Docs & Writing

mz038197 Skill

橘子蘋果課後學習表現報告完整流程。從 corp.orangeapple.co 抓取梯次學生名單、修復課堂錄音逐字稿中的語音辨識姓名誤植、從 exam.orangeapple.co 測驗平台抓取各單元成績、最後產出給家長的三明治回饋學習報告，全程使用 Chrome DevTools 與 Obsidian CLI 工具，並將各階段結果存入 Obsidian 筆記。當使用者提到「橘子蘋果課堂報告」、「梯次資訊」、「逐字稿修復」、「課堂測驗成績」、「家長學習報告」時使用此 skill。

driangle Skill

Build a skival eval suite that benchmarks one taskmd skill — fixture, deterministic graders, four variants, smoke run, and a committed report. Use when adding a suite under evals/, benchmarking a skill, or measuring whether a skill actually helps.

odere-pro Skill

Query the wiki and render the answer as portable, GitHub-flavored markdown saved under vault/output/. Trigger when the user asks to "export X as markdown", "produce a markdown brief", "save the answer to the output folder", "give me a plain markdown version of …", or invokes /claude-wiki-pages:markdown directly. Reuses the query reading contract, then strips Obsidian-only syntax so the file is usable outside the vault.

odere-pro Bundle

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

ominou5 Bundle

Builds a 2-page opt-in / lead generation funnel. Captures email addresses in exchange for a lead magnet (PDF, checklist, template, video, etc.). Use when the goal is to grow an email list.

samzong Bundle

Generate a deep, code-first project wiki and VitePress documentation site (DeepWiki-style) for a repository. Use when asked to create a complete wiki/manual for a new codebase, build a code-first documentation site, or generate a `codewiki/` folder with structured Markdown, diagrams, and navigation based on the source code (not existing docs).

samzong Skill

Read, write, and sync project memory stored as Markdown under `~/.agents/memories/{project-name}/`. Use when starting work and needing project context, when the user asks to read or update memory, or when ending a session and preserving stable learnings. Triggers: "read memory", "load memory", "write memory", "save memory", "update memory", "sync memory", "refresh memory", "读取记忆", "加载记忆", "写入记忆", "保存记忆", "更新记忆", "同步记忆".

xingfanxia Skill

Generate a session report with token usage estimates, work summary, and outcomes

andvl1 Skill

Roll up profile-usage telemetry into profile-stats.md and propose new named workflow profiles for recurring task shapes. Triggers on "/coordinator-stats", "profile stats", "which workflows do we use", "propose a new profile", "workflow usage report".

andvl1 Skill

Halt a running autonomous yolo loop and produce a final report. Triggers on "stop yolo", "halt the loop", "/team-yolo stop", "end yolo", "abort autonomous run". Safe to invoke at any time.

thevibethinker Bundle

Generate an observed AI fluency profile from real AI usage traces, workspace artifacts, and Vibe Pill methodology. Use when assessing how someone actually works with AI across systems, not when running a self-report quiz.

thevibethinker Bundle

Evaluate early-stage pitch decks across four investor credulity frames, stage-aware substantive rubric dimensions, optional named-POV reads, and markdown/JSON report rendering.

ui5 Bundle

Fix runtime-breaking patterns in JS files that the UI5 linter does NOT report. Use this skill when: - Tests fail after modernization with "ReferenceError", "TypeError: Cannot read properties of undefined", or "X is not defined" - The linter shows zero remaining errors but tests still crash at runtime - Phase 3, Step 3.2 of the modernize-ui5-app workflow (runs after the parallel globals batch, before fix-cyclic-deps) - User mentions "runtime errors after modernization", "test failures after modernization", "global namespace still used" - After running fix-js-globals and fix-cyclic-deps, but tests STILL fail - User sees "X is not a constructor" or module loading errors in test output The linter only checks sap.* globals in JS. App-specific namespace patterns (e.g., com.example.app.utils.Module) are invisible to it. This skill detects and fixes those across ALL JS files — app source AND test. NOTE: App-namespace globals in XML files are handled by `fix-xml-globals` — NOT by this skill.

ui5 Skill

Handle Fiori Elements V2 controller extensions during UI5 modernization. Use this skill when: - Extension controllers use `sap.ui.controller()` AND the manifest has a matching `controllerName` entry (Case B → report only, do not modernize) - Extension controllers use `Controller.extend()` with manifest `controllerName` registration (Case B → report only, do not modernize) - Code contains `registerControllerExtensions` calls (Case A → ControllerExtension.extend + override) - Manifest.json has `sap.ui5/extends/extensions/sap.ui.controllerExtensions` with `controllerName` entries Case B (plain object) is by far the most common. For Case B, do NOT modify controller files — report them and move on. Case A requires actual code modernization. For plain controller definitions in custom (non-Fiori-Elements) apps where `sap.ui.controller()` is just defining a standalone controller, use `fix-js-globals` (Case 9) instead.

vcxcvii Skill

Render the mandatory five-section report for a chosen window, refusing any window longer than available snapshot history rather than extrapolating a partial period into a full one. Use this skill whenever the user asks to: - Get a monthly report, weekly pulse, or quarterly review - Show progress to a client or their team - See what changed in a given period Trigger even for casual requests like "monthly report", "how did we do this month", "progress report", "show the client", "weekly pulse".

lglucas Skill

Derive a 10-section pitch from BP v0.0.2 into docs/business/PITCH.md, then ask the founder whether the BP and Pitch should live online inside the product (/pitch, /investors) — running a redaction gate over what must never go public. Runs at WIZARD stage 2.9. Use when the user says "preciso de um pitch", "vou apresentar pra investidor", "quero pôr o BP no site", "dá pra deixar isso público?", "como resumo tudo isso em 10 slides?".

linegel Bundle

Diagnose unexpected Three.js WebGPU/TSL runtime, rendering, API, asset, or version behavior. Use for a concrete failure, a suspected upstream regression or known issue, or a choice among an application fix, released upgrade, bounded workaround, upstream report, and blocker.

lync-cyber Skill

框架反馈打包 — 把下游项目使用 CataForge 时发现的问题 / 改进建议 / 偏离上游基线的纠偏，打包成 upstream-ready 的 markdown bundle，回流到 CataForge 仓库。区别于下游项目自身的用户反馈渠道：本 skill 仅针对 CataForge 框架本体（CLI / scaffold / agents / skills / hooks / docs）。当用户提到反馈框架问题、提交 CataForge issue、上游 baseline 不准确、累积 upstream-gap 想批量回报时使用。

manager-dot-dev Bundle

Prepares agendas, diagnoses struggling 1:1 relationships, and gives frameworks for running effective 1:1 meetings with direct reports. Use when the user wants to prepare for, run, improve, or follow up on a 1:1, or says "1:1 agenda," "prepare for my 1:1," "1:1 notes," "what should I talk about with," "my direct report," "check in with my report," "make my 1:1s better," "1:1 template," or "my 1:1s feel like status updates." Do NOT use when the user needs to deliver specific feedback (use feedback) or discuss performance reviews (use performance-reviews).

manager-dot-dev Bundle

Helps engineering managers work effectively with Software Architects, Staff Engineers, and Principal Engineers — covers the EM's side of the relationship (responsiveness, proactive consultation, giving credit), how to advocate for architect time, pre-consultation preparation, and the two architecture team models (Centralized vs. Decentralized). Use when the user says "architect," "staff engineer," "principal engineer," "technical design review," "working with senior technical people," "getting architecture help," or "how do I get more architect time." Do NOT use for managing staff/principal engineers who report directly to you (use `managing-high-performers` or `delegation`).

marioluciofjr Bundle

Skill para calcular o valor futuro de investimentos atrelados ao CDI. Use esta skill SEMPRE que o usuário utilizar o gatilho /cdi ou mencionar cálculo de investimento atrelado ao CDI, percentual do CDI, renda fixa CDI, rendimento CDI ou valor futuro de aplicação CDI. O usuário informa o valor investido e o percentual do CDI que o investimento oferece (ex: 110% do CDI). A skill coleta também o período e a taxa CDI vigente, executa o cálculo via script Python (cdi.py) buscando a taxa atualizada via web scraping, e retorna uma tabela markdown com valor investido, período, taxa efetiva e valor futuro projetado.

microsoftdocs Skill

Identifies and fixes spelling errors, contextual typos, and agreement mistakes in Markdown documentation. Use this when asked to fix typos, correct spelling, or proofread documentation files.

microsoftdocs Skill

Identifies severe factual errors in content. Use when asked to fact-check documentation for major inaccuracies.

microsoftdocs Skill

Identifies structural and topical gaps in documentation — missing sections, absent code samples, missing diagrams, incomplete related content, and unaddressed scenarios. Use when asked to assess content completeness.

microsoftdocs Skill

Enforces sentence case for all Markdown headings and bold sub-headings. Use when asked to fix heading capitalization.

microsoftdocs Skill

Ensures abbreviations are expanded on first use per Microsoft style. Use when asked to check acronyms or abbreviations in documentation.

microsoftdocs Skill

Replaces banned words and phrases per Microsoft Writing Style Guide. Use when asked to fix word choice or apply Microsoft style guidelines.

microsoftdocs Skill

Checks Markdown formatting including code fences, alert syntax, list markers, and table structure. Use when asked to lint or fix Markdown formatting.

xiaolai Skill

Hunt server-side template injection (SSTI) across Jinja2 (Flask/Django), Twig (Symfony), Freemarker (Java), ERB (Rails), Spring, Velocity, Mako, Thymeleaf, Smarty. Detection probes use double-curly and dollar-curly math expressions evaluated server-side. Once an engine is fingerprinted, escalate to RCE via the engine-specific class-walker, callback-registrar, or Execute-utility patterns documented in disclosed reports. Detection patterns: error messages reveal engine, blank or numeric eval reveals expression mode. Targets: email templates, PDF/report generators, CMS preview features, error pages with user input. Use when hunting RCE via template rendering, when content shows engine fingerprints, when finding endpoints that compose strings with user input before render.

berabuddies Bundle

Edit PDFs with natural-language instructions using the nano-pdf CLI.

berabuddies Bundle

GLM-OCR Multimodal Deep Analysis

axross Bundle

Deciding what a system should report about itself, independent of the SDK that carries it out — the vendor-neutral layer over logs, metrics, traces, error handling, and product events. Triggers on code that logs, throws, catches, reports an error, tracks an event, or identifies a user, and on "log level", "capture exception", "error boundary", "breadcrumb", "trace sampling", "cardinality", "event name", "identify", "reset on logout", or "cookie consent". For which package to install, which option controls collection, or source maps and build-time tokens, use the installed vendor's own capability. Covers try/catch placement, metric cardinality, and event naming through consent.

fernando-delosrios-sp Bundle

Scan a codebase for deepening opportunities, present them as a markdown report, grill through whichever one you pick, then write an OpenSpec change package when capability specs exist.

hongmaple0820 Bundle

PDF - Document Production Workbench

hongmaple0820 Skill

将 PDF/Word/Markdown 学习资料转化为精炼的 Cheatsheet 文档。支持三种风格（知识点速查卡/思维导图式/Q&A式），输出双栏小字 PDF。当用户说"生成 Cheatsheet"、"帮我做个速查表"、"把这个资料整理成一页纸"、"做个知识卡片"时触发。**不处理**：基于材料出题（→ quiz-mastery）、长期学习项目（→ study-buddy）。

hongmaple0820 Bundle

飞书 Markdown：查看、创建、上传、编辑和比较 Markdown 文件。当用户需要创建或编辑 Markdown 文件、读取、修改、局部 patch 或比较差异时使用。