explain

42

Use whenever the user asks to explain, walk through, or help them understand anything (code, a flow, a bug, a concept, an architecture, a model output). Picks the clearest output format and writes in simplified technical English.

ponytail-audit

158292

Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split. Ranked, each finding explained in plain English. One-shot report, changes nothing. Use for "audit this codebase", "review the whole repo", "find bloat", "what can I delete", /ponytail-audit.

create-second-brain-prd

796

Generate a personalized Second Brain PRD from a completed requirements template. Use when the user has filled out my-second-brain-requirements.md and wants to generate their build plan. Triggers on "create my second brain PRD", "generate my PRD", "build my second brain plan", "/create-second-brain-prd", or after completing the requirements template.

faceless-explainer

59407

Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a website (/product-launch-video — promo or tour). Unclear → /hyperframes.

seo-agentic

18358

Audit and fix agent readiness: the Lighthouse Agentic Browsing fraction, accessibility tree for agents, robots.txt and Content-Signal for AI agents, WAF treatment of agent traffic, llms.txt, Markdown delivery, ai-catalog.json, /.well-known discovery files, and WebMCP tools. Exclude AI citability and brand signals (seo-geo) and commerce protocol depth (seo-ecommerce).

optimise-github-actions

23

Optimise GitHub Actions for cost and speed. Reads the billed minutes and wall-clock time of every workflow and job from the GitHub API, finds the waste, and changes the workflows without dropping the checks that matter. Typical waste is main re-running suites the pull request already passed, path filters that match every PR, small matrix jobs, missing caches, draft pushes, Docker builds, Windows and macOS multipliers, hung jobs and bots. Use this whenever the user says CI is slow or expensive, is over their Actions quota or paying overage, wants to "reduce GitHub Actions minutes", "speed up CI" or "make CI cheaper", asks "why is our CI so expensive", or wants a CI audit. Use it even if they only point at one slow job or one workflow file.

open-code-review

42248

Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply fixes when requested. With appropriate review rules, can detect various types of issues including bugs, security vulnerabilities, performance problems, and code quality concerns.

test-audit

391540

Invoke whenever writing, changing, reviewing, or sweeping tests. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they demand.

jev

95

Write and improve programs that call Jev, TypeSafe's System One model. Use when designing TypeSafe questions (Choice, Score, Noul), structuring state, composing answers in code, setting confidence thresholds, or diagnosing a Jev question that answers wrong or with low confidence.

typesafe-ai

226

Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.

brand-architect

Build a deeply reasoned, evidence-aware BRAND.md that acts as the canonical operational model of any brand. Use this when a brand needs to be understood, reconstructed, documented, governed, reproduced, critiqued, or extended. The skill converts source material and observed brand behavior into a usable brand intelligence system rather than a conventional brand-book summary.

motion-design

1684

Applies motion design principles to create emotionally-driven, technically sound animations and transitions. Provides timing, easing, choreography, and Disney animation principles adapted for UI. Use when creating animations, transitions, micro-interactions, loading states, page transitions, scroll-triggered effects, or any motion work. Works with CSS, Framer Motion, GSAP, Lottie, Spring, or any animation system.

home-assistant

2

Operate a configured Home Assistant instance over SSH. Use for Home Assistant YAML/configuration, automations, scenes, entity registry entries, recorder state, and Supervisor/API operations.

eli5

1118

Explain any topic, code, concept, or error tailored to a specific audience's level of understanding. Use this skill whenever the user says 'explain like I am', 'ELI5', 'explain this to my', 'break this down for', 'dumb it down', 'simplify this for', or asks you to explain something to a specific person or audience type (e.g., 'explain this to a manager', 'how would I explain this to my mom', 'make this understandable for a 5th grader'). Also trigger when the user mentions wanting to understand something at a particular level, or asks for an explanation targeting a non-technical audience. Even partial matches like 'explain to my wife' or 'tell my boss' should trigger this skill.

backlog

Catch me up on this repo or project: where work left off, what is in flight, open issues and PRs, worktrees, leftover branches, collision with other agents. GitHub Issues backlog: capture, triage, research, refine, implement, qa, initialize `.backlog/`, promote memory into AGENTS.md. Use when the user says catch me up; or asks you to be the manager, product manager, or orchestrator for the backlog cycle (you only allocate: start the next role when a spawn harness is available, otherwise ask the human; never do the phase in this chat, never nest a subagent as the worker); or what to do next on an issue. Read references only for the current action.

dispatch-codex

24

Dispatch one or more tasks to codex agents in herdr workspaces — the orchestrator designs each lane's plan and acceptance criteria, codex pursues them in goal mode — supervise them to completion, then push each lane and open its pull request. Use when the user asks to dispatch/fan out/派发 tasks to codex agents or herdr lanes, to run several codex tasks in parallel worktrees, or to resume supervision of an existing dispatch-codex run (`--resume`).

ce-dogfood

25053

Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression tests and commits, judges experience against product personas, and writes a durable dogfood report. Manual invocation only.

md2wechat

3672

Convert Markdown to WeChat Official Account HTML. Use this whenever the user wants WeChat article formatting, article preview, WeChat draft upload, image generation for articles, cover or infographic generation, image-post creation, writer-style drafting, title suggestions, AI trace removal, or current discovery of supported providers, themes, prompts, and layout modules. Also use for unpublished Zhihu, CSDN, Toutiao, or Tencent Cloud Developer Community drafts through a browser. Use for product introductions, encyclopedia articles or entry drafts, and writing tailored to platforms or search targets.

shell-aliases-social

19

Regenerate a shareable shell-aliases JSON from the user's shell config — curated, universally-useful aliases and functions with usage frequency from shell history. Use when the user wants to refresh, update, regenerate, share, or export their shell aliases, asks for the shell aliases social media JSON or aliases JSON, or wants a shareable list of their zsh aliases and functions.

tiktok-shadowban-check

113

Tell whether TikTok accounts are shadowbanned / throttled, how likely, why, and what to do. Trigger whenever the user gives a list of TikTok handles plus an Apify key (or asks "am I shadowbanned", "why did my reach drop", "why 200 views", "what works on @handle", or is about to abandon/recreate an account). Returns a shadowban probability per account, the distribution-round histogram behind it, the spam/automation signals found, what works vs what flops, and a fix list.