Writing AI Skills

Per-clip quality reviewer + render retry state machine. After each rendered shot, score it on 6 axes via `bl omni` (qwen3.5-omni-plus), then decide ACCEPT / REJECT-and-rewrite / REJECT-and-escalate.…

Runs a pre-submission review of a technical paper across five dimensions: macro logic, writing details, English grammar, LaTeX formatting, and figure quality. Uses a reviewer-style severity taxonomy…

When the user wants to conduct, analyze, or synthesize customer research. Use when the user mentions "customer research," "ICP research," "talk to customers," "analyze transcripts," "customer…

Write in the concise, inverted, aphorism-driven voice of Yoda. Use when the user wants wisdom framed sparely, a mentoring tone, short punchy sentences, or playful subject-object-verb inversion instead…

Use this skill for "review this paper", "review this manuscript", "peer review", "review my paper", "critique this manuscript", "review this submission", "give me feedback on my paper", "check my…

Recover deleted, edited or historical web content using the Wayback Machine and its CDX API, archive.today, Common Crawl and Memento/Timetravel. Use when a page is deleted, changed or 404s, checking…

Plan how to test the assumptions behind a product idea before building — decompose the idea into its load-bearing beliefs, prioritize the riskiest, phrase them as falsifiable hypotheses, and pick the…

Use when layout rhythm, density, or gaps feel arbitrary or inconsistent, or when one product needs different reading pressures without splitting into unrelated spacing systems.

Design and build cinematic, award-level web pages.

Authors and updates customization overrides for installed BMad skills. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', or 'customize a workflow'

Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.

Compose, revise, or audit research proposals, opening reports, and research plans from supporting evidence. Use for 研究计划、开题报告、科研项目申请书. Invoked as researchwrite for compatibility; use nature-writing…

This skill should be used when the user asks to "translate", "翻译", "精翻", "translate article", "translate to Chinese", "translate to English", "改成中文", "改成英文", "convert to Chinese", "localize", "本地化",…

Rewrite, check, or draft prose so it carries no AI writing tells, reads plainly on the first read, and keeps every source fact. Use when asked to make writing plainer or free of those tells, to check…

GitHub quota/cache hygiene: Gitcrawl archives, Octopool-backed gh, freshness, limits.

Authoritative agent-runtime contract for working inside an OpenKnowledge project — a markdown-CRDT knowledge base exposed over MCP. Use whenever reading, listing, searching, editing, or linting any…

When the user wants to analyze competitors' App Store strategy, find keyword gaps, or understand competitive positioning. Also use when the user mentions "competitor analysis", "competitive research",…

Guidelines for writing and reviewing Dust product UI copy — buttons, errors, empty states, onboarding, tooltips, modals, form labels, notifications, settings, and any text a user reads inside the…

Screenplay format, page craft, the writing process and adaptation (剧本格式/写作流程/改编) — merged from Wendy Henson (spec format rules), Richard Walter (page craft, revision), Neill Hicks (selling vs shooting…

Run read-only SQL against BigQuery public datasets with local result capture, cost safeguards, and reproducibility outputs.

Writing and maintaining the Sidecar Docusaurus documentation site, including page structure, doc authoring, blog posts, styling, images, and deployment workflow. Use when writing documentation,…

Explain a technical spec or proposed change in plain language: what problem it solves, how the solution works, and every schema change.

Create and update Codex custom agents using standalone custom-agent TOML files.

This skill should be used when the user asks to "유튜브 정리", "영상 요약", "transcript 번역", "YouTube digest", "영상 퀴즈", or provides a YouTube URL for analysis. Extracts transcript, generates…

Reads a user's Link financial data — transactions, balances, and wallet sources — so agents can answer questions about spending and available source capabilities. Use when the user says "check my…

Use when changing a dbt model in a way that could break its consumers — renaming, removing, or retyping a column, or changing a model that downstream models, exposures, dashboards, or BI tools depend…

Line-by-line copy editing and improvement for marketing content. Polish existing copy for clarity, conciseness, impact, and conversion. Trigger phrases: "edit my copy", "improve this copy", "polish…

Create or update AgenticX skills from a live conversation workflow. Use when the user asks to save, persist, or encapsulate a multi-step procedure as a local skill, when tool calls were repeated too…

小说封面生成。根据书名、作者名自动分析题材风格，调用 GPT-Image-2 直接生成含标题和署名的专业级网文封面。 触发方式：/story-cover、/封面、「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」

This skill should be used only when the user explicitly asks to use `$ralph-specum-status`, or explicitly asks Ralph Specum in Codex for status or active spec progress.

Autonomous multi-pass lyric refinement for tightening, cohesion, and album unity. Use after lyrics are written to polish a track or entire album through iterative passes.

Load before writing or revising human-facing text. Choose words deliberately, ground the piece in the reader's context, and remove default LLM phrasing before the final draft.

Use when writing product recommendation content (种草文案) for Xiaohongshu, creating authentic product reviews, crafting persuasive product descriptions, or driving purchase decisions through genuine…

Distills ANY messy input — brain dump, transcript, long PRD, stakeholder notes, feature request, voice memo — into a tight five-field SPEC.md kernel that any downstream planning skill can consume. The…

Summarise a long application log: error counts by type, first occurrence and the likely cause.

Create a GitHub pull request with a drafted title and description. Use when the user asks to "create a PR", "create a pull request", "open a PR", or "submit a PR".

Turn supplied meeting notes or transcripts into sourced minutes, keeping discussion, statements, confirmed/proposed decisions and proposed actions distinct.

Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent instructions, skills, tools, connections, channels, sandboxes, subagents,…

Use when a question requires deep investigation using online information or web search, broad source-backed research, comparison of multiple perspectives, or synthesis beyond a quick lookup.

Recover and review local human-AI conversations from Claude Code, Codex, opencode, Grok Build, and Cursor. Use when the user wants to revisit, search, extract, summarize, or compare work across Agent…

Create original short videos using the 自主收纳回路｜物件逐层入箱、空间扰动与闭合恢复 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new…

Guides authoring agent-facing instructions following Anthropic's SKILL.md best practices. Use when adding or editing skills under `agents/skills/`, the global instructions in `agents/AGENTS.md`, or…

Turn rich agent answers and any file, folder, URL, or export into a polished single-file HTML page. Auto-picks a default route plus 17 concrete design systems (teaching, dashboard, atlas,…

One-sentence brand positioning. Use when the task requires one sentence stating who it serves, what it solves, and how it differs. Apply this method to the specified inputs and verify the deliverable

Use this skill when writing or fixing cold email — first-touch and follow-up sequences, re-engagement, subject lines, personalization at scale, ATL/BTL messaging, copywriting frameworks,…

Read an Evidence Window from a real validator log without flooding context.

Decide module boundaries before the first file: what modules exist, which way dependencies point, who owns state, and what each module may know. Use when starting a project, service, site, API, or…

When the user wants to create, plan, or optimize a lead magnet for email capture or lead generation. Also use when the user mentions "lead magnet," "gated content," "content upgrade," "downloadable,"…

Run a sustained, multi-agent vulnerability-discovery campaign against a target — split its attack surface into slices, hunt each slice with a builder agent, and have a separate critic with fresh…

AI-powered film creation assistant that transforms a single sentence or image into a complete 30-second film. Automatically generates screenplay with scenes, dialogue, and camera directions, then…

Manage durable project memory for Claude Code. Use when prefetching relevant history before work, syncing stable decisions after work, nudging for unsaved lessons, compressing noisy notes, or auditing…