Loading...
Loading...
Found 1,375 Skills
Generate thumbnails from images with smart cropping, multiple sizes, and batch processing. Ideal for web galleries, social media, and app icons.
Deploys and monitors TrueFoundry batch jobs, scheduled cron jobs, and one-time tasks. Uses YAML manifests with `tfy apply`. Use when deploying jobs, scheduling cron tasks, checking job run status, or viewing execution history. For listing job applications, use `applications` skill.
Plan cross-border e-commerce expansion. Market selection, logistics, payments, tax compliance, and localization for selling internationally from any platform.
Validate and sanitize user input to prevent XSS, injection attacks, and ensure data quality. Use this skill when you need to validate forms, sanitize user input, prevent cross-site scripting, use Zod schemas, or handle any user-generated content. Triggers include "input validation", "validate input", "XSS", "cross-site scripting", "sanitize", "Zod", "injection prevention", "validateRequest", "safeTextSchema", "user input security".
Implements the Syncfusion dotnet Calculate Library for parsing and evaluating formulas using CalcEngine, ICalcData, CalcQuickBase, and ExcelLikeComputations. Supports formula computation, custom functions, cross-sheet references, and XlsIO formula evaluation. Trigger when implementing formula calculations, expression parsing, workbook formula evaluation, or custom function registration.
When the user wants help with Google Ads attribution models, data-driven attribution, attribution windows, cross-channel attribution, how attribution affects Smart Bidding, multi-touch conversion paths, or understanding which campaigns are actually driving conversions. Triggers on 'attribution', 'attribution model', 'data-driven attribution', 'last click attribution', 'assisted conversions', 'conversion window', 'multi-touch', 'attribution model comparison', 'first click attribution', 'credit allocation', or 'which campaign is driving conversions'. For conversion tracking setup see google-ads-conversion-tracking. For Smart Bidding strategy see google-ads-bidding.
📡 Pulse — Twice-daily tech briefing for group distribution. Designed to be triggered by cronjob at morning and evening, or manually. Use this skill only when the user says "pulse" or "/pulse".
Search Slack for interpreted organizational context -- decisions, constraints, and discussion arcs that shape the current task. Produces a research digest with cross-cutting analysis and research-value assessment, not raw message lists. Use when searching Slack for context during planning, brainstorming, or any task where organizational knowledge matters. Trigger phrases: 'search slack for', 'what did we discuss about', 'slack context for', 'organizational context about', 'what does the team think about', 'any slack discussions on'. Differs from slack:find-discussions which returns individual message results without synthesis.
Apply the Fama-French three-factor model to decompose asset returns into market, size, and value factors. Use this skill when the user needs to explain cross-sectional return differences, evaluate fund performance beyond CAPM alpha, assess small-cap or value tilts in a portfolio, or when they ask 'why do small caps earn more', 'is value premium real', or 'what factors drive returns'.
Early rug-risk triage for token launches and small DeFi deployments from public data—liquidity lock and pool events, dev and sniper wallet clustering, contract authority and transfer-risk checks, coordinated exits, and evidence-backed risk scores. Use when the user asks for rug pull detection, pump-and-dump signals, launch red flags, LP removal forensics, or cross-chain profit exit tracing—not for front-running trades, harassing teams, or certifying scams without on-chain proof.
Fast Track for Feature Process - When requirements are clear and scope is small, skip the complete design process, write a compact {slug}-design.md, and proceed directly to implementation after one confirmation from the user. What is compressed is divergent discussions and phased reviews, not quality standards - code pointers, acceptance criteria, etc., must not be omitted. Trigger scenarios: User says "quick mode", "fastforward", "cut the steps", "just start working". Not suitable for complex features involving cross-subsystem integration, new terminology sorting, or more than 4 promotion steps - in these cases, proactively inform the user to revert to the complete process.
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.