Start with the job, then find an open-source answer

claude-favicon-gen takes one square master image, ideally at least 512px, and writes a multi-resolution favicon.ico, small PNGs, an Apple touch icon, Android Chrome icons, and a site.webmanifest when needed. It also provides the references needed for an HTML head or Next.js metadata.icons configuration. The Claude Code plugin runs locally with ImageMagick, so the logo does not need to be uploaded to a third-party service.

yoda-skill adds a /yoda mode that compresses Claude’s replies with OSV inversion and zero filler, with padawan, knight, master, and grandmaster levels. Technical terms, code blocks, and error strings stay unchanged, and the mode turns off automatically for security warnings and destructive-action confirmations. It saves words by deliberately trading away normal sentence order.

write-human diagnoses predictable vocabulary, even sentence rhythm, hedging, and tidy parallel structure, then rewrites in three layers: lexicon, structure, and rhythm. It re-voices the draft with a concrete point of view, challenges what still sounds synthetic, and reads the result aloud. The skill changes surface style; it does not remove cryptographic watermarks or honestly promise a zero-AI detector score.

upshift defines five execution gears: inline edits, fan-out to parallel agents, a Workflow for many similar units, background work for one long job, and scheduled runs for recurring or polling tasks. It can be invoked manually or use a soft prompt hook that suggests the lowest gear fitting the work’s shape. The hint never blocks, and the one-gear-per-job rule helps avoid both under- and over-shifting.

landed maps each artifact to where users actually receive it: a remote branch and green CI, a live URL, an install path, a database row, a registry, a running process, or an email’s Sent folder. Its manual command and proactive Stop hook check that destination rather than trusting a local green build or successful push. The hook is intentionally narrow and blocks only strong ship claims with no destination evidence.

solana-protocol-architect-skill keeps coding agents in the implementation role while it designs the protocol first. It examines oracle, collateral, liquidation, authority, and economic-attack choices, then produces a threat model, parameter review, runnable invariants, and tests for an implementation agent. It runs from a protocol description without API keys or blockchain access.

craftcode gives an AI coding agent seven defaults: mirror neighboring code, write intent comments, fail open only at safe edges, make money and auth fail closed, preserve idempotency, prefer native code for tiny needs, and keep a defensive boundary around a clean core. It runs a final checklist and explains when to bend the rules for prototypes, house style, or readability.

founder-decision reframes the decision, distinguishes reversible from one-way doors, selects only the mental models that fit, and runs a pre-mortem against known startup failure patterns. It ends with a clear recommendation, the assumption carrying it, and the signal that would change the answer. An optional gitignored context file can anchor the analysis to your market, stage, model, and constraints.

keepp-skill lets an agent manage a Keepp page through the Keepp Agent API. It can create, list, update, or delete product cards; change layout, about text, theme, hero actions, and card defaults; and choose between an external link, a detail view, or lead capture. A Keepp Pro API key is required.

uxlaws gives a design agent a catalog of 30 UX principles, each paired with its mechanism, application guidance, pitfalls, and a real example. A compact symptom-to-principle index routes the relevant entries and loads the deeper catalog only when needed. Use it as a focused UX pass during interface design or review, not as a generic style guide.

wp-elementor-mcp-skill turns a documented product JSON spec into Elementor’s _elementor_data widget tree and writes it through WordPress REST or MCP. It includes endpoint checks, offline structural validation, and a dry-run path, with real builds defaulting to draft pages. After an API write, update the page in Elementor or regenerate CSS and data so its cache picks up the layout.

layout-map-illustrator separates visual restyling from factual labeling: it detects site pads, builds a blank positional anchor, asks an image model for watercolor or cartoon styling with text removed, then overlays names and numbers at exact coordinates. The labels remain reliable even when the art changes. Standalone use requires a Google API key plus google-genai and Pillow.

skill-create-video-meta-ai drives Meta AI through a logged-in browser using Playwright MCP, producing roughly five-second clips from prompts. For a longer story, continue in the same chat so the next scene preserves the style, then stitch clips with ffmpeg. No separate video API key is needed, but Claude Code, the browser connection, and a Meta AI account are required.

claude-skill-llms-txt validates, repairs, or generates llms.txt, llms-full.txt, context files, and per-page Markdown using the llmstxt.org and Mintlify formats. It checks the root H1, blockquote summary, H2 link lists, Optional section, non-fetchable targets, and stray headings, while also guiding discovery headers and serving across stacks. A dependency-free Python validator and Claude Code hook are included.

facebook-leads targets industrial abrasive products by searching public Facebook content or analyzing private text you paste. It classifies buying, selling, competitor, and demand signals, scores lead quality, and exports a styled XLSX with tags, links, filters, and frozen panes. Append mode deduplicates by company name and URL, while public-search mode depends on an external search tool and a configurable result limit.

claude-telegram-bot-skill automates @BotFather through a logged-in Telegram Web session to create one independently revocable push bot per project. A Python standard-library helper then sends notifications from cron or scripts, reusing the same chat ID while storing a separate token for each bot. The workflow reads tokens from the DOM, cancels destructive dialogs, and avoids common Telegram Markdown parsing failures.

shopify-theme-builder interviews for brand, markets, languages, template scope, and feature constraints before generating an Online Store 2.0 theme that merchants can control from the theme editor. It uses JSON templates, modular sections, design tokens, and reorderable blocks without hard-coding copy, colors, fonts, or images, and supports bilingual and RTL storefronts. Companion orchestration and UI-UX skills are expected, with optional Shopify CLI or Python validation.

x-shot-skill captures the actual X article card instead of re-rendering a mockup. Playwright handles ordinary pages in an isolated browser, while opencli can temporarily use your logged-in Chrome for gated tweets; both paths produce precise 2× retina PNGs and stitch long cards automatically. It needs Node, Playwright, and Chrome, with Python’s standard library only for the fallback image stitcher.