Find the open-source solution that fits.

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.

xml-mapper transforms CSV, spreadsheets, JSON, database rows, API payloads, or free-form text into XML that conforms to a target DTD. Its standard-library validator reports each error with a location and explanation. When element-versus-attribute choices, content ordering, enumerated values, or required fields are ambiguous, the skill asks targeted questions instead of silently guessing. No third-party XML package is required.

humanizer-ru is a Claude Code skill for short Russian posts, ads, newsletters, and announcements. It targets 21 patterns across bureaucratic phrasing, passive constructions, stock transitions, inflated claims, repetitive lists, hedging, and chatbot-like endings, then rewrites the affected passages. It supports full or focused editing and is intended for texts up to about 500 words; longer business or academic work belongs in the companion tools.

humanizer-ru-pro edits long Russian articles, business documents, and expert content through 52 pattern checks and four passes. It examines language habits, reader experience, paragraph-level information rhythm, and structural openings, then can calibrate the rewrite to two or three samples of the author’s voice. Full editing, audit-only, and single-category modes are available, with separate guidance for short posts and academic work.

ru-academic-editor revises Russian theses, dissertations, articles, and coursework by strengthening argumentation, authorial stance, paragraph logic, terminology, and academic register. It makes targeted edits while preserving citations and strong passages. It does not invent sources or data, write the paper from scratch, or guarantee a result in any plagiarism detector.

Weekly 1:1 Structure helps managers prepare agendas from current topics and open items, remove pure status updates, and brief each subject before the meeting. Afterward it turns notes or transcripts into a log with action items and slipping work. A simple per-person context file carries open issues between weeks, while the method leaves room to loosen structure when that fits better.

Tony Skill packages a thinking-bridge method for teaching Chinese, an augmentation-focused AI methodology, and cross-temporal mental models into reusable Agent Skill material. It supports language teaching, system design, writing, and decisions through references, heuristics, and voice rules. Its present-day fact policy calls for checking current claims separately, and the framework openly notes that it lacks built-in stopping criteria.

Floor Plan Vectorizer detects walls and enclosed rooms in a raster architectural plan, then creates an interactive SVG with clickable room paths, stable IDs, and optional area labels. A known dimension or pixel scale enables square-meter or square-foot schedules; without a scale, rooms remain clickable but areas are omitted. Runtime needs numpy and opencv-python.

Study Abroad Planner asks for age, language scores, education, budget, destination, and constraints, then produces a school shortlist, EOI or visa pathway, cost and cash-flow view, risk register, and near-term actions. Australia has the deepest coverage; the UK, New Zealand, and Canada are shorter references. It does not file applications or guarantee admission or visas, and it is not a substitute for a licensed migration adviser.

PII Scrub scans a target directory before a push, share, chat, or public release, using generic patterns plus user-defined patterns for personal schools, phones, or emails. It groups matches by severity and reports file, line, and context without rewriting or sending anything. Results are not logged, and the user decides what to remove or whitelist.