Shape agent capabilities into your workflow.

Presentation Report Preflight turns a topic, source document, old presentation, or data set into a structured strategy brief before slide production begins. The brief defines the audience, objective, narrative framework, timing, conclusion-led title chain, slide-level content specifications, evidence status, speaker notes, and Q&A risks. It does not draw the presentation; it produces a machine-checkable handoff contract for a downstream slide-generation skill.

Paste a rough email, Teams message, or Slack draft and receive a clear version written in natural Australian workplace English. The skill pauses when ambiguity could change a deadline, commitment, ownership, blame, or technical conclusion, then highlights anything worth checking before sending. It can save channel-specific files, show a line-by-line diff, and explain the most useful language changes for professionals who use English as a second language.

kamar-taj bundles three Claude Code skills. wong reads the day’s sessions and produces a study guide, Slack standup, and explanations of unfamiliar Git commands. dormammu repeatedly attacks a solution with edge cases until it sees the check pass. agamotto brings in a separate AI critic to challenge a plan. wong uses Python; its optional PDF and Drive workflow also needs Node, Chrome, and rclone.

UX Principles Skill turns ideas from seven established design books into practical rules and review heuristics for Claude. During interface work, it emphasizes user goals, mental models, system feedback, error recovery, visual hierarchy, typography, usability, and accessibility rather than relying on taste alone. Heavier reference files are loaded only when relevant, making the skill useful for both UI implementation and structured design critique.

Prediction Markets Skill provides read-only access to public Kalshi and Polymarket data for Claude Code, Codex, and Cursor. Agents can locate markets, inspect order books and price history, estimate implied probability, and match equivalent markets across venues. It uses only the Python standard library and deliberately excludes trading, wallet access, and API keys.

Persian Skill handles English–Persian translation as well as Persian text mechanics. It aims for idiomatic, register-matched wording and a deterministic linter that fixes letters, ZWNJ spacing, Persian digits, punctuation, and right-to-left layout while protecting code, URLs, and version numbers. You can also run the cleanup without translating an existing Persian document.

Oh My Petcare lets cat and dog owners record symptoms, routines, vaccines, medication schedules, expenses, and other observations in plain language, then turns those local Markdown records into reminders, sitter handovers, or concise vet-visit summaries. Exports can be tailored for clinical or personal use and offered in multiple languages. It does not diagnose or prescribe; red-flag cases are directed to a clinic rather than labeled with a condition.

Codesplain maintains a readable CODESPLAIN.md alongside a project for people who direct AI rather than write or inspect every line of code. It explains what each area does, why it exists, and which consequential decisions shaped it, updating as the project changes. The file gives you a practical reference when an agent claims to have fixed something, added a dependency, or changed storage.

Give the skill one focused concept—such as an agent, RAG, or chain-of-thought—and it produces a self-contained HTML lesson with sourced definitions, plain-language explanation, a continuing product example, practice questions, and an interactive demo. It is designed mainly for AI product-manager training and technical education, using a fixed four-step creation process so separate lessons keep a consistent structure.

Claude Forge turns a mostly unconfigured Claude Code installation into a coordinated development environment for planning, TDD, review, verification, security checks, documentation, and team orchestration. It bundles specialized agents, slash commands, reusable skills, rules, and event hooks so the workflows connect instead of behaving like separate plugins. On macOS and Linux the installer uses symlinks for instant Git-based updates; Windows users rerun the installer after pulling changes.

CLAII is a command-line-first coding agent built around a tool loop restricted to a configured working directory. It can inspect and change files, run Python, and keep calling tools until a task finishes. Local knowledge-base references and optional lightweight memory make it a compact core for studying or extending agent behavior.

Obsidian Project Documentation Manager captures project progress and decisions while you work with Claude Code, then updates a structured vault using customizable templates. It infers the project from the working directory, organizes related projects and technologies, and can optionally commit or push vault changes to GitHub for backup.

Repo Business Context creates a structured /context knowledge base of small Markdown files covering brand, business, and product facts. It can onboard through a short question flow, extract context from the codebase, or grow gradually, then route each task to only the most relevant files. This helps agents retain audience, pricing, voice, and scope boundaries as the product evolves, with context changes announced when they are made.

Ralph Workflow orchestrates coding agents through planning, implementation, verification, and fixes, returning tested work for human review. It is intended for developers and small teams whose tasks are too large to supervise step by step but too risky to hand off blindly. The local Python tool supports several agents, including Claude Code, Codex, OpenCode, and Cursor, and expects clear specifications and repository guardrails.

OpenCode Intern Skill lets Claude Code hand focused work such as refactoring or test writing to an OpenCode agent through the Agent Communication Protocol. Both tools can share project instructions and skills from the same workspace, while the intern is configured to follow the requested scope and report blockers instead of making broad decisions. Claude Code, OpenCode, and Python 3.8 or later must be installed.

Harvey Specter Legal AI Skills provides separate UAE and US variants for preliminary research on company formation, healthcare licensing, employment, contracts, and selected intellectual property questions. The materials are designed to return jurisdiction-specific information with citations, examples, and risk considerations. They explicitly provide legal information only, not legal advice, and users should verify current law and consult a licensed attorney before acting.

DDD Skill guides an AI agent through strategic and tactical Domain-Driven Design. It helps identify subdomains, establish a ubiquitous language, split bounded contexts, and design entities, value objects, aggregates, domain services, and events. It also covers architectural patterns such as hexagonal architecture, CQRS, event sourcing, and Saga for complex systems and microservice boundary decisions.

This repository documents how Claude Code features work and packages the reverse-engineering process as a reusable skill. It extracts the embedded cli.js from the installed Bun binary, reformats the minified source, locates features through surviving string literals, annotates relevant code, and produces evidence-backed reports on commands, skills, agents, caching, and remote control; the workflow requires a local Claude Code installation and substantial source processing.