Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when managing blueprints directory structure and avoiding duplication. Always search existing blueprints before creating to prevent duplicate documentation. Handles naming conventions and cross-references.
Use when creating or updating technical blueprint documentation for new features, API changes, or architectural modifications. Always search existing blueprints first to avoid duplication, then write with proper structure.
First-principles briefing from technical documents. Use when: understanding why decisions were made, onboarding to feature reasoning, reviewing decision chains, explaining doc from first principles. Not for: PM/CTO summary (use project-brief), pre-doc analysis (use feasibility-study), code explanation (use codex-explain). Output: structured reasoning chain with sensitivity analysis.
Deeply research all systems and create or update blueprints/ documentation for the entire codebase
Use when writing or editing markdown files. Covers headings, text formatting, lists, links, images, code blocks, and blockquotes.
Interactive Q&A over an existing recap document. Use when: user wants to ask follow-up questions about a briefing-recap-<date>.md produced by /recap-doc, with recap-bounded context + out-of-scope redirect + optional promote-to-request. Not for: generating a new recap (use /recap-doc), general project Q&A (use /ask), code tracing (use /code-explore). Output: per-turn answer referencing file:line + end-of-session promote prompt.
Update an existing SOP to reflect changes in tools, processes, or best practices
精细化 AI 短剧 IP 创作技能（v0.6.0）。三阶段架构：Phase 1 创作（剧本+ref图，反复迭代）→ Phase 1.5 分镜图（每 grid 1-4 张候选静态图 = 视频首帧，工业级核心层）→ Phase 2 出片（按集解锁，4 模自动选）。v0.6.0 关键升级：① ref 库工艺偏置铁律（现代摩天楼易拟物，古建筑必出 chibi 人体，前期 IP 设计阶段就要避坑）② 即梦 5.0 失败模式 + 敏感词清单（3 类 fail 区分 / prompt 1500 字硬上限 / 反派词替换表 / 暧昧词清单）③ 分镜图 8 段 prompt 模板（CHARACTER/BACKGROUND/ACTION/SCENE/CAMERA/LIGHT/TEXT/STYLE）+ NOT humans 子句必加。沿用 v0.3.0 升级：Phase 1.5 分镜图层、4 模视频、ref 5-8 最优。v0.2.0：bash → Python subprocess、36 grid × 4-10s 变奏、红果必爆 7 招、工业级 ref 库 80-150 张、单 prompt 300-500 字。务必触发：用户提到短剧、微短剧、竖屏剧、AI 短剧、AI 漫剧、剧本创作、分镜、即梦/Seedance 出片、红果/番茄/抖音 IP 改编、爽剧、重生、穿越、赘婿、追妻、神医相师、AI 漫剧奇观、或"帮我做一部短剧"类请求。
Produce a rigorous academic peer review of a research paper, manuscript, or preprint (PDF, markdown, TeX, DOCX, HTML, or EPUB) using the full coarse pipeline with the user's local Claude Code subscription doing all the LLM reasoning. Every pipeline stage — structure analysis, overview synthesis, per-section review, proof verification, editorial pass — is served by a headless `claude -p` subprocess instead of a paid API. Use when the user asks to review, critique, referee, or provide feedback on an academic paper. Takes 10-25 minutes. Do NOT use for code review, blog posts, or non-academic documents.
Refactor documents — simplify without losing information, visualize flows with sequenceDiagram.