Shape agent capabilities into your workflow.

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.

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.