В каталоге 183 730 навыков в 14 категориях.
EU MDR 2017/745 regulation specialist and consultant for medical device requirement management. Provides comprehensive M...
Staged v6.1 closure workflow for the adult MDR-GNB current-state diagnostic prediction-model review. Use to screen diagn...
Produces the Messaging & Direction Summary covering product pitch, features/benefits, use cases, audiences, value props,...
Creates content with MDX including Markdown with JSX, custom components, and frontmatter. Use when building content-heav...
"Content schema design and MDX configuration patterns for knowledge bases. Use when designing content structure, configu...
Use whenever creating, renaming, or editing any file under docs/ in this repo, or when asked to compile/build the book P...
Comprehensive MDX content sanitizer that escapes angle brackets, generics, and other JSX-conflicting patterns to prevent...
Picks mdxcn next to prose. In Notion, Linear, or a README, pastes the framed ASCII from the docs MDX tab (dashed box, [...
View or change the current member's Egregore profile across Claude Code, Codex, Pi, and Prime. Use for /me, 'who am I',...
Help order food timed to arrive at a specific time. Works backward from target arrival, suggests restaurants, builds car...
Trigger: OpenAI meal plan, prompt, structured output, food restrictions, AI evaluation. Build NutrIA AI safely.
Weekly meal prep and shopping assistant that selects 3 recipes with varied proteins, generates categorized shopping list...
Expert in batch cooking, meal planning, food storage, and efficient kitchen workflows
Turn what's actually in the fridge and 90 minutes on Sunday into a week that mostly feeds itself — a cook-once-eat-thric...
meal-tracker — Track meals and calories from a photo or text description. Vision-based portion estimates, daily calorie/...
Trade mean reversion setups in the style of Scarface Trades, the mean reversion specialist known for mathematical precis...
Use when writing a Bollinger-band mean-reversion strategy on Superior Trade — anything described as mean reversion, BB b...
Roleplay as the "Armchair Executioner" — a maximally destructive, minimally accountable peer reviewer. Use when the user...
Mean test another agent when someone asks you to test, check or break it. Invoke on "test @agent", "mean test @agent", "...
Performs mean-variance portfolio optimization to find the tangency portfolio. This skill should be used when users want...
Use intention-revealing names that explain what a variable holds or what a function does Use when enforcing code quality...
Write a SLICE's measure lens as a grounding doc (measure.md) — the delivery-measurement focus, the metrics that prove it...
Establish magnitude, quality, cost, or change with comparable observations that inform a bounded decision. Use for basel...
Defines and tracks UX success through metrics, measurement frameworks, and experimentation. Part of the Intent design st...
Quantify values with uncertainty bounds. Use when estimating metrics, calculating risk scores, assessing magnitude, or m...
Use this to measure whether an AI agent actually completed its task end to end, not just whether individual LLM calls lo...
Designs an A/B test or experiment with clear hypothesis, variants, success metrics, sample size, and duration. Use when...
动 briffy 里任何用户看得见的东西之前,先把真工作区量一遍——分布、基数、每一格里真有什么。当你要回答「这个功能该怎么做」「这一版好不好」「该不该加这个维度」,或者要改筛选、搜索、检索、卡片、设置里任何一处呈现时使用。也用于给一个改动...
This skill should be used when the user wants to set up measurement or judge whether they've built something people want...
Measure logistics improvement results from before-after metrics, implementation dates, baselines, controls, and review b...
Scores completed OKR sets at cycle close with KR-level scoring per the canonical OKR type enum (committed | aspirational...
Load this skill when speed, memory, or size is the task: something is slow, a benchmark is written or read, or a change...
Define practical success measures for an initiative, including baselines, metric definitions, meaningful targets, and sa...
Analyze survey results into actionable PM insights. Produces persona segmentation, hypothesis validation status, themati...
Run measured performance optimization.
실제 웹·앱 화면을 콘텐츠 이미지나 GIF로 가공할 때 사용. 개인정보를 모자이크·블러 처리하고, 실제 대상의 픽셀 또는 렌더링 좌표를 측정해 강조 박스를 정확히 배치하며, 제목·캔버스·전체 프레임이 잘리지 않도록...
Measurement and tolerance for the trades — how dimensions are specified, measured, and verified, and how real parts are...
Auditar confiabilidade de tracking, eventos de conversão, janelas, cobertura e atribuição em relatórios de CRM e mídia p...
Review measurement instruments and results — LLM-as-instrument content scoring AND hand-tuned composite/weighted scoring...
Fix the instrument before trusting the number. Use when someone says "the metric improved but I don't trust it", "measur...
Measurement discipline for claims that rest on data. Use when deciding on an experiment result, setting a threshold (閾値)...
Measure product-market fit (PMF) and produce a PMF Measurement Pack (Sean Ellis “very disappointed” survey, retention/us...
Help users assess and achieve product-market fit. Use when someone is trying to determine if they have PMF, measuring us...
Applies RECIST 1.1 and iRECIST criteria for tumor measurement and treatment response assessment. Use when measuring tumo...
Capture bugs/enhancements/ideas to request-logs. For quick operations use /mc command instead.
Query the MecDDI mechanism-based drug-drug interaction database. Use whenever the user asks about drug-drug interactions...
Structure thinking using Mutually Exclusive, Collectively Exhaustive categories. Use when breaking down problems or ensu...
Categorize the factors of a problem so they don't overlap (Mutually Exclusive) and nothing is missed (Collectively Exhau...
Read a garage quote or invoice like someone who can't be padded — which line items connect to your actual symptom, which...
Guides mechanical design decisions toward elegant, manufacturable, serviceable solutions with a strong bias toward tool-...
Ability to design, analyse, test, and maintain mechanical systems and components that meet defined functional, safety, a...
Compile an English protocol specification into MFS (Mechanism Flow Specification) — a mechanism-level formal language th...
This skill group covers calculations of mechanical properties of crystalline materials. Two main approaches are availabl...
Use when driving Ansys Mechanical via PyMechanical (ansys-mechanical-core) through the sim runtime, or reading solved `....
Executes another MetaSkill, which must be located in
A recipe here says how to REBUILD something you already built and sold or used: a stand-alone device for Fab (for
The SudoSkill mechanic allows you to force the targeted entity to “cast”
Audit SENTINEL game data integrity. Validates regions, jobs, vehicles, and favors against schema enums.
Generates Mermaid flowchart code and visual diagrams for pathophysiological mechanisms. Converts medical concepts into c...
Reference for ability family semantic groupings and gameplay meanings
Analyze relationships across multiple SAE features - co-activation patterns, shared drivers, and subsystem identificatio...
Match SAE features between Ultra (24K) and Full (2K) models based on activation patterns and token overlap
Analyze SAE decoder weights - output influence, feature importance, and decoder similarity
Reference skill for Splatoon ability families, AP rungs, token constraints, and domain rules for mechinterp experiments
Orchestrate a systematic research program to investigate and meaningfully label SAE features
Manage feature labeling workflow - queue management, label storage, similar features, progress tracking
Propose next mechanistic interpretability experiments based on research state, hypotheses, and existing evidence
Quick "first look" overview of SAE features - top tokens, activation stats, weapons, families, sample contexts
Reference catalog of recurring SAE feature patterns - check when labeling new features, add new patterns as discovered
Execute mechanistic interpretability experiments from JSON specs - family sweeps, itemsets, interactions, minimal cores,...
Manage research state for SAE feature analysis including hypotheses, evidence tracking, and research history
Convert experiment results to Markdown research notes and optionally update research state with evidence
Run credibility checks on feature interpretations including split-half stability and shuffle null tests
- Overview
Reconstructed reference notes on EU and UK medical-device software, built from six sources captured 2026-10-13: MDCG 201...
Post-event analyst note (conferences, KOL events, site visits) with the professional note anatomy — headline verdict, pe...
Patient-flow market sizing for med products — prevalence → diagnosed → interested → affordable → covered → treated → per...
Teach medical personnel (physicians, residents, medical students, nurses, PAs, paramedics) clinical knowledge and skills...
Use this skill when a driver is being screened for sleep apnea. Covers FMCSA Medical Review Board (MRB) recommendations,...
Use this skill when a driver does not meet federal medical standards and needs to apply for a variance. Covers applicati...
Polish assemblies and call variants from Oxford Nanopore data using medaka. Uses neural networks trained on specific bas...
Bronze/Silver/Gold layer design patterns and templates for building scalable data lakehouse architectures. Includes incr...
Activates when querying employee and workplace safety data from GCS. Use this skill for: Arbejdstilsynet inspections, wo...
Filtros de química medicinal. Aplique regras de similaridade a fármacos (Lipinski, Veber), filtros PAINS, alertas estrut...
Applies medicinal chemistry filters for compound triage, using drug-likeness rules (Lipinski, Veber, CNS), structural al...
Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity m...
Medicinal chemistry filters for compound triage. Drug-likeness rules (Lipinski Ro5, Veber, Oprea, CNS, leadlike, REOS, G...
Medicinal chemistry filters for compound triage. Apply drug-likeness rules (Lipinski, Veber, CNS), structural alert cata...
研究 codex 使用 skill 生成 survey 這件事
Invoke MEDCOM for military medical advisory, ACGME interpretation, and domain expertise. Advisory-only agent that surfac...
Use to inspect qualification coverage across Metrics, Economic buyer, Decision criteria, Decision process, Implications,...
Create and maintain MEDDIC/MEDDPICC deal scorecards for pipeline hygiene, forecast accuracy, and deal coaching
8-element MEDDPICC qualification scoring rubric with Red/Yellow/Green definitions and discovery questions
Build and evaluate medical text and vision applications with Google MedGemma, including MedGemma 1.5 workflows for CT, M...
Media processing = ffmpeg + imagemagick + sox.
Audio, image and video work: text-to-speech through an OpenAI-compatible endpoint (with a Russian fallback), audio/video...
Expert en médias avancé (content strategy, distribution, monetization, AI generation, DZ context)
Search and inspect the user's photo library, including connected device galleries. Use for photo requests and whenever a...
Systematically analyze existing media to extract transferable elements for new settings. Use when adapting TV, film, or...
Audits web interfaces and media assets for accessible alternatives and operable controls across images, icons, SVG, canv...