web-state-jotai
Atomic state management with auto-dependency tracking
Найдите подходящую возможность для вашего агента.
Atomic state management with auto-dependency tracking
Remove visible Gemini AI watermarks from images via reverse alpha blending. Use for cleaning Gemini-generated images, removing the star/sparkle logo watermark, batch watermark removal.
Sync experiment results from the code repo into the paper's daily experiments log (daily_experiments.tex). Use when you have new experiment results to record, want to update the paper with latest numbers, or log experimental findings from an ML research project.
Self-improving review loop for Ralph Wiggum skills. Reviews skills against best practices, implements improvements, and continues until two consecutive clean reviews. Use when validating or improving the ralph-prompt-* skill suite.
Systematic workflow for debugging Cardano ledger epoch pots mismatches in Dolos. Use when an epoch test fails or treasury/reserves/rewards diverge from DBSync.
Reference for the AdKit CLI (`adkit-cli` on npm, `adkit` command). Maps commands to ad operations: creating campaigns, ad sets, and ads on Meta, managing drafts, uploading media, searching interests. Load when the user wants to execute ad operations through the terminal or when `adkit` is installed and the user is ready to publish. Not for strategy, copywriting, creative advice, or learning about ads.
Comprehensive guidance for building and debugging JavaScript and TypeScript CLIs with @clack/core and @clack/prompts, backed by bundled upstream source and examples. Use when implementing clack prompt flows, deciding between core primitives and styled prompts, adapting clack examples, or validating clack API usage.
Design or review command-line interfaces for usability and automation: help text, args/flags, stdout vs stderr, exit codes, TTY behavior, config precedence, and safe handling of secrets and destructive actions.
Install, use, and manage CodeWalk — a macOS app + CLI for interactive visual code walkthroughs. Use this skill whenever the user mentions CodeWalk, codewalk, code walkthrough, visual code explanation, code presentation, code tour, or wants to visually walk through code with animations and highlights. Also trigger when the user says things like '코드를 가르쳐줘', '코드 설명을 눈으로 보여줘', 'UI로 보여줘', 'show me the code visually', 'teach me this code', 'walk me through', or any request to explain code in a visual/interactive way rather than plain text. Also use when the user wants to install, uninstall, update, or troubleshoot CodeWalk, or when they want to create walkthrough JSON files for code explanation.
This skill should be used when the user asks to "audit domain authority", "domain trust score", "CITE audit", "how authoritative is my site", "domain credibility check", "is my domain trustworthy", or "domain credibility score". Runs a full CITE 40-item domain authority audit, scoring domains across 4 dimensions with weighted scoring by domain type. Produces a detailed report with per-item scores, dimension analysis, veto checks, and a prioritized action plan. For content-level assessment, see content-quality-auditor. For link profile details, see backlink-analyzer.
Brand identity generator that creates logos, color palettes, typography, brand images, and checks domain and social media username availability. Suggests and verifies available handles across platforms. Outputs a complete brand kit to Notion, Google Drive, or downloadable PDF. Use this skill when the user says things like: 'create a brand for...', 'build a brand identity', 'I need a logo for...', 'brand kit for my business', 'check if this domain is available', 'find me a username for...', 'branding for my startup', 'design a brand', 'logo and brand for...', 'help me name my brand', or wants to create brand assets, check domain availability, or find social media handles.
Research and validate product names with domain and social media availability checks. Generates name candidates, checks .com/.com.br/.io/.app domains, verifies Instagram/X/GitHub usernames, and scores name quality (pronounceable, memorable, brandable). Use when naming products, startups, apps, or brands. Also use when the user provides name candidates to evaluate, asks to check domain availability, wants name suggestions, or any naming-related task. Triggers on "check if a name is available", "suggest names for", "find a name for", "what should I call", "name ideas for", "domain available", "check this name", "evaluate these names".
Search Argentine legal databases (SAIJ, JUBA, CSJN, JUSCABA) for jurisprudence, legislation, case summaries, and doctrine using the `ley` CLI. Use when the user asks about Argentine law, court decisions, legal precedents, fallos, jurisprudencia, legislación, or mentions SAIJ, JUBA, CSJN, JUSCABA. Supports parallel search across databases, JSON/table/text output, and filtering by jurisdiction. Built from reverse-engineered MCP servers (hernan-cc) — direct HTTP calls, no MCP layer needed.
Write, scaffold, explain, and refactor code using the lorisleiva/laravel-actions package. Use this skill whenever the user is working with Laravel Actions, wants to create an action class, convert a controller/job/listener/command into an action, asks how to use AsAction trait, dispatch an action as a job, use an action as a controller or listener, set up validation/authorization in an action, test or mock actions, or asks anything about the laravel-actions package pattern.
把本仓库的工程手册 Tier0 规则注入到 AI vibe coding(跨语言:Java/Python/TS/React/Vue)。