Docs & Writing

guillemroca Skill

Use when making architectural trade-offs, changing public APIs, shipping user-facing features, or onboarding developers. Guides writing ADRs, inline documentation, and API docs.

guillemroca Skill

Use when implementing framework-specific code (Jetpack Compose, Room, Hilt, Navigation, etc.). Every API usage must be backed by official documentation, not memory or Stack Overflow.

horizonbrute Skill

Run the Horizon AIOS documentation integrity verifier — catches canon pointers to non-existent files, index tables missing on-disk skills, and stale cross-references after renames. Use when asked to check doc integrity, verify the docs are clean, run /doc-check, or after any rename or documentation change.

horizonbrute Skill

Run the Horizon AIOS index / context-cascade consistency checker — verifies every skill directory is indexed, every documentation file is indexed, every path pointer and $HORIZON_* variable in the always-loaded context set resolves, and every referenced slash-command exists, then reports passed/warnings/failures. Use when the user types /index-check, asks to "check the indexes", "find dead pointers", "verify the skill indexes", or after adding/renaming/moving a skill, a doc, or an entry in agents.md.

horizonbrute Skill

Report harness context overhead (KB, words, estimated tokens) for a given path by walking the directory tree and collecting all CLAUDE.md, agents.md, and @-import files the Claude Code harness auto-loads. Use when the user types /context-cost or /ctx-cost, asks how much context overhead a directory has, or wants to know what files the harness is auto-loading.

horizonbrute Skill

Report the skill inventory and whether the owner's aggregated view (skills_bin + usr_skills linked into skills_sbin) is in sync with the filesystem and this session, then heal any drift by rebuilding the links. Use when the user types /resync-user-skills, asks what skills they have or whether skills are in sync, adds/removes a skill, or after an upstream sync may have wiped the links.

horizonbrute Skill

Run a consistency pass between the Horizon AIOS operational wiki and the underlying source documentation, fixing unambiguous drift and surfacing decisions until clean. Use when the user types /horizon_aios_wiki_upkeep, asks to "update the wiki", "sync the wiki with the docs", or "check if the wiki is still accurate".

horizonbrute Skill

Run an iterative documentation/implementation consistency validation pass against the AIOS consistency-check standard, fixing unambiguous drift and surfacing decisions until 100% clean or blocked on user input. Use when asked to run a consistency pass/check, validate AIOS standards, or verify docs and implementation are consistent (e.g. after a feature lands).

horizonbrute Skill

Create or rebuild the Horizon AIOS documentation index so every document is registered and referenceable by a stable index entry. Use when asked to index the docs, update/rebuild the documentation index, or after adding/moving/removing documentation (supports CC-G4 in the consistency-check standard).

nick2bad4u Bundle

Maintains repository docs, TSDoc, TypeDoc output, API comments, and Docusaurus sites. Use when fixing docs drift, TypeDoc diagnostics, TSDoc quality, broken examples/links, or polishing an existing Docusaurus portal.

nick2bad4u Bundle

Builds, audits, and maintains remark and remark-lint plugin repos. Use when scaffolding plugins, creating or repairing remark-lint rules, auditing unified/Markdown AST usage, syncing docs/tests/configs, or validating package/CLI behavior.

nick2bad4u Bundle

Maintains Mermaid diagrams and config. Use when creating, editing, reviewing, theming, or debugging Mermaid flowcharts, sequence/ER/Gantt diagrams, dark themes, themeVariables, frontmatter config, renderer issues, or Markdown blocks.

abhinavbwj Bundle

Comprehensive construction documentation skill covering architectural drawing sets, sheet organization and numbering, drawing standards (line weights, text, hatching, dimensions), BIM Level of Development (LOD) requirements, specification writing using CSI MasterFormat, schedule production (door, window, finish, fixture), and construction administration workflows including RFI processing, submittal review, change orders, site observations, punch lists, and warranty period management.

alainlebret Skill

Creates or rewrites rigorous course material for higher education or professional reskilling. Use when an instructor needs lecture notes, a structured course plan, slides content, examples, or an improved version of an existing course in computer science or a related technical field.

alainlebret Skill

Audits the scientific rigor, pedagogical coherence, feasibility, and grading fairness of teaching materials and evaluation workflows. Use when an instructor wants a severe quality review of a course, TP, exam, rubric, project, or grading report before final use.

barcelosvinicius Skill

Use before deleting code, configuration, or documentation, and before moving content between files. Removal is the only operation whose error no test catches — the test dies with the code. Four axes to clear before deleting, a verification protocol for relocations, and the `// NB:` note that keeps the reason alive for whoever asks again.

barcelosvinicius Bundle

Use when writing or reviewing comments, docstrings, and inline documentation in code. When to comment vs. when to rename, the "why not what" rule, documenting public/business-rule functions, and avoiding comment rot. Per-language doc-comment formats as resources.

kangwang42 Bundle

Create, read, edit, render or validate Word .docx files, including layout, comments and tracked changes. Use when a Word file is an input or deliverable. Do not use for prose-only requests or other file formats.

kangwang42 Bundle

Create, read, edit, render or validate .pptx files, including templates, layouts, notes and comments. Use when a presentation file is an input or deliverable, not for discussion of a talk without file work.

kangwang42 Bundle

基于 officer 与中山大学官方模板制作组会、开题、中期、答辩或正式学术汇报 PPT。仅在用户明确要求中山大学/中大汇报或在 PPT 模板来源分流中选定中大官方模板时使用；不得把未说明学校的通用 PPT 自动套成中大模板。页数与结构服从时长、内容和证据，组会禁止目录页及章节分隔页。实际文件操作配合 pptx。

kangwang42 Bundle

为不限学校或机构的组会、文献分享、方法讲解、开题、中期和答辩规划内容并制作可直接汇报的 PPT。用于从主题、论文、方案、分析结果或既有讲稿新建或结构性重做学术演示；先确认用户模板、机构/会议模板或无模板中性设计，实际 PPTX 读写、渲染和文件检查配合 pptx。明确中山大学时转 sysu-ppt；只对已有 PPTX 做局部文件修改时只用 pptx。

kangwang42 Bundle

撰写、续写或重构中文分析报告、进展报告、操作指南、备忘或纪要，按请求交付正文或完整文件。只要解释或聊天摘要时不创建文件；论文、投稿材料和咨询交付包打包分别使用对应技能。

kangwang42 Bundle

中英文学术与研究报告文本的证据约束编辑及终审技能。用于已有论文、学位论文、摘要、研究或分析报告、基金申请书、cover letter、 response to reviewers、rebuttal、编辑部往来和科研邮件的局部内容修订、授权范围内改写、压缩、语气校准或终审。 先锁定研究事实、数据、统计量、引文、结论边界、允许修改范围和用户纠正，再检查内容功能、论证结构、段落节奏、因果与论断强度、术语一致性及学术书面语。论文从零写作或全文/章节级结构性重写转 academic-publishing； 实际 Word 编辑再配合 docx。不得生成研究发现，不得改动数据或引文，不用于规避披露要求或优化 AI 检测分数。

kangwang42 Bundle

基于已验证的代码、结果数字唯一来源和表图生成或结构性重写中英文期刊论文、学位论文部件、摘要、题名、cover letter、审稿回复、highlights 和投稿正式往来，并完成正式投稿或返修提交前确认。开工先用 biostat-principles；完整稿或论文级结构性重写同时用 evidence-research 核验证据与报告要求，终审用 academic-humanizer；实际 Word 操作再配合 docx。研究生学位论文开题报告使用 graduate-opening-report；已有文本的局部润色或压缩只用 academic-humanizer。

kangwang42 Bundle

以期刊同行评审人身份审查生物医学、临床、公共卫生、流行病学与生物统计稿件，建立稿件内数据和论断证据链，区分报告缺项与方法缺陷，评价研究设计、偏倚、统计、结果解释、透明度、语言和伦理，并生成可定位、分级、可行动的完整审稿报告。用于用户明确要求同行评审、审稿、评审稿件、major/minor comments、reviewer report 或投稿评议。开工先用 biostat-principles；需核验文献或方法依据时用 evidence-research；Word/PDF 文件操作加 docx/pdf，最终措辞可用 academic-humanizer。论文总结、文献综述、作者侧润色或改稿、response to reviewers、投稿前项目审计分别转相应 skill，不用于替编辑作最终录用决定或在无原始数据时声称验证数据真实性。

kangwang42 Bundle

生成、结构化重写和终审研究生学位论文开题报告，覆盖中文正文、学院表单、技术路线、研究计划、参考文献与归档前一致性检查。用户要求撰写硕士或博士开题报告、依据学院模板或既有范本生成开题材料、把研究想法整理成可评审的开题报告时使用；实际 Word 读写加 `docx`，PDF 范本读取加 `pdf`，流行病学或生物统计研究设计加 `biostat-principles` 与 `epi-study-design`。不用于完整学位论文、仅局部语言润色或只改 Word 版式。

libreyolo Skill

Report a problem or friction to the LibreYOLO maintainers with a one-click, pre-filled GitHub issue link. Use for defects: a crash or traceback inside libreyolo, weights that fail to download or 404, training that does not converge on sane defaults, wrong or silently corrupted results, absurd latency, docs that contradict the code. But also use for plain friction, even when nothing is broken: a task that took many turns of trial and error to get right, a missing or misleading doc, an unclear error message, an option that was hard to discover, a workflow that needed a workaround. If this session was harder than it should have been, that journey is itself worth reporting. Also use whenever the user says anything like "report this", "file a bug", or "tell the maintainers". The skill drafts an anonymized issue and hands the user a pre-filled URL; the user clicks submit.

libreyolo Skill

Triage a LibreYOLO GitHub issue or user bug report: reproduce it, classify it, find the owning code, and hand the user a decision-ready assessment. Use when someone says "look at issue #N", "a user reports X", "triage the new issues", or pastes a bug report / stack trace from a LibreYOLO user. Covers the reproduce-first discipline, the version gotcha (released vs dev), the classification taxonomy, multi-part report handling, and the reply the human can post. Agents never open issues, close issues, or post comments; triage output goes to the user.

mattmireles Bundle

Write or repair repo markdown files. Use when the task is editing README files, guides, plans, notes, or markdown lint failures. Apply the repo's markdown rules, preserve the right template or document structure, and keep prose tight. Do not use for inline code comments or code changes that only happen to touch markdown strings.

mattmireles Skill

Ingests offline deep-research exports into README guides for kokoro-coreml: cleans markdown, corrects library/API claims with Context7 when docs contradict the draft, annotates firsthand repo contradictions without stripping useful “worth trying” external synthesis, and adds bidirectional cross-links in README/Guides and README/Notes. Use for guide-ingest, research-to-guide, or corpus linking of a new guide from Deep Research / browser export.

mattmireles Bundle

Write or review inline code documentation that captures domain knowledge, non-obvious constraints, non-greppable cross-file contracts, and state lifecycle. Use when the task is adding or reviewing Python docstrings, file headers, state docs, or constant rationale. Do not use for README files, markdown docs, plan documents, or code changes where comments are incidental.

moda-design Bundle

Create a real, editable slide deck on Moda — slide pages on a live canvas, exporting native PPTX with real shapes and text layers, or a text-layer PDF — not screenshots in python-pptx. Use for: deck, slides, presentation, pitch, keynote, QBR, board update, "turn this doc/repo/notes into slides". NOT: an existing .pptx in hand → moda-deck-pptx; "animate these slides" or a motion version → moda-video.

moda-design Bundle

Change an existing Moda canvas — pasted (URL, share link, cvs_ id) or already in play this session: reword, restyle, recolor, resize, swap images, add/delete sections — plus export or share it. Use for: a change or export of THAT canvas, "fix this slide", every bare follow-up on what Moda just built. Outranks all triggers except mp4/gif. NOT: motion or gif/mp4 of it → moda-video; a moda.page ref → moda-website; a new artifact from it → its format skill.

moda-design Bundle

Static UI mockups and wireframes on Moda: app screens, website pages, dashboard layouts — pictures of interfaces at real viewport sizes, exported png or pdf. Use for: mockup, wireframe, "design a screen/UI for X", app concept, page redesign concept. A mockup is a picture of an interface. NOT: a live hosted page → moda-website; flowcharts and boxes-and-arrows → moda-diagram.

moda-design Bundle

Import a .pptx into Moda as an editable canvas, then fix it. For "clean up this PowerPoint" or any .pptx in hand. CLI lane; the connector routes to the app.

cuga-project Bundle

Deep Wikipedia research — go beyond the keyword search by reading articles section-by-section, following related links, and synthesising a structured report with citations. Use when the user wants a deep dive, primer, or thorough background on a topic.