Latest Agent Skills

Formats git commits using Sentry conventions with conventional commit types, issue references, and AI attribution, while enforcing branch safety.

Optimize content for AI search and LLM citations across AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and similar systems. Use when improving AI visibility, answer engine optimization, or citation readiness.

Provides guidance and patterns for using a vector-powered CLI for semantic file search with Claude/Codex skills.

Guides users through learning a new skill or concept within a dedicated teaching workspace, using structured lessons, reference materials, and learning records.

Provides guidance for performing symbolic algebra, calculus, linear algebra, equation solving, physics calculations, and code generation using the SymPy Python library.

Launches an RSVP speed reader to display text one word at a time with Spritz-style highlighting.

Connect to the MAXIA AI-to-AI marketplace on Solana to discover, buy, and sell AI services, earn USDC, and access crypto intelligence, DeFi yields, and token risk analysis.

Adaptive tutoring that diagnoses the learner's level, sets a small objective, teaches with examples, and gives practice with feedback.

Logs daily development progress per project, fuses entries into a global diary, and syncs to Notion and Obsidian.

Reference for building real-time voice and multimodal AI applications with Daily and Pipecat, covering pipeline architecture, AI service integrations, transports, and client SDKs.

Provides C programming guidance for systems programming, covering memory management, pointer arithmetic, POSIX compliance, and debugging with valgrind and gdb.

Audits hidden assumptions in decisions by classifying them into four types, ranking by fragility and impact, and rebuilding conclusions from verified premises. Auto-detects Chinese or English.

Build content-focused websites with Astro, leveraging zero-JavaScript-by-default islands architecture, multi-framework components, and Markdown/MDX support.

Orchestrates AI/ML workflows for building LLM applications, RAG systems, AI agents, and ML pipelines, covering design, integration, observability, and security.

Converts human-written CLAUDE.md files into a structured-label format that improves AI instruction compliance while reducing token usage.

Manages persistent terminal sessions, windows, and panes with tmux, including scripting multi-pane layouts and automating commands from shell scripts.

Keeps AI coding agents tightly scoped by enforcing minimal changes, simplest solutions, and asking before expanding scope or adding dependencies.

Builds web APIs and full-stack apps with Hono, covering routing, middleware, validation, RPC clients, and deployment across edge runtimes.

Design, simulate, and run quantum circuits on simulators and quantum hardware using Google's Cirq framework.

Fetches any X/Twitter post as structured JSON via the ADHX API, including full article content, author info, and engagement metrics, without scraping or a browser.

Guides test-first development with vertical slices, one test at a time, and refactoring after green.

Runs a broad SEO audit across technical SEO, on-page SEO, schema, sitemaps, content quality, AI search readiness, and GEO, orchestrating specialized sub-skills and subagents.

Grounds legal drafting in verified government references across 29+ jurisdictions, providing templates and scaffolding for business formation, employment, and contracts.

Runs a structured 6-phase security audit covering attack-surface mapping, STRIDE/PASTA threat modeling, technical checklists, red/blue team exercises, and a final verdict, plus incident-response and monitoring playbooks.

Query, filter, transform, and aggregate JSON data using jq, with practical patterns for shell pipelines and CLI integration.

规划、撰写、重构、润色、压缩、扩写、收口和审校中文医学文本，并为持续项目建立写作主控索引、内容型总纲、全文一致性账本、章节任务书、证据账本、决策记录和最终交付物清单。支持 Grant（医学基金标书、项目申请、研究目标、任务分解、技术路线、进度与甘特图、项目管理、风险分析、创新性、预期效益、研究基础和可行性论证）与 Journal（毕业论文、期刊论文、综述、病例报告、指南解读和学术报告），自动识别或联合调用全文建构、局部构篇、语言精修、结构审计、语言审计及项目收口。

Enforces complexity analysis, correct data structure selection, vectorization, and algorithm implementation discipline at principal-engineer level.

Enforces system design, project structure, dependency management, error handling, testing, and documentation standards at principal-engineer level.

Enforces a principal-engineer self-review checklist on every code block before output, covering correctness, performance, security, naming, and testability.

Enforces production-grade REST API design, distributed systems patterns, database design, and event-driven architecture at a principal-engineer level.

Enforces principal-engineer-level Python code quality: formatting, type safety, idiomatic patterns, class and function design, and anti-pattern prevention.

Enforces ML infrastructure, experiment tracking, reproducibility, model packaging, CI/CD, monitoring, and infrastructure-as-code standards at principal-engineer level.

Enforces rigorous ML modeling, feature engineering, training, and evaluation standards at principal-engineer level.

Creates a self-contained interactive HTML explanation of code changes, including background, intuition, code walkthrough, and quiz sections, with diagrams and responsive styling.

Analyzes competitive landscapes using Porter's 5 Forces, positioning matrices, and battlecard generation to secure market position.

Build 3-scenario financial models (Base/Bull/Bear) for startups with templates by business model, unit economics, cohort analysis, and runway calculations.

Manages git worktrees and submodules in monorepos, handling branch synchronization, commits, pushes, pulls, and branch switching across multiple repositories.

Explains term sheet key terms, SAFE/convertible note structures, cap table dilution calculations, and negotiation red flags for startup fundraising.

Provides domain knowledge of Korean government and private funding program announcement systems, evaluation criteria, and key program characteristics, including TIPS, Early-Stage Startup Package, Startup Growth Technology Development, and AI Voucher.

Guides founders through the fundraising lifecycle from pre-seed to Series B, covering stage benchmarks, an 8-week execution timeline, and preparation checklists for pitch decks, financial models, and data rooms.

Provides startup metrics frameworks and stage-specific benchmarks for SaaS, Marketplace, Consumer, and B2B models, including investor-ready dashboard generation.

Generates on-brand interfaces and assets for Sprintable, from throwaway HTML prototypes to production code, using the included design tokens, fonts, and UI kit components.

Analyzes a plan file and converts it into an interactive HTML explainer with brief and full modes, featuring dedicated diagrams and source links.

Generates interactive HTML explainers for code diffs, branches, and PRs from a single Markdown document, using a renderer to produce styled output with diagrams and quizzes.

Guides SaaS pricing strategy: selecting models, value metrics, packaging tiers, and applying psychology tactics to optimize revenue.

Researches VC funds and partners, providing thesis matching, portfolio analysis, and approach strategy for outreach.

Guides B2B sales teams through MEDDPICC qualification, a five-stage sales process, core metrics, and team design to build a repeatable sales engine.

Generates investor outreach emails and monthly updates with templates for warm intros, cold outreach, follow-ups, and a Day 5/10/21 cadence.

Calculates TAM, SAM, and SOM using three methodologies (top-down, bottom-up, value theory) and cross-validates results for investor-ready market analysis.

Guides go-to-market strategy with five motions, content pyramid, PESO channels, and 90-day execution plans.

Guides writing Korean government funding program business plans (사업계획서) from an evaluator's perspective, covering structure, scoring emphasis, and writing principles.

Discovers VC, accelerator, angel, and CVC investors via web search, evaluates thesis fit across four dimensions, and maps approach pathways for outreach.

Guides creating a Sequoia-style 12-slide pitch deck with slide-by-slide instructions, storytelling principles, and 30 anticipated VC questions with answer strategies.

Generates a DESIGN.md file conforming to the Stitch (Google Labs) design.md alpha spec, auto-discovering design tokens and components, then emitting YAML frontmatter and eight standard markdown sections.

Structures company knowledge bases for business plan automation, defining a 7-category schema, completeness scoring, and storage layouts for Notion or local Markdown.

Guides creation of HWP/HWPX documents and Korean government business plan formatting, including fonts, margins, and conversion workflows.

Diagnose bugs, failing tests, or unexpected behavior by reproducing, isolating, hypothesizing with evidence, and confirming fixes before making changes.

Switches Claude Code into a teaching-first mode for unfamiliar technologies, explaining concepts and commands step by step without writing code until approved.

Drafts a GitHub issue with YAML frontmatter and checkboxes, writing it to a local file for review.

Orchestrates a multi-agent build session, acting as manager to cut goals into units, spawn implementer and tester subagents, and run test-and-review loops with anti-thrash guardrails.