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.
-
garyld1962 Skill Code Investigation OrchestratorRun a cross-repository code investigation from a natural-language request or explicit pattern list and produce a versioned Markdown index.
-
hmbown Skill ArcanaIn D&D, Arcana is knowledge of magic, its traditions, symbols, and mechanisms. The real-world version is deep technical literacy: understanding how software architectures work, what protocols do at the wire level, how APIs behave beyond their documentation, and what the actual mechanisms are behind the abstractions everyone else takes on faith.
-
hmbown Skill ShatterShatter is proactive, controlled destruction for learning. You are the attacker against your own system. The goal is a brittleness report with remediation priorities.
-
hmbown Skill EnthrallEnthrall makes an audience hang on every word. The real-world version is structural engagement: opening hooks that stop the scroll, narrative arcs that sustain attention, and pacing that makes people stay until the end. This is presentation design, content structure, and the craft of making something worth finishing.
-
hmbown Skill Magic MouthMagic Mouth is trigger → message. The entire craft is specifying the trigger boundary, the message payload, and the suppression/escalation rules. It is NOT: - One-time messages: "Send a Slack message now saying X" (no trigger, no automation) - Full chatbots: "Build a conversational AI that understands context and handles open-ended questions" (requires NLU, dialogue management) - Monitoring dashboards: "Set up Grafana with real-time graphs and trend analysis" (visualization, not message routing) - Silent traps/wards: "Revert changes silently and log who tried" (defensive code manipulation, not messaging) - Encryption: "Encrypt a message so only the recipient can read it" (cryptography, not event-driven delivery) - Multimedia presentations: "Play a 20-slide deck with animations and narration" (media playback, not conditional messaging)
-
hmbown Skill Healing WordIn D&D, Healing Word heals at range with a bonus action — fast, remote, and efficient but less powerful than Cure Wounds. The real-world version is the remote quick fix: a one-liner command, a config change pushed through a dashboard, a quick Slack instruction to the person on-call, or an automated rollback trigger. You do not need to be deep in the system to apply this fix.
-
hmbown Skill Power Word KillIn D&D, Power Word Kill instantly destroys any creature below a hit-point threshold — no saving throw, no resistance, just death. The real-world version is kill -9: the unconditional termination signal. Emergency circuit breakers. Hard account terminations. The nuclear option that exists because sometimes graceful shutdown is not available and the cost of continuing is worse than the cost of data loss. Power Word Kill is not elegant. It is not kind. It is the thing you reach for when everything else has already failed.
-
hmbown Skill Power Word StunIn D&D, Power Word Stun locks a creature in place — alive but unable to act. The real-world version is SIGSTOP: a hard freeze that preserves state but halts all activity. Account lockouts, emergency process suspension, administrative holds. Unlike Power Word Kill, the target can be unfrozen. The spell is for situations where something must stop right now but destruction is not warranted — you need the process alive for investigation, for later resumption, or because killing it would cause worse problems than freezing it.
-
hmbown Skill Vicious MockeryThe bard's cantrip that deals psychic damage through insults. In practice this is adversarial review — the art of finding and articulating exactly what is wrong with something in a way that is impossible to ignore. Unlike polite feedback that gets filed and forgotten, vicious mockery lands. It is the red-team report that makes the PM cancel the launch, the code review that makes the author delete the PR, the roast that makes the founder pivot. The damage is the point.
-
shengdabai Bundle QASystematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack) Voice triggers (speech-to-text aliases): "quality check", "test the app", "run QA".
-
shengdabai Bundle QA OnlyReport-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes. (gstack) Voice triggers (speech-to-text aliases): "bug report", "just check for bugs".
-
shengdabai Bundle Lark Doc飞书云文档 / Docx / 知识库 Wiki 文档(v2):创建、打开、读取、获取、查看、总结、整理、改写、翻译、审阅和编辑飞书文档内容。当用户给出飞书文档 URL/token,或说查看/读取/打开某个文档、提取文档内容、总结文档、生成/创建文档、追加/替换/删除/移动内容、调整排版、插入或下载文档图片/附件/素材/画板缩略图时使用。文档内容中出现嵌入电子表格、多维表格、需要将重要信息可视化为画板(含 SVG 画板)、引用或同步块时,也先用本 skill 读取和提取 token,再切到对应 skill 下钻。使用本 skill 时,docs +create、docs +fetch、docs +update 必须携带 --api-version v2;默认使用 DocxXML,也支持 Markdown。
-
shengdabai Skill TestingSkill validation framework PLUS daily test-suite health and regression intelligence. Validates skill conformance (frontmatter, manifest coverage, resolver coverage). Runs the project test suite in tiered phases (unit / evals / integration / system health), classifies failures, and produces a regression-aware report.
-
shengdabai Bundle Make PDFTurn any markdown file into a publication-quality PDF. Proper 1in margins, intelligent page breaks, page numbers, cover pages, running headers, curly quotes and em dashes, clickable TOC, diagonal DRAFT watermark. Not a draft artifact — a finished artifact. Use when asked to "make a PDF", "export to PDF", "turn this markdown into a PDF", or "generate a document". (gstack) Voice triggers (speech-to-text aliases): "make this a pdf", "make it a pdf", "export to pdf", "turn this into a pdf", "turn this markdown into a pdf", "generate a pdf", "make a pdf from", "pdf this markdown".
-
delorenj Skill Gsd Docs UpdateGenerate or update project documentation verified against the codebase
1 -
delorenj Skill Gsd Ingest DocsScan a repo for mixed ADRs, PRDs, SPECs, and DOCs and bootstrap or merge the full .planning/ setup from them. Classifies each doc in parallel, synthesizes a consolidated context with a conflicts report, and routes to new-project or merge-milestone depending on whether .planning/ already exists.
1 -
delorenj Skill Gsd Session ReportGenerate a session report with token usage estimates, work summary, and outcomes
1 -
vibeeval Skill Nia DocsSearch library documentation and code examples via Nia
-
vibeeval Skill Plan DocumentationStructured plan file generation for large tasks -- phased planning, completion tracking, and decision documentation
-
vibeeval Skill Developer RelationsDeveloper relations - community building, documentation, DevRel metrics.
-
vibeeval Skill Persistent PlanningPersistent planning system with 3 markdown files (PLAN.md, PROGRESS.md, CONTEXT.md). Use when starting large features, multi-session work, or complex refactoring. Auto-tracks commits in PROGRESS.md.
-
ftshare-lab Bundle Limit Up Public Report查询涨停对外归因报告。接口:GET /api/v3/market/data/limit-up-reports/public-report。所有请求必须设置 FTSHARE_API_KEY。
-
ftshare-lab Bundle Report Announcement List按公告日期分页查询报告公告列表,可选按证券代码过滤。用户提到「报告公告列表」「公告列表」「某日公告」「report announcement list」时使用。返回公告标题/附件信息/处理状态和公告 ID;公告 ID 可用于查询公告摘要。分页返回,page_size 最大 200,支持 --all 翻页。
-
ftshare-lab Bundle Report Announcement Summary根据公告 ID 查询单条报告公告的摘要、标题、证券信息和处理状态。用户提到「报告公告摘要」「公告摘要」「单条公告详情」「report announcement summary」时使用。未找到公告时 data 为 null、code 为 404。
-
ascend-ai-coding Skill External Mindstudio Github Raw Fetch当用户提供 GitHub 文件页面链接,或希望读取某个仓库中的源码、配置、README、Markdown、docs 内容时,使用此技能。技能不仅支持将 `github.com/<owner>/<repo>/blob/<ref>/...` 转换为 `raw.githubusercontent.com` 链接,还要求在读取仓库 docs 前优先读取同仓库同 ref 的 `agent_router.md`,根据其中声明的目录结构或路由规则拼出真实路径,并优先通过 `curl` 获取内容。
Audited -
ferroxlabs Skill Financial Wellness ScorecardHolistic financial health evaluation covering income stability, savings adequacy, debt management, insurance coverage, and retirement preparedness. Produces a scored wellness report with prioritized action steps for financial improvement. Use when the user asks about financial wellness scorecard, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of financial wellness scorecard or requires a different specialized skill.
Audited 37 -
williamcorrea23 Bundle Sap Report Automation WorkflowEnd-to-end SAP ABAP 开发对象自动化——通过 node-rfc 直连 SADT_REST_RFC_ENDPOINT 调用 RFC ADT API。支持 REPORT/CLAS/FUGR/INTF/Include 全部对象类型。FS 规范化→DDIC 元数据→技术文档→按模板写 ABAP→激活循环。所有 SAP 操作统一走 `scripts/rfc_client.js`(查询)和 `scripts/deploy_rfc.js`(部署)。语法速查 [abap-syntax-quickref.md](abap-syntax-quickref.md),卡点速查 [troubleshooting.md](troubleshooting.md)。
-
davidcastagnetoa Bundle PDF Form FillRellena formularios PDF oficiales (TA.2/S, Modelo 145, Carta de Baja) usando pdf-lib. Usar para completar la generacion de documentos oficiales espanoles.
-
ascend-ai-coding Bundle External Gitcode Ascend Npu Adapter ReviewerGPU代码到昇腾NPU适配审查专家。当用户需要将GPU上的代码(特别是深度学习、模型推理相关)迁移到华为昇腾NPU时,必须使用此skill进行全面审查。此skill能识别GPU到NPU迁移的堵点、编写适配脚本、生成验证方案,并输出完整的Markdown审查报告。触发场景包括:用户提到"NPU适配"、"昇腾迁移"、"GPU转NPU"、"Ascend"、"CANN"、"模型迁移"、"算子适配"等关键词,或者用户要求对GPU代码仓库进行审查并迁移到NPU平台。
-
ascend-ai-coding Bundle External Gitcode Ascend Triton Operator Doc Gen为昇腾 NPU Triton 算子生成标准化接口文档。当用户需要为算子创建 README、生成 API 文档、编写产品支持表、整理参数说明时使用。关键词:文档生成、doc generation、README、接口文档、API documentation。
-
ascend-ai-coding Bundle External Gitcode Ascend Megatron Migration GeneratorGenerate migration deliverables for bringing relevant Megatron changes into MindSpeed after branch alignment and impact mapping are complete. Use when Codex already has a confirmed MindSpeed-to-Megatron branch pairing and needs to produce a migration report, candidate patch, or guarded workspace edits instead of redoing upstream analysis from scratch.
-
ferroxlabs Skill SupportEntry point for customer support work: reads what the request actually is — one reply, a pattern across tickets, an escalation, a refund, a queue review — and either routes to the specialist skill or runs the procedure inline. Covers reply drafting, knowledge-base articles, FAQ generation, escalation briefs, refund and credit scripts, SLA and queue review, NPS and CSAT analysis, and the support health report. Use when a support task arrives without a shape yet. Do NOT use when the shape is already known — go straight to mend-ticket-triage for prioritising a queue, mend-churn-prevention for a save play on an at-risk account, or mend-onboarding-flow for the first-thirty-days path — and do NOT use it to write policy (use sop-creation) or to redesign the process itself (use process-mapping). Support templates can create binding commitments: check refund and SLA language against actual policy and applicable consumer law before it is sent.
Audited 37 -
ferroxlabs Skill Onboarding PlanCreates a 30-60-90 day onboarding plan with milestones, activities, check-in schedules, and success criteria for new employee integration. Use when the user asks about onboarding plans, new hire orientation, 30-60-90 day plans, or employee ramp-up programs. Do NOT use for job descriptions (use job-description), training curriculum design (use lesson-plan), or project onboarding documentation.
Audited 37 -
ferroxlabs Skill Line EditorProse-level editing methodology covering sentence rhythm, word choice, show-don't-tell diagnosis and fixes, dialogue tag optimization, filtering word elimination, passive voice correction, prose tightening, and style sheet creation. Use when the user asks about line editor or needs help with related topics. Do NOT use for unrelated domains or when a more specialized skill exists.
Audited 37 -
ferroxlabs Skill Finance Sales TaxTrack post-Wayfair economic nexus state by state, handle marketplace-facilitator law, build the multi-state registration and filing checklist, manage exemption certificates, and resolve tax-on-shipping rules, ending in a state-by-state exposure report. Use when the user sells across state lines and does not know where they are now required to register. Do NOT use for payroll or income tax (use finance-payroll-prep) or for R&D credits (use finance-r-and-d-credit). Analysis only — registration and voluntary-disclosure decisions belong with a state and local tax professional.
Audited 37 -
ferroxlabs Skill Pitch Deck CreatorInvestor pitch deck design and content creation using Sequoia format, Guy Kawasaki 10/20/30 rule, slide-by-slide storytelling, and investor Q&A preparation. Use when the user asks about pitch deck creator or needs help with related topics. Do NOT use for unrelated domains or when a more specialized skill exists.
Audited 37
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 code-investigation-orchestrator, arcana, shatter. 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.