В каталоге 183 730 навыков в 14 категориях.
Keep Dropbox API scripts authenticated for good — the one-time OAuth flow that yields a refresh token, and the four-line...
Comprehensive skill for implementing dropdown components in React-based modals and forms, ensuring consistent data bindi...
Product research for dropshipping businesses. Identify profitable products with reliable suppliers, healthy margins, and...
Every Dropsuite (NinjaOne SaaS Backup) read, plus fleet-wide backup health, coverage gaps and billing reconciliation fro...
Divergence Regularized Policy Optimization (DRPO) — smooth advantage-weighted quadratic regularizer replacing hard trust...
Drug-Indication Mapping - Map drug indications: ChEMBL drug indications, FDA indications, OpenTargets drug associations,...
---name: drug-interaction-checker
Drug Metabolism Study - Study drug metabolism: FDA metabolism data, ChEMBL metabolism records, PubChem compound data, an...
Drug Repurposing Screening - Screen existing drugs for new indications by querying FDA indications, ChEMBL mechanisms, a...
Comprehensive Drug Safety Profile - Build a complete drug safety profile by combining FDA adverse reactions, boxed warni...
Drug-Target Structural Biology - Integrate drug and target structure: get drug from ChEMBL, target structure from PDB, d...
Drug Warning Intelligence Report - Generate drug warning report: ChEMBL drug warnings, FDA boxed warnings, adverse react...
Use this skill when the user asks about commercial driver drug & alcohol testing under 49 CFR 382 + 40 — the six testing...
Cite-or-Block 架构下的药名 cross-check 原子 skill。给定报告文本与 .cache/<slug>/sources/,扫描每个药品提及 → 找最近 citation 锚点 → 核对锚点指向的源里是否真的提到了此药...
Pharmaceutical research assistant for drug discovery workflows. Search bioactive compounds on ChEMBL, calculate drug-lik...
Checks for potential drug-drug interactions (DDIs) between a list of medications.
Check for drug-drug interactions in veterinary patients with species-specific pharmacokinetic considerations. Use when a...
Document a pharmacist's clinical intervention — the interaction or error spotted, what was done, what the prescriber dec...
Medication photo to personalised PGx dosage card via Claude vision — snap a pill, get genotype-informed guidance
Provides correct pronunciation guides for complex drug generic names. Generates phonetic transcriptions using IPA and au...
Comprehensive drug screening pipeline from molecular filtering through QED/ADMET criteria to protein-ligand docking, ide...
Use when a task involves reviewing evidence for a proposed drug-target relationship across mechanism, genetics, pharmaco...
Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, ta...
研究 codex 使用 skill 生成 survey 這件事
Search DrugBank comprehensive drug database with natural language queries. Drug mechanisms, interactions, and safety dat...
Predict the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties of the input molecules.
Check if the input protein sequence or molecule SMILES string is valid.
Calculate disease reversal scores for the provided molecules relative to a specific disease.
Compute the drug-likeness metrics (QED score and Number of violations of Lipinski's Rule of Five) of the input candidate...
Use ESMFold model to predict 3D structure of the input protein sequence.
Implement data transmission between the local computer and the MCP Server using Base64 encoding
Generate new molecules sampling from the input two warhead fragments.
Calculate different types of molecular properties based on SMILES strings, covering basic physicochemical properties, hy...
Compute the Tanimoto similarities between a target molecule and a list of candidate molecules using Morgan fingerprints.
from mcp.client.streamablehttp import streamablehttpclient
Given a protein sequence and its structure, employ ProSST model to predict mutation effects and obtain the top-k mutated...
Search the protein information from the input gene name and downloads the optimal PDB or AlphaFold structures.
The keeper of the animal ecosystem. Not an animal themselves, but the one who understands the forest deeply enough to in...
Apache Druid technology expert. Deep expertise in real-time analytics, columnar ingestion, segment management, query typ...
Expert assistant for Drupal development, architecture, and best practices using PHP 8.3+ and modern Drupal patterns
Routes Drupal contribution work to the right contribution-quality stage and supplies the contribution knowledge layer. U...
Drupal Back End Specialist skill for custom module development, hooks, APIs, and PHP programming (Drupal 8-11+). Use whe...
Execute Drupal configuration changes from drupal-planner specs.
Drupal code, config, and architecture review for PRs, implementations, and migration plans.
Drupal Front End Specialist skill for theme development, Twig templates, and rendering system (Drupal 8-11+). Use when w...
Plan Drupal implementations — entities, config, migrations, cache, permissions.
Plan Canvas Code Components — definition, metadata, props, data fetching, styling, validation.
Plan Drupal search — Search API, Solr/Elasticsearch, faceted search, indexing strategies.
Plan Drupal themes — base theme, component strategy (SDC/traditional), CSS methodology, responsive design.
Review Drupal themes — template structure, CSS organization, component patterns, performance.
Drupal development tooling skill for DDEV local environments and Drush command-line operations (Drupal 8-11+). Use when...
Manage Drupal content, entities, views, menus, fields, and site structure using drush webmaster (wm:*) commands. Use whe...
When writing or reviewing code to eliminate duplicated knowledge and business logic. Use when the user says "this is dup...
Detect duplicate code and suggest DRY refactors using jscpd
Find the subsystems that should be one subsystem. Traces a codebase resource-first instead of subject-first, then report...
Preventing and removing repetitive code in scala-ts. Use when asked to deduplicate code, find repeated patterns, refacto...
Refactor duplicated code by extracting helpers, shared abstractions, or clearer reusable structure. Use when asked to ap...
Review code from the current (or clearly-restored) session for DRY opportunities. Apply the obvious wins immediately; su...
Trigger: DRY, duplicated business knowledge, duplication. Distinguish harmful knowledge duplication from harmless simila...
Scans new/modified code against multi-mono shared libraries (@metasaver/core-utils, @metasaver/core-service-utils, @meta...
Perform a comprehensive DRY (Don't Repeat Yourself) code review on a codebase. Identifies duplicated code, repeated logi...
Detects deeply nested loops with duplicated inline logic and recommends extracting into small, named functions. Enforces...
This rule enforces the Don't Repeat Yourself principle to avoid code duplication and improve maintainability.
When writing code, identify and eliminate duplication Use when enforcing code quality standards. Quality category skill.
Use when user asks to "remove duplicates", "DRY up code", "extract common logic", "consolidate repeated code", or when /...
Simulates command execution in dry-run mode without file modifications. Sets dry_run flag, executes command with read-on...
Validate an implementation plan by tracing through each change without implementing. Use when user says dry walkthrough,...
Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards), s...
This skill should be used when the user asks to 'start data analysis', 'brainstorm analysis approach', 'plan a data proj...
Takes over an existing PR, branch or agent thread and finishes its original goal while keeping credit for the first cont...
Expert audit of a project's design system across TWO dimensions — (1) clean codebase and (2) AI-native structure (can an...
Run N independent attempts at the same task in parallel, pick the strongest as the base, and graft the best parts of the...
Find what a change could break outside its own diff, then prove the key safety fact by running real code. Use before shi...
Design the types, function signatures and module layout first, agree on that shape, then implement against it. Use when...
Bootstrap a project's design system from the shared base once a DA (art direction) is chosen — Phase 1. Use when the use...
This skill should be used when the user asks to "start a data science project", "brainstorm analysis", "plan a data anal...
Give the user a short plain-language catch-up on what changed since their last message, followed by every decision still...
DS Code Auditor — finds ALL design system violations in Swift code: inline patterns that should be reusable components,...
Keep a PROGRESS.md for long tasks and move to a fresh session or subagent that reads only that file when the context get...
Subagent delegation for data analysis. Dispatches fresh Task agents with output-first verification.
Builds a frontend with a clear visual direction instead of the generic AI look. Use when you create a new page, app scre...
Reviews an existing UI with scores based on evidence, then fixes the highest-impact problems. Use when a page or app scr...
Use when asked how other design systems handle a component, prop, token or pattern; to name a component, prop or token;...
DS Ecosystem Master Plan — полный пайплайн создания Figma экосистемы Hexbound. 10 этапов: UI-аудит → Foundations → Token...
"Provides Performs exploratory data analysis using summary statistics distributions, correlations, and descriptive metho...
Explain how a piece of code works, why it is built that way, and what that means, in plain language a person can follow....
DS Extract Component — extracts an inline UI pattern from Swift code into a reusable component + creates matching Figma...
Generate or refresh a clean Figma design system FROM the code (the code is the source of truth). Use when a project has...
DS Figma Sync — verifies 1:1 parity between Swift code tokens/components and Figma DS file, finds mismatches, and fixes...
This skill should be used when the user asks to 'fix analysis', 'wrong results', 'notebook error', 'reviewer feedback',...
Create structured handoff document for DS workflow session pause/resume.
Pick the right deepseek-stack skill for a task and explain how the pack fits together. Use when the user asks which skil...
REQUIRED Phase 3 of /ds workflow. Enforces output-first verification at each step.
Gets independent reviews of a change from two or three different models or providers and loops on fixes until they agree...
Keep a one-row-per-decision log during long or unattended runs, and re-read it before each step so the run does not drif...
Find mistakes agents keep repeating in this repo and turn each into structure that blocks it, preferring types over lint...
项目目录结构地图 - 生成带说明的可视化目录树，快速理解任意代码库
Always-on working style for DeepSeek agents: restate the task, read before editing, small verified steps, evidence befor...
REQUIRED Phase 2 of /ds workflow. Profiles data and creates analysis task breakdown.
Write a numbered plan with an acceptance check for each step, critique it once in a fresh pass, revise it, then execute...