Loading...
Loading...
Found 612 Skills
Creates dbt models following project conventions. Use when working with dbt models for: (1) Creating new models (any layer - discovers project's naming conventions first) (2) Task mentions "create", "build", "add", "write", "new", or "implement" with model, table, or SQL (3) Modifying existing model logic, columns, joins, or transformations (4) Implementing a model from schema.yml specs or expected output requirements Discovers project conventions before writing. Runs dbt build (not just compile) to verify.
Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement on the DEFT-augmented dataset. This is the default entry point for any "run the AOI workflow", "fine-tune my PCB AOI model end-to-end", "improve my AOI ChangeNet model", or "AOI workflow with AutoML" request — route here instead of tao-run-deft-aoi directly unless the user explicitly asks for the DEFT loop ONLY (e.g. "run JUST the DEFT loop", "skip AutoML, only DEFT"). Also handles the same three-phase pattern for non-AOI DEFT applications — AutoML baseline then DEFT loop warm-started from AutoML's winning HPs then post-DEFT AutoML refinement on the iteration-augmented dataset. Trigger phrases include "run the AOI workflow", "AOI end-to-end", "AutoML + DEFT", "AutoML then DEFT", "tune hyperparameters then DEFT", "DEFT with AutoML at both ends", "warm-start DEFT", "improve my AOI model".
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
Forces exhaustive problem-solving using corporate PUA rhetoric and structured debugging methodology. MUST trigger when: (1) any task has failed 2+ times or you're stuck in a loop tweaking the same approach; (2) you're about to say 'I cannot', suggest the user do something manually, or blame the environment without verifying; (3) you catch yourself being passive — not searching, not reading source, not verifying, just waiting for instructions; (4) user expresses frustration in ANY form: 'try harder', 'stop giving up', 'figure it out', 'why isn't this working', 'again???', '换个方法', '为什么还不行', '你再试试', '加油', '你怎么又失败了', or any similar sentiment even if phrased differently. Also trigger when facing complex multi-step debugging, environment issues, config problems, or deployment failures where giving up early is tempting. Applies to ALL task types: code, config, research, writing, deployment, infrastructure, API integration. Do NOT trigger on first-attempt failures or when a known fix is already executing successfully.
Determine when a product, platform, or communication crosses the regulatory line from education into investment advice requiring registration. Use when the user asks about the definition of investment advice under the Advisers Act, whether a fintech feature or AI chatbot constitutes advice, the publisher's exclusion for newsletters or model portfolios, broker-dealer solely incidental exclusion, what triggers a 'recommendation' under Reg BI, or DOL education vs advice safe harbors. Also trigger when users ask 'do I need to register as an investment adviser', 'does this app give investment advice', 'is this tool just education or advice', 'robo-adviser registration', or 'disclaimer language for financial content'.
Run a daily content digest pipeline that fetches Podcast RSS feeds and YouTube channels, transcribes audio, generates AI summaries in Traditional Chinese, and optionally sends notifications via Telegram. Use this skill whenever the user wants to: set up or run a daily digest, summarize podcasts or YouTube videos, create a content briefing, aggregate RSS/YouTube content, or build an automated summary system. Also triggers for: "daily digest", "每日摘要", "podcast 摘要", "YouTube 整理", "跑摘要", "內容彙整", "幫我整理今天的 podcast", "summarize my subscriptions", or any request to periodically collect and summarize media content. Even if the user just says "digest" or "摘要", check if this skill applies.
Complete catalog of reusable typography and text patterns for SGDS applications. Use this skill whenever the user needs to style text, create typography hierarchies, format headings, style lists, or needs consistent text layouts. Also use when the user mentions headings, page titles, body text, lists, paragraphs, display text, content headers, or any typography styling — even if they just say "make a nice heading" or "style my text". Current patterns include headings (H1-H6), display typography (large prominent text), content headers, lists (ordered and unordered), and paragraphs. Each pattern links directly to the raw HTML template for implementation.
This skill is applicable when users explicitly request to 'write/generate NSFC budget specification', 'write budget explanation', 'generate budget.tex / budget.pdf', or 'write NSFC budget justification'. Based on the user's proposal text or supplementary materials, output a submittable budget specification LaTeX project and render `budget.pdf`. If the user does not specify a working directory, you must pause and ask them to specify it first. ⚠️ Not applicable: Users only want to understand budget principles; users only want budget table figures without writing the specification; or users are in the 2026 Youth A/B/C default lump-sum scenario where no budget specification is required.
Iterative design-to-code feedback loop. Critique → adjust → ship cycle for tightening visual fidelity between brief and built UI.
Has SM been in this token for weeks, or did they just enter? Are they still buying?
Evaluate product desirability, market positioning, and emotional resonance—the complement to friction analysis. Assess whether users will WANT a product (not just use it), identity fit, trust signals, and value proposition clarity. Activate on "will they like it", "market positioning", "appeal analysis", "product desirability", "value proposition", "why would someone choose this", "landing page review", "conversion optimization", "messaging strategy". NOT for UX friction analysis (use ux-friction-analyzer), visual design implementation (use web-design-expert), or A/B test setup (use frontend-developer).
Plan trips with assumptions, not questions. Trip Planner extracts flight constraints from natural conversation, fills in the gaps with smart defaults, and returns structured flight recommendations with direct booking links. Assume first. Show your work. Book the flight. Just say "trip-planner" to get going.