Total 64,999 skills
Showing 12 of 64999 skills
Add access control to a ZenStack V3 schema. Use when writing access policies (@@allow / @@deny), the auth() function, field-level rules, post-update rules, or setting up the policy plugin and $setAuth runtime. (For data validation — @email/@length/@@validate — see zenstack-querying.)
Knowledge base on spatial intelligence as the next frontier in AI, based on Fei-Fei Li's insights from her Y Combinator AI Startup School talk. Use this skill when users ask about spatial intelligence concepts, 3D world modeling, the evolution of computer vision from ImageNet to World Labs, AI research strategy and problem selection, or when seeking advice on AI entrepreneurship and founding AI companies. Also trigger when discussing the relationship between vision/spatial understanding and AGI, differentiating generative vs discriminative models in 3D contexts, or exploring the data-algorithm-compute trinity for AI breakthroughs.
Provides François Chollet's framework for understanding intelligence, AGI development paths, and the limitations of current AI approaches. Use this skill when users ask about- (1) What intelligence really means and how to define AGI, (2) Why scaling pre-training alone won't achieve AGI, (3) The difference between memorized skills and fluid intelligence, (4) Test-time adaptation and its role in AGI, (5) The ARC benchmark and what it measures, (6) Type 1 vs Type 2 abstraction in AI systems, (7) Program synthesis approaches to intelligence, (8) Evaluating claims about AGI progress, or (9) Understanding the conceptual foundations needed for building generally intelligent systems.
Strategic questioning framework for AI startup founders navigating AGI uncertainty. Use when founders or entrepreneurs need to evaluate AI startup ideas, assess defensibility in a rapidly changing landscape, plan strategy assuming 2-3 year AGI timelines, determine what problems remain hard when AI capabilities expand, or think through hiring/product/go-to-market decisions in the AI era. Triggers include questions like "Should I start this AI company?", "How do I plan for AGI?", "What's defensible in AI?", "How should AI change my startup strategy?", or "What questions should I ask before building an AI product?"
Provider-independent FFmpeg finishing workflow for AI agents preparing generated or edited media deliverables. Use when finalizing images, image sequences, video, audio, captions, overlays, social/export variants, checksums, manifests, delivery specs, and QA with ffmpeg/ffprobe, including transcode versus stream-copy decisions, scaling, frame-rate handling, color metadata caution, loudness normalization, subtitle burn-in or sidecars, concat/trim, GIFs, batch variants, and reproducible command reporting.
Reads and writes ClickUp tasks through the clickup CLI: prepares a task for grilling (card, comments, linked tasks, statement in the developer's own words, list of unknowns), creates tasks and bug reports to the team's own convention, puts estimates and comments on tasks. Use whenever the user gives a ClickUp task id or app.clickup.com/t/ URL, or says «прочитай задачу», «что в таске», «подготовь к грилю», «заведи таску», «багрепорт», «поставь оценку», «напиши коммент в таску», read the task, create a task, bug report, estimate the task, comment on the task — even when ClickUp is never named and even when the request looks like a one-liner.
Review somebody else's merge request: read the diff against the team checklist, hunt bugs with the built-in reviewers, and post the findings as comments on the merge request. Trigger on «сделай ревью», «посмотри MR», «проверь мерж реквест», «отревьюй», review this MR, code review — and on any GitLab merge-request URL, even with no other instruction. Read-only on the code: it describes fixes, it never applies them. Reviewing your own fresh work is part of implement-task instead.
Use when working on this project's architecture documentation in .arc42.md files.
Expert CSRD (Corporate Sustainability Reporting Directive, EU 2022/2464) compliance advisor. Use this skill whenever a user asks about CSRD, European Sustainability Reporting Standards (ESRS), double materiality assessment, sustainability reporting obligations, ESG disclosure, CSRD scope and thresholds, value chain reporting, XBRL digital tagging, third-party assurance, CSRD gap assessments, CSRD implementation timelines, ESRS E1–E5 environmental standards, ESRS S1–S4 social standards, ESRS G1 governance, the 2026 Omnibus scope change (Directive (EU) 2026/470, 1,000+ employees) and revised/simplified ESRS (July 2026), CSRD vs GRI/TCFD/SASB alignment, or any EU corporate sustainability reporting question. Trigger even if the user only mentions "ESG reporting Europe", "sustainability disclosure EU", or "non-financial reporting".
AMM liquidity provision mathematics including constant-product, concentrated liquidity, price impact, and LP share calculations
Linting and formatting SAS code with @sasjs/lint - the .sasjslint rules and their defaults, severityLevel and exit codes, per-file @sasjslint overrides, what the formatter fixes, and how the SASjs CLI, VS Code extension and SASjs Server run it. Use when configuring lint rules, resolving a lint warning, or wiring lint into CI, a git hook or an editor.
Export Administration Regulations (EAR, 15 CFR Parts 730-774) compliance advisor — ECCN classification across all 10 CCL categories and 5 product groups (A-E), EAR99 determination, jurisdiction analysis (EAR vs ITAR order of review), license requirement analysis via Country Chart, all license exceptions (LVS, GBS, CIV, TMP, RPL, GOV, TSU, ENC, TSR, APP, BAG, AVS, ACE), end-user/end-use controls (Entity List, Denied Persons List, Unverified List, MEU List), deemed export rules, Foreign Direct Product Rule (FDPR), de minimis thresholds, 10 General Prohibitions, SNAP-R license applications, voluntary self-disclosure, civil/criminal penalties, Export Compliance Program (ECP) design, and EAR vs ITAR jurisdiction determination. Use for any dual-use export control, CCL classification, or BIS compliance question.