Docs & Writing
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
-
xuiltul Skill Image Posting 3채팅 응답에 이미지를 넣어 표시하는 스킬. 도구 결과 URL 감지, Markdown 이미지, assets 경로를 다룬다. Use when: 검색·생성 도구 이미지를 답변에 포함, Markdown으로 이미지 삽입, 첨부 표시가 필요할 때.
-
xuiltul Bundle Skill Creator 3Markdown 스킬을 만드는 메타 스킬. SKILL.md frontmatter·본문과 Progressive Disclosure·create_skill 절차를 다룬다. Use when: 신규 스킬 추가, read_memory_file 경로 규칙 확인, references·templates 포함 생성이 필요할 때.
-
cp-here Bundle DOCX Formatter将文本或 Markdown 内容排版为专业的中文 Word (.docx) 文档,支持 OMML 数学公式、表格框图、标准排版、引用上标和轻量完整性验证。当用户要求 Word 排版、把 Markdown 或纯文本转成 Word 文档、生成带公式的 Word 文档、用数学方程格式化文档、在 Word 中创建流程图样式图表、将参考文献引用渲染为上标、或格式化文档为 Word 时调用。
-
xuiltul Skill Web Search ToolWeb search tool. Queries the public internet via the Brave Search API. Use when: researching current events, finding documentation, fact-checking, or fetching ranked search results.
-
idwong Bundle Hld Design生成概要设计说明书(HLD / High-Level Design)的技能。在需求确定后、详细设计前,从 SRS 需求说明书推导系统总体架构。 触发场景:(1) "概要设计" "概要设计说明书" "生成概要设计" "写概要设计" "HLD", (2) "系统设计" "总体设计" "架构设计" "系统架构设计", (3) "分层设计" "模块划分" "技术选型方案", (4) "审查概要设计" "检查概要设计" "概要设计有没有问题", (5) "根据代码补概要设计" "反向生成概要设计" "同步概要设计", (6) "导出概要设计" "概要设计导出Word", (7) 用户已有 SRS 需求说明书,需要产出系统架构级设计文档时触发。 支持完整生成、局部完善、审查修复、反向同步、导出 Word。
-
idwong Bundle Lld Design生成详细设计说明书(LLD / Low-Level Design)的技能,一份文档涵盖「模块详细设计 + 数据库物理设计 + API详细设计」三大维度。在概要设计后、编码前,产出开发可直接照着编码的设计依据。 触发场景:(1) "详细设计" "详细设计说明书" "生成详细设计" "写详细设计" "LLD", (2) "数据库设计" "数据库物理设计" "表结构设计" "建表设计" "数据库文档", (3) "API设计" "接口设计" "API详细设计" "接口文档" "接口规格", (4) "类图设计" "模块详细设计" "时序设计", (5) "审查详细设计" "检查详细设计" "检查表结构" "检查接口设计", (6) "根据代码生成详细设计" "反向生成详细设计" "从代码补数据库设计" "同步详细设计" "代码和设计对齐", (7) "导出详细设计" "详细设计导出Word", (8) 用户已有 SRS 或概要设计,需要产出表结构/接口/模块实现级设计文档时触发。 支持完整生成、局部完善、审查修复、反向同步、导出 Word。
-
idwong Bundle Pm Test Cases用户要求生成、撰写或创建测试用例时必须使用本技能。 触发场景:(1) "生成测试用例" "写测试用例" "创建测试用例", (2) "QA测试" "测试文档" "验收标准" "测试计划", (3) "导出测试用例" "测试用例导出Word" "测试文档转Word", (4) 从需求生成功能/边界/异常/权限测试用例, (5) 生成 API 测试用例或测试报告模板。 基于需求文档或功能描述自动生成完整测试用例集。
-
xuiltul Skill Zoom Meeting ScribeListen-only scribe workflow for Zoom meetings. Silently understand and record meeting transcripts delivered via RTMS, escalate only urgent matters to your supervisor, and post the report only after human approval once the meeting ends. Use when: receiving an inbox message with source=zoom (carrying a "[Zoom会議実況 チャンク#N …]" or "[Zoom会議終了 …]" header).
-
xuiltul Skill NewstaffSkill for hiring and creating new Digital Anima in the AnimaWorks organization. Create a character sheet (Markdown) based on interviews, then use the CLI command (animaworks anima create) to generate identity/injection/permissions in bulk. After creation, self-configure via bootstrap. "Create a new employee", "Hire someone", "New employee", "Hiring", "Create Anima", "Recruitment", "Add team member", "Expand the team", "Add staff", "Create subordinate", "hire", "recruit", "team member"
-
xuiltul Skill Newstaff 2AnimaWorks組織に新しいDigital Animaを雇用・作成するスキル。 キャラクターシート(Markdown)をヒアリングに基づき作成し、CLIコマンド(animaworks anima create)で identity/injection/permissions等を一括生成する。作成後はbootstrapで自己整備。 「新しい社員を作って」「人を雇って」「新しい社員」「雇用」「Anima作成」「採用」「チームメンバーを増やす」「人員追加」「部下を作る」「スタッフ追加」「hire」「recruit」「team member」
-
xuiltul Skill Newstaff 3AnimaWorks 조직에 새로운 Digital Anima를 고용 및 생성하는 스킬. 인터뷰를 기반으로 캐릭터 시트(Markdown)를 작성한 후 CLI 명령어 (animaworks anima create)로 identity/injection/permissions 등을 일괄 생성합니다. 생성 후 bootstrap으로 자체 설정합니다. "새 직원 만들기", "사람 고용", "신규 직원", "고용", "Anima 생성", "채용"
-
idwong Bundle Pm Operation Manual用于生成、撰写或创建操作手册或用户指南的技能。 触发场景:(1) "生成操作手册" "写操作手册" "创建操作手册" "用户手册", (2) "使用说明" "功能说明文档" "快速入门" "用户指南", (3) "导出操作手册" "操作手册导出Word" "用户手册转Word", (4) 生成系统管理员操作手册, (5) 生成终端用户手册或快速入门指南。 基于需求文档和现有前端页面生成操作手册。
-
leeyudok Skill Docs Sync 2Bring documentation back in line with the code after changes to behavior, paths, versions, or generated output. Use on "update the docs", "refresh the README", "docs are stale", and right before opening a PR that changed any of those. Checks each documented claim against the actual code, command output, or official docs, and updates the parallel-language files together.
-
idwong Bundle Feasibility Report生成应用系统类项目可行性研究报告(可研报告)的技能。 触发场景:(1) "写可研报告" "生成可行性研究报告" "做可研" "项目可行性分析", (2) "写项目方案" "生成项目建设方案" "项目立项报告" "项目申请报告", (3) "可行性研究" "项目论证" "项目可研" "立项可研", (4) "导出可研报告" "可研报告导出Word" "可研报告转Word", (5) 用户提供项目背景、建设目标、功能需求,需要输出正式的可研报告文档时触发。 支持生成完整可研报告、分章节生成、导出 Word 格式。
-
byenzyme Bundle EnzymeUse Enzyme in an already activated Obsidian, Markdown, or Hermes workspace for working-memory retrieval, source-grounded exploration, semantic search by concept rather than keyword, runtime note-writing, and refresh. If the workspace is not initialized, follow the first-time setup section before normal retrieval.
-
bo55like69 Bundle Lab Report Workflow理工科实验报告生成全流程工作流。当用户要写实验报告/实验预习报告/数据处理报告,或给出实验主题与原始数据要求产出报告时触发。覆盖预习→原始数据→处理计算→图表→讨论→结论→排版七阶段,含占位符参数、五处关键节点确认机制、docx 交付规范与自查清单。
-
pavelsozonov Bundle Tip SlidesUse when the user wants a Claude Code tip presented as slides or visually — "/tip-slides", "tip of the day as slides", "show me a tip visually", "make slides for tip
-
mingdui Bundle QA Test Runner在 spec-task 和测试脚本就绪后,逐条执行、分类失败、修最小根因、收集证据、跑 completion 门禁。 你只负责"跑"——不生成报告、不审查代码、不判 Ready。审查留给 qa-code-reviewer,报告与判定留给 qa-report-generator。 不适用:报告生成、代码审查、用例设计。
-
mingdui Bundle QA Code ReviewerQA 流程倒数第二步的独立审查环节。在 qa-test-runner 执行完成后,以独立视角审查代码本身——检查架构、安全、并发正确性、数据一致性、 回归风险、测试覆盖缺口——不受执行方结论的影响。产出 code-review.json(含 severity 分级发现和 readiness 约束), 和 assert-code-review 门禁一起构成代码审查证据,交给 qa-report-generator 汇入最终报告。P0/P1 安全问题、资金逻辑缺陷、权限漏洞、数据不一致风险标记为 blocking。 不适用:生成用例、执行测试、修改产品代码(除非用户明确要求)、报告生成。
-
pascalorg Bundle Furniture Fit 2Assess whether furniture fits in a measured Pascal room or layout. Use this skill for sofa, table, bed, cabinet, appliance, staging, placement, collision, clearance, or rotated-footprint questions. Produce a tool-backed spatial report that distinguishes footprint fit from unsupported height, door-swing, assembly, and delivery-route claims, and return insufficient evidence when dimensions or scale are missing.
-
cbenjamin23 Bundle Moos Ivp DocsConsult MIT MOOS-IvP PDFs and local ivp/src for documentation-backed answers about apps, behaviors, parameters, concepts, upstream semantics, or doc-vs-source differences.
-
collinthefarmer Skill Skill FeedbackUse this skill when the user wants to give feedback on a skill, report a skill issue, suggest a skill improvement, or invokes '/skill-feedback'. Captures structured feedback on an existing skill and writes it to the skill's design or orders directory.
-
gloomyweather Bundle LinguisticsUse when working with academic linguistics: phonetics/phonology and IPA transcription (Russian, English, French), morphosyntax with interlinear glossing, corpus analysis (RNC, COCA/BNC, French corpora), historical linguistics and reconstruction, language comparison, parsing sentences or word forms. Also suitable for planning French learning from scratch and preparing teaching materials in linguistics.
-
stbenjam Skill Automatic 2Use when reviewing a test report to summarize failures requiring investigation.
-
padosoft Bundle Padosoft Docs Match CodeUse this skill when writing or reviewing documentation that quotes the code — a README, a CLAUDE.md or AGENTS.md, a SKILL.md, an ADR, an onboarding guide, an API doc — and whenever the user reports that a documented command, column, env var or flag does not exist, that setup instructions fail on a clean machine, that the docs describe an older behaviour, or asks to document a feature. It checks the quoted facts against migrations, models, config, command signatures and routes, and prefers a generated or pointed-to source over a copied snippet. Do not use it for writing style, for choosing a docs platform, or for translating existing documentation.
-
padosoft Bundle Padosoft Query PerformanceUse this skill when writing or reviewing code that reads or writes the database in volume — a listing, an export, a report, a cron or queued job that walks a table, a recalculation of a denormalised table, an endpoint that got slow as the data grew. Also when the user reports N+1 queries, a job exhausting memory, a paginated page that gets slower the deeper it goes, a timeout on a large table, or asks how to process a few hundred thousand rows. It covers access patterns, the volume thresholds that change the technique, keyset pagination, existence checks, and recalculating without leaving a window of emptiness. Do not use it for index and table design (padosoft-database-design) or for tuning the server itself.
-
stbenjam Skill Skillsaw IssueUse when skillsaw reports a likely false positive, misses an edge case, behaves incorrectly, or needs an RFE. Gather a safe report and, only with explicit user permission, create a feedback bundle or open a GitHub issue.
-
stbenjam Bundle Skillsaw UpdateUpdate a repository to the newest skillsaw — upgrade the install, report new rules and their findings in your repo, and bump version pins (GitHub Action SHAs, Makefile targets, pre-commit hooks). Use when a new skillsaw release is out and you want its latest checks.
-
stbenjam Skill Skillsaw Ecosystem ScoutSurvey the AI coding assistant and agentic tool ecosystem, assess skillsaw's competitive position, identify emerging patterns and missing capabilities, and produce a prioritized strategic report as a GitHub issue. Use when evaluating ecosystem trends and product gaps.
-
stbenjam Skill Weather ReportRetrieve local weather observations when the user asks for a weather report.
-
stbenjam Bundle Report BuilderBuild weekly status reports from git history and issue tracker exports. Use when preparing a status report.
-
wncfht Bundle Report DownloadUse when the user asks to download A-share or Hong Kong listed company financial report PDFs, including 年报/中报/一季报/三季报, annual report, interim report, or when a stock-analysis workflow needs the latest full-year report PDF.
-
wncfht Bundle Paper Note SkillPull an arXiv LaTeX source paper into the default paper workspace, inject bilingual annotation support into the original LaTeX project, and produce a single bilingual PDF where each English sentence is followed by its Chinese translation, with optional function-block pnotes and default tcolorbox summaries. Use when the user asks for an annotated paper source workflow rather than a rewritten summary.
-
coorasse Bundle Wine IdentifierIdentify a wine from a photo of its label (front, back, or capsule) or from a name and vintage, then research it on the web and report verified facts only: the producer (with official website), the wine itself (grapes, region, appellation, style, ageing), tasting notes, when to drink it, food pairings, the characteristics of that specific vintage when they are documented, and the current bottle price on the European market in EUR with source links. Use this skill whenever the user shares a picture of a bottle or a wine label, names a wine (even misspelled or partial, e.g. "Tignanello 2019", "that Barolo from Conterno"), asks what a wine is, what it costs, what to pair it with, whether a vintage is good, or asks for help choosing at a restaurant, wine shop, or supermarket. It also fits when the user only sends a photo with no text. Never answer from memory alone: the skill exists so that every fact and price comes from a live web search.
-
stbenjam Skill Current LogRead the tidal current log for the approach channel and report the slack-water windows. Use when planning a tow through the channel.
-
stbenjam Skill Incident HandoffSummarize open incidents from the pager rotation and produce a morning handoff report. Use when the user asks for an incident summary, a handoff report, or the current pager status. Includes links to each incident, the owning team, current severity, and the latest status update for every open incident.
Frequently asked questions
What are Docs & Writing agent skills?
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
Which Docs & Writing skills are most installed?
Popular Docs & Writing skills on SkillMD right now include image-posting, skill-creator, docx-formatter. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Docs & Writing skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.