Loading...
Loading...
Found 1,378 Skills
You MUST use this when an implementation plan or a finished implementation needs an independent review by other agent CLIs - by default the opposite CLI (Codex for work done in Claude Code, Claude Code for work done in Codex), plus any reviewer the user names, Antigravity (Gemini) included - whether the user asks for a cross-review, a cross-cr, or a second opinion from the other agent. Replaces devflow cross-review. Same-host review belongs to cr-request and deciding on findings to cr-received; spec review and per-task review are outside this skill.
Keeps every reply to the user to three lines or fewer, with no preamble, restated question, recap, or closing offer. Use when the user says "be brief", or when about to reply to the user: load it before every reply in every session, including plain questions, recommendations, and comparisons, even when no other skill applies.
FFmpeg CLI reference for video and audio processing, format conversion, filtering, and media automation. Use when converting video formats, resizing or cropping video, trimming by time, replacing or extracting audio, mixing audio tracks, overlaying text or images, burning subtitles, creating GIFs, generating thumbnails, building slideshows, changing playback speed, encoding with H264/H265/VP9, setting CRF/bitrate, using GPU acceleration, creating storyboards, or running ffprobe. Covers filter_complex, stream selectors, -map, -c copy, seeking, scale, pad, crop, concat, drawtext, zoompan, xfade.
Convert Markdown articles into inline-style HTML compatible with WeChat Official Accounts. It uses the kami paper-style theme by default, and supports switching between multiple themes including kami, magazine-ink, magazine-indigo, magazine-forest, magazine-kraft, magazine-dune, elegant, modern, and minimal, as well as parameter configurations such as font, font size, accent color, background color, and output path. It is used for official account typesetting, article HTML generation, and replacing unstable external typesetting services, and is especially suitable for converting articles in this vault into a format that can be copied to the WeChat Official Account editor.
Drafts peer-review rebuttals and author responses in the three real venue formats - (a) strict one-page LaTeX rebuttal PDFs (CVPR-style), (b) OpenReview threaded per-review replies under 10,000-character budgets (NeurIPS/ICML/ICLR), and (c) revise-and-resubmit packages with a change-log response document (CHI, SIGMOD/ICDE revision rounds, journals). Anchors every response to paper sections, tables, figures, and line numbers; enforces character/page budgets and point-by-point coverage with bundled checker scripts; ships a one-page rebuttal LaTeX template. Use when the user says "write my rebuttal", "respond to reviewers", "author response", "reviews came back", "reviewer 2 says", "revise and resubmit", "response letter", "rebuttal deadline", or needs to fit a response into an OpenReview character limit or a one-page PDF. Drafts files on disk only; never posts, uploads, or submits.
Reverse-engineer and rebuild any website — including its WebGL/WebGPU/canvas shader effects — into a clean local codebase. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy a website or landing page, especially designy sites with animated/shader/3D hero backgrounds. This is the top-level coordinator: it does recon, classifies every page surface as DOM vs GPU-rendered, routes plain layout to the dom-clone sub-skill and shader surfaces to the shader-extract sub-skill, scaffolds a build target on demand, composites the two tracks, and runs automated visual QA. It also produces a human-readable TEARDOWN.md (stack, measured design system, every effect with its exact runtime params and how it works) — pass --analyze-only to stop there. Trigger on "clone this site", "rebuild this page", "make a copy of this website", "reverse-engineer this landing page", "clone this but the background is some WebGL thing", any pixel-accurate site reproduction, AND on analysis asks: "how did they build this", "tear down this site", "site teardown", "break down this page", "what stack/animations does this site use", "how does this effect work", "website blueprint", "steal this website's design", "/site-teardown". Provide one or more target URLs.
The Synthesia craft skill — produce avatar video (training, onboarding, explainers, localized series, faceless educational content) with the consent-first architecture and honest fit boundaries. Use when someone wants to make videos with Synthesia/AI avatars, create a personal avatar/digital twin, localize one video into many languages, build training/L&D video at scale, or asks whether an avatar should replace them on camera. Uses the HUMAN framework. Reads the content skill + brand-profile + voice-builder first. The agent scripts and plans (API where connected); the HUMAN approves every video; WoopSocial publishes. Spines: the fit test (avatars win at scale/localization/training, lose to a real face for trust-led content); consent-first likeness; the script is most of avatar quality — lock copy before generating. Never impersonate, fake endorsements, or skip AI-disclosure. Distinct from heygen, talking-head-and-piece-to-camera, ai-video/luma, ai-voiceover, and descript.
Upload large Remotion repository assets to the Cloudflare R2 bucket behind remotion.media and replace local public/ assets with hosted URLs. Use when a file is too large for Git or when a PR should avoid committing media binaries by hosting them on remotion.media.
Scope a feature end to end and write an implementation spec under specs/ from an accepted proposal — current-system mapping, goals/non-goals, a Decision Log for one-way-door choices, a live Open Questions backlog, and a real migration + test plan. Read when asked to write a spec, scope this feature, turn this proposal into a spec, plan the implementation, or break this into tasks. Do NOT fire on frame a proposal or write the PRD (sibling frame-a-proposal — a PRD frames a change before it is accepted; this skill starts once one is), record a decision or write the ADR (record-a-decision), write a postmortem (write-a-postmortem), or review this design (review-a-design) — those are separate skills. Complements the platform open-knowledge skill; does not replace it.
Migrates LLM observability from LangSmith into Arize AX — historical trace import via OTLP (LS outputs→output.value, session/thread→session.id), datasets, and Prompt Hub prompts (latest or versions). Use when migrating from LangSmith to Arize, importing LangSmith runs into AX, or replacing LangSmith with Arize.
Labor-dispute information assistance for workers in mainland China. Use when the user mentions labor arbitration, wage arrears, pay cuts, dismissal or termination, failure to sign a labor contract, related documents, or asks to resume an interrupted case or only read the case file in the current workspace; in such resume-only requests, ArbiBuddy Skill must be the first tool call, without exploring the workspace or reading references first. Supports case fact collection, evidence and claim organization, amount calculations, negotiation and mediation, arbitration preparation, and subsequent procedures, prioritizing national rules while providing enhanced Shanghai-specific guidance. It does not replace the judgment of a lawyer or competent authority and makes no promise of success.
Characters and animation - Humanoid properties/states, spawning (LoadCharacterAsync), health and damage, HumanoidDescription appearance, Animator/AnimationTrack playback, priorities and markers, default animation replacement, Tools, TweenService, IKControl, Character Controller Library (beta). Use when changing movement, abilities, damage, respawn, avatars, animations, tweens, or tools/weapons.