菜单
SkillsMP 已收集 build-with-dhiraj/ai-workflow-framework-portability-kit 中的 154 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 40 / 154 个已收集 Skill。
AI image generation for SEO assets: OG/social preview images, blog hero images, schema images, product photography, infographics. Powered by Gemini via nanobanana-mcp. Requires banana extension installed. Use when user says "generate image", "OG image",…
原文语言：英语
Live SEO data via DataForSEO MCP server. SERP analysis (Google, Bing, Yahoo, YouTube, Google Images), keyword research (volume, difficulty, intent, trends), backlink profiles, on-page analysis (Lighthouse, content parsing), competitor analysis, content…
原文语言：英语
Full-site crawling, scraping, and site mapping via Firecrawl MCP. Use when user says "crawl site", "map site", "full crawl", "find all pages", "broken links", "site structure", "discover pages", "JS rendering", or needs site-wide analysis.
原文语言：英语
SERP-based semantic topic clustering for content architecture planning. Groups keywords by actual Google SERP overlap (not text similarity), designs hub-and-spoke content clusters with internal link matrices, and generates interactive visualizations.…
原文语言：英语
Google SEO APIs: Search Console (Search Analytics, URL Inspection, Sitemaps), PageSpeed Insights v5, CrUX field data with 25-week history, Indexing API v3, and GA4 organic traffic. Provides real Google field data for Core Web Vitals, indexation status, search…
原文语言：英语
Snapshot Claude Code setup (agents, skills, plugins, MCP, tooling) into a portable folder. Use for backup or Mac migration.
原文语言：英语
How to write effective prompts for Claude Design (claude.ai/design), for both creating new designs and editing existing prototypes, decks, or pages. Use this skill whenever the user wants to prompt Claude Design, iterate on a Claude Design project, convert…
原文语言：英语
Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files
原文语言：英语
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
原文语言：英语
Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern
原文语言：英语
Audit a UI or design against WCAG 2.2 AA/AAA and ARIA patterns, returning criterion-referenced findings with severity and specific fixes. Use when the user wants an accessibility check, contrast verification, keyboard/screen-reader review, or wants to confirm…
原文语言：英语
Discover the best community MCP server on GitHub/npm for any service, install it into Claude Code via the `claude mcp` CLI, wire authentication from existing local credentials, and verify tools work. Use when the user asks to add, install, connect, or…
原文语言：英语
Use when valuing a BANK, NBFC, small-finance bank, or insurer — any financial-services stock where ROCE and free-cash-flow break down and the stock-onboarding v2 machinery's `bank` model applies (CSBBANK, UJJIVANSFB, NORTHARC, KOTAKBANK, HDFCLIFE, etc.).…
原文语言：英语
Use when assessing how well a CEO/management team allocates capital — to score the CONVICTION dimension "management quality" with a structured, cross-CEO scorecard drawn from William Thorndike's Outsiders framework. Applies during Stage 1 dossier writing,…
原文语言：英语
Use when working with color naming, color theory, color spaces, color definitions, or any task involving color knowledge - palettes, ramps, gradients, conversions, accessibility, perceptual matching, pigment mixing, print-vs-screen color, CSS color syntax, or…
原文语言：英语
Generate, extend, or audit design tokens in DTCG format with the 3-tier architecture (primitive → semantic → component). Use when the user wants a color palette, type scale, spacing/shadow/radius/motion tokens, multi-brand theming, or wants to validate token…
原文语言：英语
Extract design primitives from a public website and generate starter token files for your project.
原文语言：英语
Strip AI-writing tells and, for anything a decision-maker reads, enforce decision-first structure so it lands like a human wrote it. Two modes: STAKEHOLDER/EXEC (pattern-removal + structure, add ZERO voice) and PEER (pattern-removal + measured voice). Pick…
原文语言：英语
The global 4-stage idea→shipped pipeline (Sonnet brainstorms → tracker tickets with dependencies → Fable plans in-repo → Fable orchestrates Opus 4.8 implementers). Invoke when the user says "run the pipeline", "idea to build", "take this brainstorm and build…
原文语言：英语
Use when the conviction step needs a rigorous moat judgment — taxonomy, durability test, and pricing-power check — for any Indian stock being onboarded or re-graded. Enriches the existing v2 conviction step (STAGE 3) and the inversion/FOREVER gate (STAGE 4);…
原文语言：英语
Detect material events (results, deals, filings, governance) on HELD Indian stocks and refresh the affected dossier head-windows so verdicts stop decaying — without ever silently re-ranking the LOCKED Action Dashboard. Use when the user says "refresh the…
原文语言：英语
Use when deciding HOW MUCH to put in a position — the "Max size" (col M) decision on the Action Dashboard. Encodes Kelly fraction + half-Kelly for estimation uncertainty, conviction-scaled position ceilings consistent with the v2 conviction rubric and MoS…
原文语言：英语
Use when onboarding/grading an Indian stock and you need LIVE ground-truth — retail due-diligence, management-call commentary, and community sentiment — to corroborate or disconfirm a dossier. This is the finance-desk "channel-checker / primary-research…
原文语言：英语
Convert frontend code (Vite, React, etc.) to a Stitch Design by chaining static HTML extraction, design system extraction, and file upload. **ALWAYS** use this skill when the user's intent is to move existing web apps or React components into Stitch (e.g.,…
原文语言：英语
Extract a comprehensive design system (DESIGN.md) directly from frontend source code — React, Vue, Svelte, Angular, plain HTML/CSS, or any web framework. Analyzes component files, stylesheets, Tailwind configs, theme definitions, and design tokens to produce…
原文语言：英语
Extract self-contained static HTML from a built web application or React components by inlining CSS and images. Use this skill whenever you need to capture a specific UI state, share a static version of a page, or prepare assets for Stitch upload, even if the…
原文语言：英语
Generate new screens from text prompts or images, edit existing screens with prompts and design system tokens, and generate design variants using Stitch MCP. Includes prompt enhancement pipeline, design mappings, professional UI/UX terminology, design tokens…
原文语言：英语
Manage design systems in Stitch using MCP tools. Includes retrieval of assets, creating/updating design systems in Stitch, and applying them to screens.
原文语言：英语
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
原文语言：英语
Upload local assets (images, mockups, extracted HTML, design markdown) to a Stitch project. ALWAYS use this skill when you need to upload visual assets, HTML pages, or design docs to Stitch, particularly when direct MCP tool calls fail or truncate due to…
原文语言：英语
Onboard new Indian stocks into the "Paise se Paisa" Action Dashboard end-to-end, using the v2 vault-aligned machinery (understanding gate → quality-gated conviction with ROIC+runway → conservative IV range → conviction-scaled margin-of-safety vs opportunity…
原文语言：英语
Closed-loop reasoning discipline distilled from Claude Fable 5's handover manual — read the request beneath its words, decompose by checkability, verify by re-derivation, label known vs guessed, prosecute your own conclusion, report answer-first with…
原文语言：英语
Write or review UI copy — buttons, errors, empty states, microcopy, notifications, labels — using the voice & tone system (clear, concise, useful, human, honest) with the what→why→how error formula and inclusive-language rules. Use when the user needs…
原文语言：英语
Use when valuing a durable, high-ROIC LONG-RUNWAY COMPOUNDER — a proven franchise with a 10–20 year reinvestment runway (IGI, CAMS, the HUL/NESTLE/TITAN "forever-in-waiting" trio, consumer/franchise/platform compounders) — where a standard 5-year DCF would…
原文语言：英语
End-to-end playbook for moving a full developer + Claude Code environment from one Mac to another under the SAME Claude login — covers both the OLD-Mac backup side and the NEW-Mac restore side. Trigger this whenever the user is getting a new Mac/MacBook,…
原文语言：英语
Use when sharpening Stage 4 (inversion / strict FOREVER gate) of the v2 onboarding machinery, or when attaching a decision-journal artifact to any conviction call. Provides process-vs-outcome (resulting) discipline, base-rate and skill/luck awareness,…
原文语言：英语
Systematically FIND, GRADE and BUY great ETFs / REITs / InvITs that ride durable global trends — evaluating funds LIKE stocks (verdict → conviction → margin-of-safety) and holding the good ones for life. The fund mirror of the stock onboarding pipeline. Use…
原文语言：英语
Use at the DOSSIER / UNDERSTANDING stage (Stage 1) on EVERY stock to run the governance-integrity screen before any conviction or IV work. India-specific promoter and accounting red-flag checklist grounded in the SEBI-Satyam, SEBI-IL&FS-CRA, and…
原文语言：英语
Design and operate loop-engineered agent systems in Claude Code and Cursor. Use for loop engineering, harness design, Ralph loops, /loop, /goal, agent hub, self-improving agents, SKILL.md optimization, or choosing installable loop tooling from the research…
原文语言：英语
SUPERSEDED (2026-06-13) — OFFLINE xlsx-research variant ONLY; for adding/ranking stocks into the LIVE Action Dashboard use the stock-onboarding-pipeline skill instead (vault-binding v2). This v1 runs the full matured equity quality+valuation ranking pipeline…
原文语言：英语