Shape agent capabilities into your workflow.

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.

grayscale converts one image, many images, a directory, a ZIP archive, or any mix of them through a Claude skill or a plain Python command. It adds a -Grayscale suffix, preserves alpha channels for PNG, WebP, GIF, and TIFF, and keeps folder structure when rebuilding an archive while removing macOS junk and non-image files. Pillow is the only library dependency, with options for recursive folders and a custom output directory.

Web Experience Auditor splits a website or web-app audit across specialized subagents for scope, browser capture, layout, UX, KPIs, structured data, research, and synthesis. Its knowledge gate checks installed versions before making version-specific recommendations and can fall back to static fetching when browser capture is unavailable. Full runs need a Claude Agent SDK environment and optional browser tooling.

Forced-Holding Screen uses de-identified tickers and descriptions to map where index funds may force exposure to a stock, classify the risk, and show category-level alternatives that keep similar market exposure. It checks current IPO status and fund holdings at run time, so the result can change. The project is informational, not investment, tax, or legal advice, and should be checked against primary sources.

Gov Writing Skill turns notes or rough drafts into formal Chinese government and Party documents, including reports, summaries, speeches, implementation plans, minutes, letters, and Party-building material. It can switch between strategic provincial language and more operational county or district wording, while applying structured political framing and parallel prose. It is a drafting and editing aid, not a source of official facts.

ADHD Filter restructures notes, documents, or pasted conversations for easier scanning while preserving every fact, equation, definition, link, and nuance. It can add a bottom-line summary, callouts, chunking, a table of contents, and answerable reflection prompts, then checks element counts before writing. Files marked in frontmatter are skipped on later runs unless forced.

P2H2P converts an old deck, rough idea, whiteboard photo, or screenshot into editable HTML and PPTX. It orchestrates template selection, parallel HTML building, visual checks, conversion, and final QA, pausing at outline, template, and HTML-preview checkpoints. It is an orchestration layer rather than a standalone renderer and needs the companion HTML-template and PPTX skills plus their runtime tools.

Shizheng aggregates CCTV’s Xinwen Lianbo and domestic-news sources into a daily current-affairs brief. It supports date and source selection, full or brief output, local deduplication, configurable limits, and Markdown archiving without sending the full text through the model. It needs Node.js 18+ but no API key; source availability, freshness, and the rights to republish content remain outside the skill’s control.

PITH compresses long natural-language handoffs between agents with local word-information scoring, while quarantining code, JSON, URLs, and paths. A negation check protects polarity, and a bounded sentence-length gate can reduce the pruning ratio and retry. Payloads below 10,000 characters pass through unchanged; the skill, MCP server, and Python CLI work offline without external APIs.

BA Project Factory gives business analysts 24 connected prompts spanning initiation, discovery, planning, delivery, testing, and release. Each prompt generates an artifact, asks for user approval before storing it, and flags related documents that may need updates. Outputs include Confluence-ready Markdown, Jira-ready stories, Figma-ready wireframe specifications, and meeting or requirements registers, even when source material is incomplete.