All Skills

Elite code review expert specializing in modern AI-powered code review. Use when reviewing pull requests or establishing code review standards.

Analyze SaaS and usage-based metrics for diligence: NDR/NRR, gross margin, CAC payback, sales efficiency, cohorts, and unit economics by segment. Use when diligencing B2B SaaS or infra companies.

Search the web (especially GitHub)** for **recent issues** and **security vulnerabilities/advisories** relevant to the given mcp server and its dependencies and produce a **high-signal health + security assessment** with concrete remediation steps

Cross-post blog content to social platforms. Claude handles audit, user selection, and generates rewrites for short-form platforms. Invoke from ANY repo — crier works globally via site_root config.

Manage Google Tasks from the command line - view, create, update, delete tasks and task lists. Use when the user asks to interact with Google Tasks, manage to-do items, create task lists, mark tasks complete, or check their Google Tasks.

Scan Terraform, Kubernetes, CloudFormation, ARM templates, and Dockerfiles for security misconfigurations using 790 Terrascan-derived policies with NIST 800-53 control mappings. Use when users need to review IaC for security issues, audit cloud configurations, check compliance posture, harden infrastructure code, or identify misconfigurations across AWS, Azure, GCP, and Kubernetes before deployment.

Documents development work into changelog-style markdown files organized by date. Analyzes recent changes and creates structured work logs. Use when logging completed work or creating development history.

Based on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.

Reference adapter for Codex multi-agent review. Read by any orchestrating skill via the Read tool. MCP server path (preferred) with auto-setup option, CLI path as fallback, interactive pre-flight advisory when not configured, correct flags embedded. Usable by deep-council, deep-review, deep-audit, or any future skill that needs Codex-based review.

Reference adapter for Claude (Anthropic) dispatch. Read by any orchestrating skill via the Read tool. Defines how to invoke Claude sub-agents or the Anthropic API, with availability checks. Usable by any AI orchestrator — Claude Code, OpenCode, Codex, Gemini, or custom agents.

This skill should be used when the user asks to \"craft Amazon listing\", \"write book blurb\", \"KDP blurb\", \"book description\", \"Amazon keywords\", \"book categories\", \"KDP listing\", \"improve my blurb\", \"help with book marketing metadata\", or mentions creating or refining the marketing copy for a book on Amazon KDP. It generates blurb, keywords, categories, and author bio — the four artifacts that determine discoverability and conversion on Amazon.

Plan, design, and implement A/B tests and experiments with proper sample sizing, statistical significance, and hypothesis frameworks

--- name: abandoned-cart-sms description: "Don't just say 'You forgot this.' This agent scrapes your product page to find the specific key benefit (e.g., 'Full Grain Leather') and uses it to write a persuasive, 3-part SMS recovery sequence automatically." version: 1.0.0 category: Sales Ops --- # T

This skill should be used when the user asks to \"KDP audit\", \"check manuscript formatting\", \"is my book ready for KDP\", \"Amazon publishing requirements\", \"Kindle formatting check\", \"manuscript readiness\", \"book formatting audit\", \"prepare for Amazon KDP\", or mentions KDP/Amazon publishing compliance. It audits a book manuscript against Amazon KDP (Kindle Direct Publishing) requirements for both eBook and paperback formats, handling technical books (LaTeX, math-heavy) and fiction/general nonfiction.

Apply VueUse composables where appropriate to build concise, maintainable Vue.js / Nuxt features.

Multi-model review council. Dispatches review tasks to all available bridge adapters (Claude, Gemini, Codex, OpenCode), each of which runs internal sub-agents. Synthesizes findings across model families using debate-protocol. Usable standalone or as a second-pass from deep-verify. Orchestrator-agnostic — can be invoked by Claude Code, OpenCode, or Codex CLI.

File-based planning with interactive gates and native task tracking. Use when starting complex multi-step tasks, projects with unclear requirements, tasks with multiple valid approaches, or research projects. Supports task-based (single plan file) and spec-driven (multi-file specs with manifest) modes. Phase/Sprint/Spec hierarchy with dependency DAG. Plans are categorized (feat/fix/refactor/review/test/polish/general) and stored in docs/plans/{category}/{name}/. Triggers on: 'plan this', 'let me think through this', 'break this down', 'create a plan', 'spec this out', 'what should the approach be'.

Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file

Generic multi-domain research framework with domain-aware scheduling. Model-agnostic and domain-agnostic - perform comprehensive research on any topic.

SEO and AEO (Answer Engine Optimization) best practices including EEAT principles, structured data, and technical SEO. Use when implementing metadata, sitemaps, structured data, or optimizing content for search engines and AI assistants.

Use when you want GitHub Copilot to review a PR and automatically address its feedback within the current agent session. For any reviewer (human or bot), use pr-review-loop; for a fresh-context-per-comment approach, use ralph-wiggum-loop.

Generate professional git commit messages following cbea.ms guidelines. Outputs plain copy-pasteable commit message text by default.

This skill should be used when the user asks to \"publish on KDP\", \"publish my book\", \"Amazon book publishing\", \"Kindle Direct Publishing\", \"self-publish\", \"publish on Amazon\", \"KDP workflow\", \"submit to Amazon KDP\", \"publish to Kindle\", or mentions Amazon/KDP book publishing. It guides the complete workflow for publishing a book through Amazon KDP, handling both technical books and fiction/nonfiction.

Use when implementing any feature or bugfix, before writing implementation code