Trace data lineage, source attribution, audit trails, and W3C PROV-O export in Semantica graphs. Uses ProvenanceManager.

Use when visually testing Tiny World Builder UI, camera, ghost opacity, buildings, tile geometry, or frontend polish in the browser.

Use when adding or changing persisted user state — settings defaults, audio, camera/orbit, panel positions, feature flags, and the in-app "Save Defaults" pipeline that snapshots localStorage into tinyworld-defaults.json. Also covers the inline-script regex gotcha that has burned us twice.

Use when changing Tiny World Builder Auto palette behavior, model inference, suggestions, or provider/model/API-key logic.

Delegate analysis- and context-heavy work to Fractal, an agentic CLI powered by a self-harnessed Recursive Language Model (predict-rlm), by running it non-interactively (fractal -p). Reach for it when a task needs reasoning over a large or deep codebase, synthesizing an answer across many files, auditing, or open-ended investigation — work that would otherwise flood your own context. The RLM reasons over context programmatically (no context rot) and returns a distilled answer. Use when asked to run Fractal headless, script it, call it from CI or another agent, or offload a heavy analysis/large-context task. Less suited to trivial single-file edits you can do directly.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.

FLOW framework integration for bloggers. Evidence-led content workflow using the Find, Optimize, Win loop with stage-specific AI prompts from the FLOW knowledge base (30 blog-applicable prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "blog flow", "evidence-led blogging", "find optimize win", or wants stage-specific blog prompts.

Extract, suggest, and sync tags and categories for blog posts across all major CMS platforms. Supports WordPress REST API, Shopify GraphQL, Ghost Content API, Strapi REST/GraphQL, and Sanity GROQ. Generates tag suggestions from content analysis (keyword frequency, heading extraction, semantic grouping), enforces minimum post-count thresholds to prevent thin tag archives, and syncs taxonomy via authenticated API calls. Use when user says "tags", "categories", "taxonomy", "tag suggestions", "sync tags", "WordPress tags", "Shopify tags".

Use when answering a question that needs data from a ktx-connected database - investigating, analyzing, "how many", "show me", "what's the breakdown of", finding records by value, exploring tables, comparing periods, explaining metrics, or any data-analysis request. Triggers even when the user does not say "analytics"; if the answer requires querying a configured ktx connection, this skill applies.

Score and rank options contracts for any ticker using AlphaGBM's multi-factor scoring model (liquidity, IV attractiveness, Greeks balance, risk/reward). Returns scored option chains with the best contracts highlighted. Use when: evaluating which option to trade, finding the best strike/expiry, ranking options by quality. Triggers on: "score AAPL options", "best options for NVDA", "which TSLA call should I buy", "option chain for SPY", "rank META puts".

AI DevKit · Track dev-lifecycle / structured-debug progress on a durable task with the ai-devkit task CLI. Use to record phase, progress, next step, blockers, and validation evidence.

AI DevKit · Requirements phase guidance for starting features and reviewing requirements. Use when the user wants to capture a new requirement, clarify product scope, initialize feature docs, review requirements, or run dev-lifecycle phases 1-2.

Activate when the user needs to interact with any website — browser automation, web scraping, screenshots, form filling, UI testing, monitoring, or building AI agents. Provides pre-verified page actions with step-by-step instructions and tested selectors.

Build, repair, or review Maple dashboard widgets via the MCP. Triggers on phrases like 'create_dashboard', 'add_dashboard_widget', 'update_dashboard_widget', 'dashboard widget JSON', 'panel_type', 'QueryDraft', or any session that submits widget JSON to the maple MCP. Covers the panel-type table, the kind-discriminated data source, the percent vs percent_100 unit rule, valid aggregations and group-by tokens per source, the custom whereClause grammar, the scalar reduceToValue transform, and the verification step (MCP success != chart correctness).

Tinybird Python SDK for defining datasources, pipes, and queries in Python. Use when working with tinybird-sdk, Python Tinybird projects, or data ingestion and queries in Python.

Drug and chemical toxicity assessment via adverse outcome pathways (AOPs), real-world FAERS adverse event signals, FDA labels, and toxicogenomic associations. Triangulates molecular initiating event to cellular outcome to organ-level toxicity to clinical adverse event. Use for hepatotoxicity/cardiotoxicity/nephrotoxicity prediction and toxicology reports.

Review existing work against the user's actual goal and surface evidence-backed strengths, gaps, risks, and next fixes. Use when asked to eval, evaluate, review, assess, or check current/this/my/our work; decide whether a task is complete; build a definition-of-done checklist or rubric; or perform grading, LLM-as-judge, Qworld, or RET evaluation. Treat plain eval/review requests as qualitative: resolve "current work" from the conversation, artifacts, files, or diff, and never assign numeric scores unless the user explicitly requests scores, grades, points, ratings, weighted criteria, Qworld, or RET. Do not use for implementing automated eval suites, tests, graders, or benchmarks.

Build AI scientist systems with the ToolUniverse Python SDK for scientific research. Covers the 3 calling patterns (`tu.run` portable dict API, `tu.tools.X` function API, direct class instantiation), tool loading, batch execution, MCP server integration, and embedding-based tool search. Use for SDK programming, custom tool composition, benchmarking pipelines, and integrating ToolUniverse into research workflows.

Post-translational modification (PTM) analysis — phosphorylation, ubiquitination, acetylation, glycosylation, methylation. Uses iPTMnet (sites + enzymes), ProtVar (functional consequences), UniProt (baseline), STRING, ELM (linear motifs), MassIVE/ProteomeXchange (experimental). Use for PTM site annotation, kinase-substrate identification, and PTM-disease associations.