Shape agent capabilities into your workflow.

Chinese EPUB Typo Fixer handles OCR mistakes in Chinese ebooks made from scanned images. It applies clear visual-character or simplified/traditional corrections by default, lists archaic-usage modernization separately, and outputs a corrected EPUB plus a change report. The scripts only unpack, rewrite, and repack; they avoid network access and skip ambiguous or oversized changes.

Vastu-Jyotish Mentor uses birth and business details to calculate charts, planetary periods, auspicious times, Vastu considerations, and numerology, then returns a short verdict with plain-language reasons or suggested remedies. It uses pyephem and keeps personal data in a local private profile. The project frames this as a traditional cultural lens, not a scientific guarantee or a basis for medical, investment, or marriage decisions.

Humanamente rewrites Spanish AI text by identifying inflated phrasing, negative parallelism, mechanical lists, English punctuation, generic conclusions, and other local writing tells. It preserves meaning while iterating through a six-dimension style check, without regex, scripts, or find-and-replace rules. A simple mode is available, with optional voice profiles for close, corporate, technical, or commercial tones.

Holo-Zlib is a portable Agent Skill for searching and downloading ebooks through the Z-Library eAPI, from Claude Code, Codex, Cursor, Gemini CLI, or a shell. Runtime use needs only Python 3.10+ and the standard library. Credentials and downloads stay outside the skill directory, but users must prepare credentials/zlib.json and can choose an output directory.

TikZ Scientific Figures turns a plain-language description into editable TikZ or PGFPlots source, compiles it into a vector PDF, and returns both files. It covers plots, circuits, biological and physical diagrams, and other technical figures, with optional SVG editing through bundled tools. A LaTeX toolchain such as pdflatex is required, with extra dependencies for previews and SVG export.

Circuit reads Gmail in a read-only flow, keeps threads with genuine two-way replies, filters newsletters and automated senders, and surfaces relationship type, status, deadlines, and action items. The open-source version can use Claude's Gmail connector or a local MCP engine, with no Circuit server handling the mail. Background sync and a web dashboard belong to the hosted tier.

youtube-learn turns a YouTube link into structured notes for lectures, podcasts, interviews, and tutorials. It fetches captions with yt-dlp, falls back to Whisper when needed, reads the full transcript, and writes a TL;DR, key takeaways, topic-by-topic explanation, notable quotes, and audience guidance. Tutorials are organized like reference material, and the result is saved as Markdown.

autoresearch-skill gives Claude a disciplined loop for optimizing a measurable target such as test runtime, bundle size, latency, memory, or training loss. Each experiment is benchmarked, useful changes are committed on one branch, and regressions or failures are reverted while the run history remains available. Session files support resuming later, but the approach is intended for iterative work rather than trivial one-off edits.

ziyu packages crisis-communication playbooks for brands, creators, and small teams using Claude Code. It covers eleven crisis types with severity assessment, information checklists, response strategies, action lists, recovery timelines, and templates for apologies, clarifications, denials, and legal warnings. Separate monitoring guidance supports current-issue scans and scheduled checks that organize signals into a structured public-opinion report.

Local Service Research helps compare nearby providers such as plumbers, salons, vets, or mechanics. It gathers reviews, ratings, review counts, and pricing, creates a research note for each business, and combines them into a shareable Markdown comparison with a clear verdict. An optional self-contained HTML report can be printed to PDF, while missing evidence and red flags are called out instead of filled in.

trade-chokepoint evaluates import and export lanes for supply-chain bottlenecks, landed cost, and trade risk. Its India edition incorporates factors such as CEPA, RoDTEP, and BIS, applies weighted scores and penalties, and produces a one-page PDF verdict. The project presents the result as research support: its weights are not empirically validated, and the output does not replace customs, legal, or tax advice.

journal-this turns a current work session into a dated Markdown journal entry written in the user’s voice. It reads recent entries for continuity and focuses on what changed or moved forward instead of producing a generic recap. Entries can stay in a local folder or be committed and pushed to a GitHub repository, with setup options and pull-rebase handling for concurrent updates.

kens-designer steers Claude toward senior design-engineering practice when building or critiquing interfaces, with React and Tailwind as the default stack. It begins by learning the desired visual direction, then combines implementation with a critique of hierarchy, layout, typography, color, accessibility, and interaction details. The repository also describes an AGENTS.md setup for Codex and distills principles from a broad design reference library.

Consulting Visual helps create strategy-consulting covers, executive infographics, methodology diagrams, flowcharts, and 2×2 analysis pages. It separates the logic of covers from information and analysis layouts, condenses long themes into a title system, and chooses a clear business metaphor such as a path, funnel, flywheel, or matrix. Code-rendered HTML, CSS, and SVG keep the typography sharp across several aspect ratios.

Shinri designs prompts for expressive calligraphy and lettering images with Nano Banana 2, Nano Banana Pro, or ChatGPT Image2. An interactive flow starts from Chinese or Japanese characters, longer text, or a signature, then combines eight style families with five emotional axes covering weight, texture, temperature, spatial fullness, and time. It produces prompts rather than images and is intentionally not aimed at standard decorative lettering.

Musica Pura translates a novel fragment, image, or scene description into structured music directions for SUNO and Lyria 3. Its workflow extracts an emotional curve, separates narrative details into sound attributes, shapes lyrics and language blocks, and adds guidance for selecting among generated takes. The companion Claude Code skill analyzes resulting audio and records observations that can inform later prompt design. It produces prompts, not finished tracks.

harness-check audits multi-agent frameworks assembled from prompts, Markdown, and scripts. It checks four dimensions: system architecture, trigger reliability, execution reliability, and declared-versus-wired behavior, covering 24 failure patterns involving discovery, registries, symlinks, script seams, locks, and state handling. Findings must be verified against real files, then appear in a behavior-focused report with severity, fix risk, and a split between safe fixes and decisions that need the owner’s call.

Argus audits apps, websites, CLIs, APIs, and MCP services by assigning parallel agents to exercise every relevant control and compare before-and-after screenshots. It checks persistence, cross-surface sync, accessibility, performance, privacy, empty states, onboarding, and other lenses, then sends findings through an adversarial verification pass to remove false positives. The package includes customer-audit for reports and overnight for an audit, fix, verify, and commit loop.