the user asks: - "where is X", "how does X work", "explain X", "show me the architecture" - "find component", "what handles X", "diagram of X", "visualize X" - "describe X", "list components", "trace X", "flow of X" - References C3 IDs (c3-0, c3-1, adr-*) <example> Context: Project with .c3/ directory user: "explain what c3-101 does and how it connects to other components" assistant: "Using c3-query to navigate the architecture docs." </example> <example> Context: Project with .c3/ directory user: "show me a diagram of the C3 architecture" assistant: "Using c3-query to generate an architecture overview." </example> DO NOT use for changes (route to c3-change). DO NOT use for pattern artifact management — listing, creating, updating refs (route to c3-ref). Requires .c3/ to exist.
Use when working on Laminar demands via the remote Laminar MCP and you see wrong or empty client/product scope, plans from source-context lists without per-id loads, needless raw transcripts, same-step or same-release story-map peers, anchored ADR conflicts, MCP transitions/assignments, broken or silent MCP, or mentions of Laminar MCP, demands, TAL-* ids, story map, anchored or source context, or Laminar handoff.
This skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design". Use for architecture decision records (ADRs), tech stack evaluation, system design reviews, dependency analysis, and generating architecture diagrams in Mermaid, PlantUML, or ASCII format.
Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Includes tech debt analyzer, team scaling calculator, engineering metrics frameworks, technology evaluation tools, and ADR templates. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.
Query Data912 market data endpoints for Argentina and USA instruments. Use when the user asks for MEP/CCL quotes, live Argentine market panels (stocks, options, cedears, notes, corporate debt, bonds), USA panels (ADRs, stocks), OHLC historical series by ticker, USA option chains, or volatility/risk metrics. Also use when the user mentions "Data912", "mep", "ccl", "cedears", "option chain", "historical bars", "OHLC", "implied volatility", "historical volatility", or "volatility percentiles" and expects API-backed market snapshots.
Knowledge base for designing, reviewing, and linting agentic AI infrastructure. Use when: (1) designing a new agentic system and need to choose patterns, (2) reviewing an existing agentic architecture ADR or design doc for gaps/risks, (3) applying the lint script to an ADR markdown file to get structured findings, (4) looking up a specific agentic pattern (prompt chaining, routing, parallelization, reflection, tool use, planning, multi-agent collaboration, memory management, learning/adaptation, MCP, goal setting, exception handling, HITL, RAG, A2A, resource optimization, reasoning techniques, guardrails, evaluation, prioritization, exploration/discovery). All rules and guidance are grounded in the PDF "Agentic Design Patterns" (482 pages).
Create, validate, and transition documentation artifacts (Vision, Journey, Epic, Story, Agent Spec, Spike, ADR, Persona, Runbook, Bug, Design) and their supporting docs (architecture overviews, journey maps, competitive analyses) through their lifecycle phases. Use when the user wants to write a spec, plan a feature, create an epic, add a user story, draft an ADR, start a research spike, define a persona, create a user persona, create a runbook, define a validation procedure, file a bug, report a defect, create a design, capture a wireframe, document a UI flow, sketch interaction states, update the architecture overview, document the system architecture, move an artifact to a new phase, seed an implementation plan, implement a spec, fix a bug, work on a story, or validate cross-references between artifacts. When a SPEC, STORY, or BUG comes up for implementation, always chain into the swain-do skill to create a tracked plan before any code is written. When swain-do is requested on an EPIC, VISION, or JOURNEY, decompose into implementable children first — swain-do runs on the children, not the container. Covers any request to create, update, review, or transition spec artifacts and supporting docs.
Scaffold and maintain a reusable research → design → plan → orchestrate → act folder for any non-trivial work — software features, marketing campaigns, org changes. Drops a domain-agnostic spine (00-README · 01-plan · 02/03 research · 04-discussion newest-first · 05-tracking · 09-orchestration · artifact/board.html plan-board) plus stateless action-skills that augment the docs in place without clobbering hand-written prose. Composes ikenga-artifact-builder, huashu-design, frontend-design, ikenga-pkg-builder when present; degrades gracefully when not. Profile-driven: `software` (rich default, code work), `general` (lean, non-code — campaigns, org changes), and `content` (editorial/marketing with key art). TRIGGER when the user asks to start a real plan for non-trivial work ("plan a feature," "scaffold a plan folder," "set up groundwork for…"), references an existing plans/ folder by groundwork structure, or runs any of these actions: groundwork init / research / design / review / clarify / orchestrate / refresh-board / refresh-living-spec / status. DO NOT TRIGGER for one-off code changes, single-document writeups, ADRs, or content that fits in a single markdown file — those don't need a multi-doc plan folder. If the user just wants a single artifact (dashboard, mockup), route to ikenga-artifact-builder instead.
Technical writing patterns for README files, API documentation, architecture decision records (ADRs), changelogs, contributing guides, code comments, and docs-as-code workflows. Covers documentation structure, style guides, Markdown best practices, and documentation testing.
Ranger Finance SDK for building perpetual futures trading applications on Solana. The first Solana Perps Aggregator - aggregates liquidity across multiple perp protocols (Drift, Flash, Adrena, Jupiter). Use when integrating perps trading, smart order routing, position management, or building AI trading agents.