Understand a pull request through guided questions before running automated review.
Project overview
Give pr-buddy a pull request number, branch, or URL and it will lead you through five Socratic stations covering the goal, architecture, decisions, risk, and ownership. You answer before the skill reveals its reading, so the review builds on a mental model you can explain. It then hands off to pr-review-toolkit and closes with a three-bullet recap; authenticated gh and the toolkit are required.
General skillTesting and debuggingModel Context Protocol
OpenClaw-Doctor-for-Claude-CoWork
@zurbrick
Diagnose OpenClaw failures through a repeatable operator workflow.
Project overview
The skill guides Claude through a five-step OpenClaw investigation: run the built-in doctor, verify gateway health, inspect logs, examine sessions, and troubleshoot the affected channel. It covers common failures across messaging, cron jobs, sessions, routing, and security. OpenClaw must already be installed, while terminal access is optional for direct command execution.
Develop WooCommerce extensions and checkout flows with Claude Code guidance.
Project overview
Use this skill when extending WooCommerce through Claude Code. It covers custom product types, payment gateways, shipping methods, HPOS, REST API extensions, cart and checkout customization, and Blocks integration, and can activate automatically for relevant WordPress work or be invoked directly.
Create reviewable local HTML mockups from an existing design system.
Project overview
The skill first inspects a project's tokens, fonts, components, styling system, and framework, then builds a standalone HTML mockup using that existing visual vocabulary. You can choose low, medium, or high creative scope and review the result in a browser. It will not change application code until you explicitly approve the mockup, and it supports several common frontend stacks without relying on paid design APIs.
Convert DeepResearch Word exports into clean, Obsidian-compatible Markdown.
Project overview
The skill handles formatting patterns common in ChatGPT DeepResearch DOCX exports, including headings, nested lists, code fences, Mermaid diagrams, tables, Office MathML, and bibliography-backed citation links. It verifies the generated Markdown for broken math, diagram labels, and citation formatting. The converter mainly depends on python-docx and can run in an isolated uv environment.
Create a detailed, sequential walkthrough of a codebase with showboat.
Project overview
Pass a source path to the Claude Code command and the skill uses showboat to produce a linear explanation of the codebase. The resulting walkthrough is intended to guide readers through structure and implementation in a deliberate order. It requires the showboat command to be installed and available on PATH before use.
Manage project TODOs with a compact index and separate context-rich files.
Project overview
This Claude Code skill keeps a small `TODO.md` table for browsing and stores each task's context, guidance, notes, and work history in its own Markdown file. Commands can add, start, update, finish, reopen, or remove tasks without loading the entire backlog. The split layout scales better for long-running projects, at the cost of creating more files in the repository.
Route each new Claude session to the right files, skills, and MCP connectors.
Project overview
Configure a context map for your projects, then let the skill turn each opening request into a setup checklist of files to load, skills to enable, and MCP connectors to enable or disable. When the request is unclear, it asks a small number of focused questions. A mid-session check can remove deadweight or add newly relevant tools as the work changes.
Turn a stock ticker into a sourced five-part equity research report and PDF.
Project overview
Enter a ticker to research the business, catalysts, valuation, peer comparisons, downside risks, technical setup, and overall thesis using current web data. The skill adds sector-specific analysis for biotech, SaaS, and commodities and can export a formatted PDF alongside the chat summary. It states a data-backed view without issuing buy or sell advice, and critical figures should still be independently verified.
Reframe technical resumes and LinkedIn profiles for higher-value roles.
Project overview
Use this Claude Code skill to prune low-value experience and rebuild a scattered technical background into a clearer architecture, governance, or consulting narrative. It can review LinkedIn headlines, About sections, and resumes, then produce English and localized positioning for engineers targeting founders, recruiters, or B2B clients.
Turn a Claude Code session into a structured handoff and progress report.
Project overview
Run the skill at the end of a session to capture completed work, decisions, changed files, build and test status, blockers, and next steps in a dated Markdown document. The result can restart a later Claude session, serve as an end-of-day report, preserve a development log, or let a colleague continue asynchronously without a handoff meeting.
Review code, architecture, and product scope through a simplicity-first senior engineering lens.
Project overview
Use this skill to challenge premature abstractions, unnecessary services, oversized product scopes, and clever code that future maintainers will struggle to understand. It favors readable implementations, prototypes, integration tests, small refactors, and measurement before optimization. The playful grug voice is optional; the underlying review keeps technical rigor and still accepts complexity when the problem genuinely requires it.
Turn a GitHub project into screenshot-ready LinkedIn and Facebook post drafts.
Project overview
Point the skill at a repository and it gathers project details, finds screenshots in common local folders, and writes separate LinkedIn and Facebook posts. It packages the copy, embedded images, platform tips, and visual suggestions in a styled Word document for easy copy-and-paste publishing. The workflow requires Claude Code, an authenticated GitHub CLI, Python 3.11+, and python-docx.
Challenge impulsive decisions with bias checks, base rates, expected value, and a Plan C.
Project overview
Use this Claude Code skill when a life or technical decision is being driven by emotion, anchoring, narrow framing, or a repeated debugging hypothesis. It follows a fixed intervention: name the bias, replace intuition with probabilities or base rates, surface an overlooked option, calculate expected value when useful, and end with one time-bound next action. It stays silent when no intervention is needed.
Prepare X posts and articles with clipboard-ready text and local media.
Project overview
This skill prepares regular X posts and long-form X Articles without automating the final browser submission. It copies polished text or rich article content to the clipboard, downloads remote images, renders Markdown tables as local PNGs, and creates short helper commands that serve cover and body media in order for manual insertion on X.
Review B2B positioning, pricing, and product-led growth through Leah Tharin’s frameworks.
Project overview
Ask Claude to critique a B2B landing page, PLG motion, product-led sales strategy, pricing package, growth team, or ideal customer profile using frameworks drawn from Leah Tharin’s public work. The skill is intentionally direct and opinionated, focusing on what is broken and what to change. It is a fan-made project and is not endorsed by or affiliated with Leah Tharin.
Find recurring Claude Code workflows that are worth automating.
Project overview
Skill Finder reads local Claude Code history, transcripts, skills, settings, and CLAUDE.md files to identify repeated behavior across projects. It produces frequency tables, avoids recommending workflows already automated, and ranks quick wins across persistent instructions, skills, agents, and plugins; the analysis itself is read-only.
Profile a Polymarket wallet’s performance, trading style, and EV signals.
Project overview
Paste a Polymarket profile URL to analyze public trades, current positions, and order books for the wallet’s most active markets. The report covers realized performance, drawdown, market concentration, buy-versus-sell pricing, round-trip results, holding times, and liquidity signals to help separate repeatable behavior from lucky outcomes. Results are anonymized by default, and the tool neither trades nor copies positions.