Docs & Writing

valorvie Bundle

以統一格式撰寫計畫、報告、指南、教學、紀錄、規範等文件，並依專案慣例決定知識庫放置路徑、主題分類與索引更新。 Use when: 使用者要求撰寫或起草文件，或需要整理 docs 目錄、文件分類、主題索引與知識庫結構。包含但不限於：計畫書（新功能/重構/遷移）、報告（調查/階段/分析）、指南、教學、會議紀錄、事件紀錄、決策紀錄、規範文件。 觸發方式: /custom-skills-doc-writer [type] [variant] Keywords: 撰寫文件, 文件模板, 文件分類, 文件目錄, 知識庫, 主題索引, 計畫書, 報告, 指南, 教學, 紀錄, 規範, document writer, plan, report, guide, tutorial, record, standard, 寫文件, 起草, draft

aizech Bundle

Guidance for AI-assisted structured reporting tools. Also use when the user mentions AI reporting, automated templating, speech-to-report, or wants to configure or optimize AI-assisted radiology reporting systems (RadAI, Abba, DeepRad).

aizech Bundle

Create and optimize structured radiology reports using standardized templates. Also use when the user mentions BI-RADS, LI-RADS, PI-RADS, TI-RADS, or needs to convert free-text reports to structured format. For free-text analysis, see radiology-report-analysis.

aizech Bundle

Analyze structured/free-text radiology reports, extract key findings, measurements, and impressions. Also use when the user provides a report for review, summary, data extraction, critical findings identification, or report quality assessment. For structured reporting templates, see structured-reporting.

alekseiul Bundle

Create presentations from text/outline using Marp (Markdown to slides). Use when user asks to create presentation, slides, pitch deck. Triggers on "презентация", "слайды", "presentation", "pitch deck", "сделай презентацию".

cody-sims Bundle

Checks repository-owned .shadow decision graphs read-only, validates architecture drift, stale decisions, relations, evidence, indexes, and derived output, and reports aligned, drifted, stale, and unknown findings. Use when asked to check Shadow, validate .shadow, investigate architecture drift, or identify stale decisions; not for general completion verification, pull-request review, documentation maintenance, observation capture, speculative architecture, or repairing the graph.

cody-sims Bundle

Keeps README, API docs, architecture notes, ADRs, and changelogs accurate when code changes by identifying which documents a change invalidates, documenting rationale, keeping setup instructions and examples runnable, updating the changelog with user-visible changes, and removing stale content. Use when code, configuration, commands, interfaces, or behavior change and documentation must be updated, or when writing an ADR or changelog entry.

conmuyan Bundle

Own rendered visuals and visual redesign from supplied content or values: plot, beautify, lay out, generate, reconstruct, and QA paper figures, visual tables, method/architecture diagrams, icons, palettes, reference-guided layout control, and editable SVG/PDF/PPTX. Use for result-table layout, color/readability improvement, visual table redesign without changing numbers, 绘图美化, 排版, 配色, architecture diagrams, GPT Image 2 generation, reference-driven composition, explicit pure SVG, and editable reconstruction. Visual beautification remains here even for experiment results. Do not choose datasets/baselines/metrics, design evidence semantics, invent content, review the paper, rewrite prose, or convert PDFs into writing exemplars.

andysolomon Bundle

Creates a short project summary file from local notes. Use when the user asks to summarize notes into notes/summary.md, create a project summary, or turn raw notes into a concise markdown artifact. Do not use for general prose editing or unrelated documentation tasks.

anthropics Bundle

Run the oncall handoff for a rotation window — the whole handoff, not just a document: build the summary (what the incoming oncall needs to know first, what is still open, incidents with impact numbers, alert and page counts, hygiene suggestions, every number traceable to a source), post it as the report for the outgoing oncall to correct, walk the incoming oncall through the open items and answer their questions in the thread, update the open-items list as they respond, and note when the incoming person acknowledges. Runs mainly in the team's standing oncall / monitoring channel, normally as a scheduled routine that fires at rotation change so the report is waiting when the shift turns over; it can also be asked for by hand ("@Claude run the handoff"), and works from an incident channel too. Use when a scheduled handoff routine fires, or on "handoff", "hand-off", "hand over", "oncall summary", "shift summary", "weekly oncall report", "what happened this shift / this week", "write up the rotation", or when so

anthropics Skill

Post a sitrep (situation report) for a live incident, in its incident channel: a short update in a fixed layout for people who have not read the whole channel — the current picture and what moved since the previous update, nothing more. Use on "sitrep", "status update", "where are we", "what's the latest", "catch me up", "summarize the incident so far", "update for leadership / support / customers", or when asked to keep posting one on a schedule ("post a sitrep every hour until this is resolved"); also when the oncall memory sets an update cadence for incidents of this severity and the person running the incident asks Claude to keep it. Reads the channel, the alert thread and the findings already posted, re-reads the one key signal, and writes: status line, TL;DR, impact, what changed since the last sitrep, what is in progress and who has it, what is needed, when the next update comes, one chart. Facts come only from what people in the channel said or what Claude read first-hand; cause and recovery time are

ascend Bundle

Analyzes user-provided error messages, logs, and environment information to identify root causes and generate customer-friendly responses for Ascend NPU hardware scenarios. Use when: (1) User provides error logs, stack traces, or crash reports, (2) User describes a problem with environment/context involving Ascend NPU hardware, (3) User requests debugging assistance or root cause analysis for MindSpeed, MultimodalSDK, Vision SDK, or other Ascend-related components, (4) User needs issue resolution guidance. This skill works independently from any specific codebase and can analyze errors based on built-in knowledge, common patterns, external documentation, and provided context. Supports multiple repositories by accepting configurable repository paths for source code reference. ALWAYS use this skill when user provides ANY error information in Ascend NPU context - do NOT attempt to analyze without it.

ascend Bundle

Generate daily operations reports for GitCode repositories with key metrics, AI summaries and Markdown output. 将 GitCode 上配置的仓库运营数据整理成日报输出；支持关键指标统计、AI 摘要与 Markdown。Python 3.7+ standard library only, no pip dependencies.

ascend Bundle

Generate release notes for GitCode repositories from commits (by tag range or since-date), grouped as feat/fix/docs/other, output Markdown for Release pages. 按 tag 区间或日期拉取提交并生成版本发布公告 Markdown。Python 3.7+ standard library only.

belos-street Skill

快速生成结构化上市公司投资分析报告，涵盖公司业务、投资逻辑、催化剂、财务与估值分析、风险提示和操作建议。Invoke when user asks for investment memo, one-page report, or quick analysis of a public company.

composio-community Skill

Generate MRR/ARR reports from Stripe — new, expansion, contraction, churn — broken down by plan or segment. Use on "what's my MRR?", "weekly revenue report", "churn this month", or "show me expansion".

cyberuni Bundle

Use this skill when pulling Asana project tasks into local markdown for offline planning or documentation.

cyberuni Bundle

Use this skill when the user wants a sprint summary — completed vs incomplete tasks for retro or stakeholders.

dandacompany Skill

모든 산출물에서 인용·근거를 보존하고 사실/의견을 분리하는 회사 공통 규칙. 출처 URL 누락, 추측 어휘 사용, 비공식 평가 발언을 차단한다. Brand Intelligence Lab 모든 에이전트가 상속한다.

howarewoo Bundle

Use when reviewing a completed conversation for concrete, preventable instruction gaps; invoke as /woostack-reflect or at a candidate-gated final-reply boundary to report suggestions and, only after explicit acceptance, prepare a sanitized duplicate-safe upstream issue.

iamzifei Skill

Generate a deliverable markdown report by merging all /money-save snapshots for a project. Produces a shareable, dated document at ~/.smtm/reports/{project}/. Useful for sharing progress with co-founders, advisors, investors, or for personal review weeks/months later. Use when the user wants to package up accumulated state into a readable artifact. Triggered by: 'package this up', 'make me a report', 'export for partner', 'give me the deliverable', '出报告', '打包', '整理一份', '给合伙人看的'.

jposluns Bundle

Draft, rewrite, edit, review, or quality-assure prose using the Clean Language standard. Use for emails, Teams or LinkedIn messages, executive communications, reports, policies, governance artefacts, technical documentation, incident communications, strategy material, and other finished prose where directness, precision, natural cadence, Oxford English, and removal of generic AI-writing patterns matter. Preserve legal, technical, contractual, quoted, and standards language when alteration could change meaning.

jwiegley Bundle

Write in John Wiegley's authentic voice. Use when drafting technical articles, blog posts, essays, or any written material that should read as if John wrote it himself. Captures patterns from 1,100+ posts spanning 1992-2026 across both technical (newartisans) and personal (johnwiegley) blogs. Focuses on technical writing but incorporates cross-cutting voice patterns from the full corpus.

jwiegley Skill

Guides writing and editing of technical documentation in an elevated, sedate, institutionally grounded register — measured, authoritative, and formal rather than casual or promotional. Applies when drafting or revising manuals, plans, runbooks, specifications, or policy documents, or when lifting an existing flat draft into this register.

jwiegley Bundle

Methodology for finding and removing dead code and stale documentation with evidence-based safety, using a mark / debate / act / verify workflow. Use when asked to remove dead code, unused symbols, unreachable branches, stale docs, unused imports, or dead feature flags -- gathering independent evidence before each removal and re-verifying build and tests after. The `/eliminate-dead-code` command turns it on.

jwiegley Bundle

Use when the user requests a thorough pre-PR code review of the current branch — e.g. "run a validated code review". "validated" is a key word

kdeldycke Skill

Write a bug report for an upstream project. Read its contribution guidelines, issue templates and community norms first, then produce a markdown file ready to paste.

kdeldycke Skill

Compare and synchronize Sphinx documentation against the upstream `kdeldycke/repomatic` reference, or across sibling projects. Downstream repos compare against upstream by default. Find the differences in conf.py, install.md, the index.md toctree, pyproject.toml docs dependencies, extra-deps sections, readme badges and static assets. Use when you align documentation structure, catch stale dependencies, or push improvements across Sphinx-enabled repositories.

khuynh22 Skill

Documentation

ksachdeva Bundle

Comprehensive Zephyr SPI subsystem expertise for serial peripheral communication. Use when: (1) Configuring SPI controllers or devices via devicetree or Kconfig, (2) Implementing synchronous SPI transfers with spi_transceive/spi_read/spi_write, (3) Implementing asynchronous SPI with spi_transceive_cb or spi_transceive_signal, (4) Setting up SPI modes (CPOL, CPHA, word size, bit order), (5) Managing chip select via GPIO or hardware CS, (6) Using scatter-gather buffers for multi-part transactions, (7) Choosing between sync and async APIs for a use case, (8) Troubleshooting SPI communication issues (clock polarity, CS timing, data corruption).

l3ad3r1 Bundle

Read, extract, and manipulate PDF files — extract text and tables, merge multiple PDFs, split or extract page ranges, rotate pages, add watermarks, and OCR scanned PDFs. Built on the permissively licensed pypdf, pdfplumber, and OCRmyPDF libraries. Use this skill whenever the user wants to read a PDF's contents, combine or split PDFs, rotate or watermark pages, pull tables out of a PDF, or make a scanned PDF searchable. For converting a PDF to Markdown or handling batches of mixed file types, use markitdown-converter instead.

l3ad3r1 Skill

Create, read, and edit Microsoft Word (.docx) documents — add headings, paragraphs, styled runs, tables, images, page breaks, and read existing documents' text and tables. Built on the MIT-licensed python-docx library. Use this skill whenever the user wants to generate a Word document, edit an existing .docx, extract text or tables from a Word file, or produce a formatted report/letter/memo as .docx. For converting a Word file to Markdown or handling batches of mixed file types, use markitdown-converter instead.

l3ad3r1 Skill

Create, read, and edit PowerPoint (.pptx) presentations — add slides, titles, bullet text, images, tables, and speaker notes, and read text out of existing decks. Built on the MIT-licensed python-pptx library. Use this skill whenever the user wants to generate a slide deck, edit an existing .pptx, extract text or notes from a presentation, or produce slides/a pitch deck as a PowerPoint file. For converting a deck to Markdown or handling batches of mixed file types, use markitdown-converter instead.

lensetek Bundle

Use to prepare final PDF export specifications for academic books after layout and DOCX review, with flexible page sizes including default UNESCO, A5, A4, and custom dimensions.

lensetek Bundle

Use to convert a single research paper, thesis chapter, dissertation segment, or focused research report into a monograph outline, chapter plan, and expansion strategy.

lensetek Bundle

Use to prepare academic book manuscripts for editable DOCX export for Microsoft Word or Google Docs, including page size, margins, heading styles, header/footer, table of contents, captions, bibliography, and metadata/privacy checks.