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

Greenfish Compose Multiplatform Skill collects practical conventions for Kotlin Multiplatform apps using Compose, Material 3, Koin, and one-way MVI state per screen. It encourages one class per file, named UI tokens instead of magic numbers, no mock data in production, and adaptive navigation that changes with width. The detailed rationale lives in the skill file.

Interview Outline turns a guest’s profile, company, field, public material, and recording schedule into a nine-section interview guide with follow-up questions. It also plans a main video title and short clips built around conflict, quotable lines, and methods. At least one link to the guest’s prior public output is required; engagement data must be supplied separately when unavailable.

Tamara Payments is an offline documentation skill for integrating Tamara checkout, order states, signed webhooks, capture, refunds, and supported commerce plugins across GCC markets. It guides the server-side flow from checkout to approval, authorisation, fulfilment capture, and refunds, while separating API, notification, and public credentials. The bundled mirror is dated and should be checked against the current sandbox and documentation before launch.

Client Sourcing turns leading business signals into qualified consulting outreach. It scores prospects on fit, budget, timing, and edge, then produces a personalized email, chat brief, HTML digest, or Salesforce-ready CSV. The skill requires real support for every claim and keeps a person in the send loop; LinkedIn connection data and derived outputs remain local.

LinkedIn Posting Skill turns LinkedIn publishing into a repeatable routine: choose one audience, earn the stop, earn the read, invite a reply, and stay present on schedule. It covers hooks, post structures, timing for global and Indian audiences, content pillars, a 30-day plan, and metrics. Its guidance cites the project’s listed 2026 sources, while actual reach still depends on the account and audience.

GitHub Boards lets an agent manage a GitHub Projects v2 board by conversation: file issues, inspect human and agent queues, move lanes, route owners, sync TODOs, reconcile drift, and plan undo from snapshots. Every write is staged for explicit approval, and the tool fails closed on missing or ambiguous configuration. It requires authenticated gh, Node 18+, and project permissions.

Animated Presentation Skill uses Remotion and OpenMontage to create narrated explainer videos with native UI recreations, word-level narration sync, subtitles, Portuguese versions, and sound design. It also documents visual QA and FFmpeg gotchas. The environment needs Node, ffmpeg, ImageMagick, sentrysearch, and OpenAI plus AssemblyAI credentials; the license is for internal or educational use.

Recon maps a codebase, hunts for defects and refactoring opportunities with read-only subagents, and sends selected work to implementers in isolated worktrees. Each phase has a human gate; fixes and behavior-preserving optimizations must meet the test baseline and verifier checks before being cherry-picked. Its pentest mode is limited to authorized, non-destructive targets.

Illuminate converts a research corpus, book, codebase, conversation archive, or specification into a single self-contained interactive HTML file. It extracts a structured argument, then presents the governing thought, supporting signals, keyboard navigation, focus mode, and signal view in a Swiss editorial layout that works offline without a server. The process has explicit gates, but the same model can still overrate its own checks.

Kannaka Plugin adds HRM memory metrics, NATS swarm status, session model and cost details, and a pulse-like statusline to Claude Code. Its bundled zero-dependency MCP server exposes recall, remember, dream, and swarm messaging tools, while bounded background snapshots avoid a persistent daemon. The kannaka binary is needed for full HRM and swarm data; without it, the session line still works.

The SUMIT / OfficeGuy skill helps Claude Code integrate Israel’s billing and accounting API in Next.js and TypeScript applications. It covers browser-side payments.js tokenization, server-only secret keys, integer enums, idempotent charges, invoice and receipt documents, recurring billing, CRM data, and webhook verification. References also cover Israeli VAT and allocation numbers. Because the API can evolve, the project recommends checking official documentation and using a dedicated test terminal before live money flows.

Etymolt design-skills packages brand guidance, a design system, and marketing-page composition as three installable agent skills. The brand bundle locks voice, taglines, colors, typography, and logo assets; the design-system bundle supplies Tailwind tokens, CSS variables, and reusable UI primitives; the marketing bundle adds a PublicPage pattern plus canonical SEO and Open Graph metadata. Compatible coding agents can load the conventions automatically after installation.

Claude Photoshop Skill turns plain-language design requests into layered Photoshop PSD files. Claude writes a small ExtendScript, runs it through Photoshop, renders a preview, and can rebuild after changes to text, color, or placement. It supports common social, presentation, web, print, and card formats, but remains an early prototype: a Mac with Adobe Photoshop, Claude Cowork, code execution, and macOS control access is required, while print PDF output is experimental.

exam-prep-guide-builder turns past exam PDFs into figure-rich study guides for quizzes, finals, certifications, and other tests. It clusters recurring topics, ranks their frequency across years, writes step-by-step solutions, and extracts diagrams or tables from typed and scanned pages. Optional lecture slides can be linked to the questions they teach. Answer sources and uncertainty are marked, and a verification script checks figures and dropped questions.

SEO / AEO / GEO Content Review audits articles, guides, comparison pages, and listicles before they are published. It checks important claims against primary sources, maps search intent, examines extractability and citability, and applies SEO, E-E-A-T, helpfulness, originality, and review-content lenses. The output includes a scorecard, fact-check, lens-specific findings, and a prioritized action plan. It is an audit by default and rewrites only when requested.

Crawlora Agent Skills teach coding agents to fetch structured public data through Crawlora’s REST API, returning JSON for search, marketplaces, YouTube, app stores, reviews, finance, maps, and keyword research. The bundle includes standalone skills, endpoint references, and a small curl helper, so no MCP setup is required. Users supply a separate CRAWLORA_API_KEY, and the repository’s role is to package the instructions and request helpers rather than store the data itself.

Content Dashboard archives posts from platforms such as Xiaohongshu, Douyin, WeChat, Taobao, and Xianyu into a local system. A Claude skill extracts titles, copy, screenshots, metrics, tags, comments, and history, storing Markdown for later agent use and a single offline HTML board for human browsing and sharing. The board shows trends and platform or rating breakdowns, applies configurable performance labels, and keeps a separate library for reference posts.

App Store Localization translates iOS App Store metadata and screenshot captions into multiple locales, then writes the standard fastlane directory layout. Gemini handles copy and in-image text, Astro ASO checks localized keywords against storefront data, and Python scripts composite the translated caption band onto the untouched screenshot while linting Apple field limits. Uploading is handed off to the user or fastlane; the skill does not submit an app for review, and RTL or CJK output still needs checking.