Docs & Writing

typeweaver Bundle

Write, revise, or review source-code comments that preserve context unavailable from the code. Use for module comments, inline explanations, API documentation, TODOs, deprecations, suppressions, or workaround notes during implementation or review. Do not use for standalone user documentation, general prose, commit messages, or review discussion.

wecode-ai Bundle

Submit wiki documentation pages to Wegent backend API. Simplifies the HTTP POST process for wiki content submission.

coleam00 Skill

Run THIS project's full quality gate — tests, type-check, lint, and (for full-stack) the build — and report overall health with ✅/❌. Use before opening a PR; this is the gate that runs BEFORE the PR, not after.

gxgeek-n Bundle

将浙江大学 MEM 学位论文 LaTeX 项目（zjuthesis/body 或 chapters/，可含 ref.bib/PDF）或普通 md/docx 草稿生成或审计为符合官方模板的 DOCX，优先使用 scripts/mem_docx.py（latex/draft 子命令）。仅在用户明确要运行/维护 thesis-docx 管线、把该类论文/草稿转 Word、或诊断该管线输出时使用；不要用于普通 Word 排版、通用三线表、非 ZJU MEM 论文、参考文献咨询。

gxgeek-n Bundle

ZJU MEM 答辩准备一站式，覆盖**中期答辩 / 预答辩 / 盲审 / 最终答辩**全部环节 — 评委视角主线审计 (30秒扫骨架+三连接测试+题目/目录/摘要可扫描性)、答辩策略、预测问答、套官方模板做PPT (桥接 report-ppt-builder)、从真实答辩录像提取老师问答(桥接 video-transcribe-analyze)、 把材料压成≤2页高密度答辩手卡并打印；**中期答辩模式**另含 ZJU 中期报告会五段 PPT 逐页结构、 讲稿与 100 分制评审打分。触发词：答辩准备、中期答辩、中期报告会、中期汇报PPT、预答辩、 盲审准备、最终答辩、答辩PPT、模拟问答、defense、midterm defense、答辩策略、主线梳理、答辩手卡、答辩打印。 先读 references/midterm-playbook-实战.md（通用打法）；中期材料结构见 references/midterm-defense-ppt.md。

gxgeek-n Bundle

ZJU MEM 论文 LaTeX 编译。格式预检→环境验证→四遍编译→PDF输出验证。支持 quick/full/clean 模式。 触发词：编译论文、build thesis、编译、生成PDF、LaTeX、xelatex。

gxgeek-n Bundle

从学术论文/内容自动生成"图片版"幻灯（Gemini 出图 + 风格画廊 academic-paper/blueprint/chalkboard…）， 自动侦测 PDF 里的图表。适合投稿汇报、组会、讲座这类以视觉呈现为主的幻灯。 Generate professional slide deck IMAGES from academic papers/content; auto-detects figures from PDFs. 触发词：做PPT、生成PPT、幻灯片、演示文稿、论文转PPT、图片版幻灯、组会PPT、讲座PPT、 create slides、make a presentation、slide deck。 边界：学位论文**答辩/中期官方模板 PPT**（套学校母版、嵌演示者备注、量化自检门）→ thesis-defense （桥接 report-ppt-builder，含中期模式）；本 skill 只出"图片版"风格幻灯，不套官方 Word/PPT 模板。

gxgeek-n Bundle

ZJU MEM 中期报告全流程生成：登记表、完整中期报告（五段结构+已写章节+三级目录）、PPT大纲、系统填报指引。含自动评分和对抗审查循环。触发词：中期报告、中期报告登记表、中期报告会、midterm report、MEM中期、论文中期。用户说"帮我写中期报告""生成中期报告""中期报告登记表"时触发。

gxgeek-n Bundle

为硕士研究生，尤其是 ZJU MEM 学生，生成和审查读书报告、文献综述型读书报告、第 4 篇中期前读书报告，以及中期报告中“课程学习/实践实训/读书报告完成情况”与文献综述衔接内容。输入通常包括 3-8 篇文献、报告标题、字数要求、学校/学院/专业/导师/姓名/学号、研究方向或学位论文题目；输出符合硕士培养要求、GB/T 7714-2015 引用规范、模板格式、文献来源可追溯，并在交付前完成 MEM 100 分制自评与自动检查。用户提到“读书报告”“文献综述”“硕士读书报告”“MEM 报告”“第4篇读书报告”“中期报告前读书报告”“课程学习与文献阅读”“开题后文献整理”“中期报告文献部分”“读书报告自动评分”时应触发；若用户直接要求生成完整 MEM 中期报告，本 skill 可提供五段结构草稿和自评清单，但必须要求用户提供开题目标、已完成工作、阶段成果、差异说明和下一步计划等进度材料，不能虚构成果。

gxgeek-n Bundle

Manage a thesis project's machine-readable state, numeric-evidence ledger, literature-verification registry, unified Doctor checks, stage artifact provenance, and tri-state submission gates. Use when Codex or Claude needs to refresh paper status, trace every thesis number to evidence, diagnose Python/LaTeX/font/citation/caption/statistics/DOCX/PDF readiness, or return PASS, REOPEN_WRITING, or REOPEN_ANALYSIS for an advisor-review, predefense, blind-review, or final-delivery package.

gxgeek-n Skill

批量提取参考学位论文 PDF → 自动定位章节结构 → 与自己的论文对比分析。 从参考学位论文目录中选取相关论文，用 pdftotext 提取全文，自动识别章节标题和结构， 然后按章节逐段对比写作手法、论述逻辑、数据呈现方式。 触发词：参考论文分析、对比参考论文、参考论文提取、论文对比、范文结构、参考范文、对标范文结构、ref analysis。 边界：范文的**语体/口吻**对标（句子怎么写）→ thesis-style；本 skill 做**结构/章节/论述手法**的 PDF 提取与逐章对比。

jd-solanki Skill

Create a new Bruno API endpoint file from API documentation

jd-solanki Skill

Draft one small, plain ticket as a markdown file, then file it on the project's tracker once the user approves.

kellymears Skill

Bump plugin versions in this repo's .claude-plugin/marketplace.json after making changes. Detects which plugins were modified, determines the appropriate semver bump (major, minor, or patch) from commit history, updates the manifest, and syncs project documentation (README plugin table, site homepage) with the manifest. Use when the user wants to bump versions, update plugin versions, or says "version bump". Also trigger when the user says "bump changed plugins", "update versions", "bump versions", or anything about versioning plugins after making changes — even just "version" or "bump".

kellymears Bundle

Draft human-facing communications — emails, Slack messages, blog posts, and general markdown — in the user's authentic voice. Use this skill whenever the user asks to write, draft, or compose any message intended for other people: emails, Slack messages, blog posts, announcements, PR descriptions, issue writeups, documentation prose, or any text where voice and tone matter. Also trigger when the user asks to "write something up", "send a message", "draft a response", "put together an email", or any variation of composing human-readable text that isn't pure code.

kellymears Skill

Create a document in an Obsidian vault. Supports all vaults synced via iCloud. Use this skill when the user asks to create a note, write to Obsidian, save to their vault, or any variation of composing a markdown note for Obsidian.

latchagent Skill

GitHub PR attestation comment service for Latch Enclave. Posts session receipts as Markdown comments on GitHub PRs via the REST API. Use when working on PR annotations, attestation comments, or GitHub integration for session receipts.

liaoann Skill

Diff hygiene principles for human-auditable changes. Use when deciding how to split, limit, or report a diff so behavior changes, refactors, renames, formatting, generated output, and test changes remain separable and reviewable.

liarmttt Bundle

Refine prose and everyday explanations to remove formulaic AI phrasing, empty rhetoric, repetitive structure, and generic character voices while preserving meaning and technical syntax. Use for 洗稿、去 AI 味、去八股、自然表达, or to enable, inspect, or exit an explicitly requested continuous or persistent rewriting mode. Supports character-card prose, dialogue, narrative, documentation, plans, and reports; ordinary card creation does not activate a persistent mode.

truefoundry Bundle

Fetches TrueFoundry documentation, API reference, and deployment guides. Use when the user needs platform docs or how-to guidance.

tstelzer Bundle

Technical writing reference for docs, plans, reviews, prompts, and user-facing artifacts.

wagneripjr Bundle

Use when adopting the Open Knowledge Format (OKF v0.2) in a repository, or maintaining a documentation bundle already in it: bootstraps a conformant tree, stamps and repairs YAML frontmatter, regenerates every index.md bottom-up so no document goes unlisted, excludes paths another tool owns via .okfignore, removes log.md and strips changelog/history sections because git already holds history losslessly, and wires CLAUDE.md/AGENTS.md/GEMINI.md to the root index so agents stop grepping for a document's identity. Ships a conformance check that fails closed, plus a coverage check that names every document no index reaches. Triggers on: 'set up OKF', 'make these docs OKF-conformant', 'regenerate the docs index', 'add frontmatter to the docs', 'which docs are missing from the index', 'our documentation keeps drifting'. NOT for writing a document's body or deciding its content - repo templates and the adr skill own that. NOT for reverse-engineering a codebase into fresh specs.

wxxzy Skill

【共享】成本核算 — 汇总 token/时间/API 费用 → docs/cost-ledger.md。当用户说「花了多少/成本报告」时使用。

yha9806 Bundle

Show literature-to-chapter coverage and the writing progress dashboard — which sources support which chapters, and word counts against targets.

yha9806 Skill

Read PDF page by page with structured output — key arguments, terms glossary, thesis connections. Use when reading academic papers, books, or articles.

ozrwayne Bundle

将 Markdown 文稿切成带稳定 ID 和 hash 的段落块，只对用户批准的块执行替换，并输出保留比例、修改理由和问题追踪报告。Use when the user asks for“只改这几段”“按审稿意见局部修改”“保留其他内容不动”“生成可复核修改 patch”,or requests the rw-revision-patch workflow.

ozrwayne Bundle

从论文 PDF 和补充材料中提取结构化字段、章节、图表、原文位置、缺失项和可支持的判断，并可建立带 hash 的 Paper Case 和分阶段精读报告。 Use when the user asks for “提取这篇论文”、“批量抽论文信息”、“做论文卡片”、“精读 PDF”、“提取图表” or “分阶段精读报告”. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.

pipecat-ai Skill

Triage Bug Report

pipecat-ai Skill

Generate a Gradient News & Observer newspaper front page for a time window. Pulls game events into a structured digest, writes ten illustrated story ledes (7 straight news + 2 gossip + 1 market box) into a markdown file, then renders a 2160x3840 newspaper front-page PNG. Usage `/news-front-page [duration]` (default `24h`; e.g. `1h`, `6h`, `7d`).

rubicon Skill

Use when sending a message to another Claude Code Desktop (CCD) session, or when a session needs to report its own address so another session can message it — covers cross-session send_message and session self-identification.

scchearn Skill

Use when resuming work after a pause, reboot, or context switch and the workspace uses `wiki/checkpoints/` resumable notes. Read the latest relevant checkpoint chain, orient to the most likely in-flight scope, verify current files and tools before acting, and report the safest next step. Treats a goal path as concrete context; checks live goal status over stale checkpoints.

scchearn Bundle

Create or extend an Obsidian-friendly markdown wiki scaffold in the current workspace. Use this when the user wants to build a wiki, set up a knowledge base, create a research vault, or scaffold a living markdown note graph before adding sources with `/loam::adding-to-memory`. Identifies goals as sibling workflow artifacts, not wiki content. Not for importing or normalizing existing memory-like corpus; use /loam::normalizing-memory for that.

scchearn Bundle

Read a local source file or synthesize conversation context, then integrate admitted content directly into topic, entity, concept, and analysis pages in existing memory (the wiki substrate). Use this when the user wants to add a source to the wiki, add a document, ingest a local note, transcript, article, report, or PDF, or explicitly preserve the current conversation as a topic note. For session-learning routing across wiki, guidance, checkpoint, task annotation, or discard, use /loam::learning-from-session. Must not ingest a goal wholesale; admit only independently reusable findings.

scchearn Bundle

Inspect an existing memory corpus (wiki substrate) and align it to this repo's Obsidian-friendly note-graph conventions. Use this when the user wants to import, normalize, retrofit, or clean up existing memory, notes folder, vault, docs tree, or mixed markdown knowledge base. In monorepos, also use it to align relevant AGENTS.md and CLAUDE.md files. Excludes goals/ from normalization. Not for routine wiki maintenance; use /loam::linting-memory for that.

securityskills Skill

Write bug bounty reports that get triaged quickly and rated accurately — clear impact statements, minimal reproduction steps, and professional tone. Use before submitting any vulnerability report.

winhok Bundle

TestSpec 用例评审（流程第 5 步）- 对生成的测试用例做 14 维度交叉验证（R1-R6 规则检查 + H1-H8 启发式检查），产出 review-report.md 评审报告。当用户要「评审用例」「检查用例质量」「审查测试用例」或执行 testspec-review / testspec review 时使用。也适用于用户说「用例写完了帮我看看」「检查一下覆盖度」「用例有没有问题」的场景。支持默认模式和 --deep 深度模式。