Explore skills

Analyze crypto neobank positioning against competitors, find unclaimed territory, and generate a messaging framework. Use when a neobank needs to differentiate or when auditing a prospect's positioning.

A Claude Code-based design skill for hi-fi prototyping and Figma MCP-driven precision design work. It's structured by three essential rules: fact verification, confidentiality before external calls, and a strip-then-scan import gate for AI assets, all integrated into Codex CLI (GPT-5.5 reasoning, gpt-image-2 image generation) and the Figma MCP toolchain.

An IoC-based local scanner and safe-eradication runbook generator for npm/PyPI supply-chain worm campaigns. It detects OS persistence, IDE-hook implants, malicious lockfile versions, and C2/Session-Protocol exfil traces, orchestrating persistence-first eradication.

PowerPoint speaker notes editor for AI agents. Use to modify PPT speaker notes, export them to Markdown, rewrite them in various styles, or unpack/pack PPTX files. Compatible with Claude Code, OpenClaw, and other SKILL.md-supported agents.

Performs customizable N-day (7-365 days) technical analysis for Solana, outputting a regression channel chart, key indicators, and a scenario playbook.

An end-to-end workflow for publishing agent skills to GitHub, ClawdHub, and skills.sh. It handles repository creation, topic tagging, ClawdHub publishing, skills.sh index requests, and installation verification.

Automate GitHub PR review workflows with configurable reviewers. This skill helps manage code reviews at scale, iterate through feedback cycles, address comments, and ensure tests and CI pass until all reviews are resolved, supporting multiple reviewers and a coder role.

Organizes and deduplicates file collections (music, images, documents, video) by scanning directories and ZIP archives, detecting duplicates via MD5, and copying unique files into a clean structure. Use this skill to clean up, sort, or reorganize any file collection, supporting strategies like by artist name.

Translate one or more PDFs into polished Simplified Chinese while preserving layout, headers/footers, original figures, tables, formulas, and visual style. Use when Codex receives PDFs and the user asks for Chinese translation, bilingual technical/proper terms, LaTeX/PDF output, figure/table label translation, or strict page-by-page visual QA with subagents.

Structured code review with a focus on security and quality. This skill systematically reviews code changes, PRs, and diffs, covering logic, error handling, security, performance, and readability, using a checklist approach.

This skill sets up an automated multi-agent research pipeline to discover non-consensus findings across various topic domains like AI hardware, biotech, or geopolitics. It builds a self-running system that re-executes periodically, performing deep sector-by-sector research and cross-sector analysis to identify mispriced findings.

Generates a single-file, deep-dive HTML article in the "principle-deepdive" visual style, featuring a dark/light theme, indigo/amber accents, inline-SVG diagrams, and collapsible cards. It's offline-readable, under 300KB, and ideal for long-form analytical articles that explore topics principle-by-principle.