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.
-
serialexperimentslainnnn Skill Knowledge Management StandardsDocumentation as infrastructure with a maintenance cost, for human readers. Use when deciding what to document and what to delete, applying the Diataxis framework (tutorial, how-to guide, reference, explanation) and splitting a document that mixes them, running docs-as-code with docs/ in the repository reviewed in the PR and built in CI, adding a broken-link gate with lychee or a prose linter with Vale, choosing or migrating a documentation stack (MkDocs Material, Docusaurus, Sphinx, Antora, Read the Docs, BookStack, Wiki.js, Outline, Confluence, Notion) and checking its licence and per-user price, generating reference from the source of truth (OpenAPI, JSON Schema, CLI --help, database schema) instead of writing it by hand, writing a README, a runbook nobody has executed, a design document, an onboarding guide or a postmortem write-up, setting a per-document owner and review-by date and deleting stale pages, fixing discoverability and search when three wikis exist, measuring bus factor and turning one person
-
gitzhiqing Bundle Deep Research先校准问题、再消耗调研资源的深度调研 skill,产出 research/<主题>-<日期>/ 目录下 REPORT.md(调研报告)+ REFERENCES.md(素材登记簿)双文件。 当用户提出需要联网多源交叉验证的调研需求时使用:触发词包括"帮我调研""深入研究" "全面了解""对比分析""查清楚…的现状""research""deep research"等,或问题术语 有歧义、领域冷门、表述模糊时主动使用。调研开始前先检查环境可用的 web_search / web_fetch 工具;无论问题多明确,调研理解与档位都须经用户确认后才执行。当用户 只需一次搜索可答的单点查询、或明确要求不联网时,不要使用本 skill。
-
iambedant Skill TeachUse this skill when the user wants to learn a codebase interactively in a Socratic, teacher-student style. Trigger phrases: "teach me this codebase", "walk me through the code", "explain how this works step by step", "I want to understand this project", "give me a code tour", "/teach". Conducts a back-and-forth session: one concept at a time, waits for user confirmation before advancing, handles tangential questions as clean named detours, tracks a breadcrumb of progress throughout, and writes a learning-notes markdown document at the end. Works on any language or project type.
-
shine8592 Bundle Duduppt主人说'做个PPT'时用这个技能。把文档/数据/想法转成咨询风格高密度PPTX。三阶段:证据分析→视觉蓝图→PPTX生成+QA。GitHub: github.com/Shine8592/duduppt。
-
geekplux Skill MarkvisUse when the user wants a chart of numbers in Markdown (bar, line, area, scatter, pie, hist) from a table — emit a Markdown code block tagged chart|markvis|vis, never a flowchart pie/xychart, never a PNG, never Vega-Lite JSON as the default.
-
mrudisill26 Bundle Arcade Booth GenerateUse when turning a finished source-content scene file into a generated Arcade video. Triggers on requests to build the booth video for a subtopic, generate a video from a source-content markdown file, or produce the trade show loop for a product subtopic.
-
mrudisill26 Bundle Arcade Source ContentUse when turning raw product material, a list of subtopics, and a list of demos into per-subtopic scene files for an Arcade video or slide deck. Triggers on requests to build deck source content, fill the scene template per subtopic, or prepare a product story for Arcade handoff.
-
ono-sendai-labs Skill Codebase SummaryAnalyze a codebase and generate structured documentation describing system architecture, components, interfaces, and workflows. Use when the user wants to document, summarize, or understand a codebase's architecture, or generate a knowledge base for AI assistants to reference during development tasks.
-
yjhqwer Skill Prior Art SearchMandatory pre-implementation research skill. Search GitHub, official documentation, package registries, and existing battle-tested implementations before writing new features, rules files, skills, or architecture. Enforces the Adopt-Extend-Compose-Build hierarchy and delegates heavy search loops to subagents to prevent main-thread context bloat. Use before any non-trivial feature, skill, config, or library choice — and whenever an existing approach fails or survives only on a workaround and 'keep the status quo' is tempting — not for bug fixes, refactors, or mechanical changes.
-
kascote Skill DmetricsHow to run dmetrics and read its reports. Use when running dmetrics, reading a dmetrics report, deciding what to do about a cyclomatic, cognitive or coupling warning, or refactoring a scope to lower a warning.
-
emran05 Skill CanvasCanvas LMS coursework — plan the day around what is due, check deadlines, sync course materials, or answer questions from lecture notes and assignment descriptions. Use when the user runs /canvas, or says "what's due", "what do I have due this week", "plan my day around canvas", "sync canvas", "what did my professor post", "what's on the midterm", or asks about an assignment, syllabus, module or slide deck by name.
-
ciberjohn Bundle Technical TrainerFull lifecycle technical course creation — AI and Linux courses in English (UK), European Portuguese (PT), and Brazilian Portuguese (BR). Orchestrates market research, fact-checking, technical writing, and trilingual translation via parallel sub-agents. Produces curriculum plans, video scripts, lab exercises, assessments, and B2B pricing packages — all saved to a GitHub repository.
-
finalferrin Skill No Legal Waiver WallpaperUse before writing anything that will be read outside this chat — a document, report, memo, deck, PR description, commit message, README, code comment, email, or any file handed to another person — and again before calling it finished. Not for replies in chat.
-
vaibtan Bundle SwarmFan out independent slices, races, or coverage checks to Codex subagents and aggregate one evidence-backed report. Use for $swarm or explicitly parallel work.
-
xjli360 Bundle Sealeap Taotie Amazon Search Term Report Tiered ReviewReview the Sponsored Products search term report by tier—impressions, clicks, CTR, orders and conversion per customer search term—separating searched terms from targeted keywords and ASIN entries, then produce a keyword-promotion list, a negative-keyword list and a listing-fix list gated by evidence. Use for 搜索词报告怎么看、客户搜索词和关键词区别、B0 开头是什么、哪些词加否定、否定短语和否定精确怎么选、自动广告的词怎么迁到手动、有点击没转化怎么办. Do not use to push negatives or bid changes to live campaigns without an approved change table.
-
xjli360 Bundle Sealeap Tianlu Amazon Data Reporting Filing Evidence CollectHelp a seller decide and execute a response after a marketplace begins sharing seller sales data with tax authorities: verify reporting-scope applicability, collect sales and deductible-cost evidence from backend report channels, document a comply-now-or-wait decision with a review trigger, and check payout-account compliance. Does not determine final tax liability or endorse entity-switching as a workaround. Use for 平台数据报送后报税应对决策、抵扣凭证归集、收款账户合规核对. Do not use to decide final tax liability, and do not use to justify switching business entities to avoid reporting.
-
professor-gpt Bundle Technical WriterProfessional technical documentation specialist that creates API references, READMEs, architecture docs, and developer guides.
-
geraltvitas Bundle Patent Flowchart GenerationGenerate compliant patent flowchart images (A4@300DPI, black/white, no color) and assemble them into a WPS-compatible PPTX. Maps code logic into structured 2xN or 3xN grid flowcharts with precise arrows, bounded text, and formal layout.
-
rmazrim Skill Ast Anti Pattern SlayerParses Python or JavaScript-style source into an AST, computes cyclomatic complexity v(G) as decision count plus one, maximum block nesting depth, bare except clauses and unreachable dead code, then uses a conservative ast.NodeTransformer to rewrite trailing if/else wrappers into semantics-preserving early return and continue guard clauses, emitting a structured JSON diagnostics report with file line and column locations.
-
michaelwjohnson Skill Check ClaimsUse before sending, submitting, or publishing anything containing factual claims — a proposal, report, spec, README, analysis, review, or answer to a question. Catches statements that are fluent and wrong: numbers whose source nobody can name, thresholds attached to the wrong metric, facts that are true of a neighbouring concept, and figures that lost their referent when something was edited. Triggered by: finishing a document, "is this right", stating a baseline or floor or threshold, quoting a number, explaining a metric, any claim a reader would take on trust.
-
michaelwjohnson Skill Writing ReviewUse before sending prose that has to persuade, explain, or be acted on — a report, proposal, email, summary, design doc, or manuscript section. Checks whether the argument holds and whether the sentences carry it: an unstated point, sections in an order nobody can follow, generalizations with no evidence under them, abstraction where a concrete noun belongs, and clutter that survived the first draft. Triggered by: finishing a draft, "does this read well", "can you review this writing", sending something to a reader who can stop reading.
-
geraltvitas Bundle Academic Report PptUse when building a 导师汇报/答辩 PPT from locked evidence.
-
faroxdev Skill Vault ReadRetrieve reliable information from a long-term Markdown Vault without modifying it. Use for questions that require finding current facts, configuration, project state, or relevant history in the Vault.
-
tiennguyen1203 Skill San Do ReGenerate a TikTok Photo Mode carousel plan for the "Săn Đồ Rẻ" affiliate channel (Vietnamese home-goods / cheap finds). Given a product, produces per-slide Google Flow image-generation prompts (9:16), overlay text, hook variants, caption, and hashtags. Use when the user wants to create a photo-mode post, "gen ảnh", make a Săn Đồ Rẻ slide carousel, or plan TikTok affiliate content.
-
faroxdev Skill Vault MaintainMaintain a long-term Markdown Vault as a concise, current, human-readable source of truth. Use for persistent note creation, correction, consolidation, or other authorized content changes.
-
rmazrim Skill Performance Budget BouncerEnforce performance budgets in CI and reject pull requests that exceed size, weight, or timing thresholds with a machine-readable flagging report.
-
rmazrim Skill Flaky Test JuryAnalyze repeated CI test logs, classify flaky tests by root-cause category, and emit stabilization patches plus a verdict report before they erode team trust.
-
rmazrim Skill Pr Logic ReviewerReview a pull-request diff for logic bugs — boundary conditions, null safety, state and edge semantics — not style, and emit a bug-first review report.
-
johnson68878-ops Bundle KicadAnalyze KiCad projects and PDF schematics: schematics, PCB layouts, Gerbers, footprints, symbols, netlists, and design rules. Reviews designs for bugs, traces nets, cross-references schematic to PCB, extracts BOM data, checks DRC/ERC, DFM, power trees, and regulator circuits. Every finding carries a confidence label and evidence source with trust_summary rollup. Analyzes PDF schematics from dev boards, reference designs, eval kits, and datasheets. Supports KiCad 5–10. Use whenever the user mentions .kicad_sch, .kicad_pcb, .kicad_pro, PCB design review, schematic analysis, PDF schematics, reference designs, Gerber files, DRC/ERC, netlist issues, BOM extraction, signal tracing, power budget, DFM, or wants to understand, debug, compare, or review any hardware design. Also for "check my board", "review before fab", "what's wrong with my schematic", "is this ready to order", "check my power supply", "verify this circuit", OSHWA certification readiness, or any electronics/PCB design question.
-
johnson68878-ops Bundle SpiceRun automatic SPICE simulations on subcircuits detected from KiCad schematic analysis — validates filter frequencies, divider ratios, opamp gains, LC resonance, and crystal load capacitance. Supports ngspice, LTspice, and Xyce (auto-detected). Generates testbenches, runs batch mode, produces structured pass/warn/fail report. Use when the user asks to simulate, verify, or validate any analog subcircuit — RC filters, LC filters, voltage dividers, opamp circuits, crystal oscillators. Also for "simulate my circuit", "run spice", "verify with simulation", "check my filter cutoff", "does this divider give the right voltage", "what's the bandwidth of this opamp stage". Consider suggesting simulation during design reviews when the schematic analyzer reports simulatable subcircuits and a SPICE simulator is available.
-
rmazrim Skill Openapi Spec WriterExtract backend API code into OpenAPI/Swagger 3.0 documentation.
-
johnson68878-ops Bundle Pfmea ProcessBuild a PFMEA worksheet, process risk analysis, or AP table using the AIAG-VDA FMEA Handbook 2019 7-step approach. Covers Structure Analysis, Function Analysis, Failure Analysis, Risk Analysis (Action Priority H/M/L), Optimization, and Documentation. Required by IATF 16949 and OEM customer-specific requirements for new processes, process changes, and post-escape PFMEA updates.
-
shivani26singh Skill Pw Multi Tab HandlerWrites race-free Playwright code for any flow that opens a second tab, popup, or window — target="_blank" links, "open in new window" buttons, OAuth/SSO consent screens, payment redirects, and PDF preview tabs. Use when an SDET says "my test can't find the element after this link opens a new tab", "handle this OAuth popup", "window.open breaks my test", or a test needs to manage several open tabs at once. Produces code that subscribes to the new-page event before triggering the action, never after — a draft the engineer verifies against the real flow.
-
senih25 Bundle New AssignmentCreate a new programming homework assignment for Mergington High School students. Use this skill whenever the user wants to create, add, scaffold, or generate a new assignment, exercise, or homework — even if they don't use the word "assignment" explicitly.
-
johnson68878-ops Bundle EmcEMC pre-compliance risk analysis for KiCad PCB designs — 18 check categories, 44 rule IDs covering ground planes, decoupling, I/O filtering, switching harmonics, clock routing, differential pair skew, board edge radiation, PDN impedance, return paths, crosstalk, ESD protection, shielding, and magnetic leakage from switching inductors. Produces severity-ranked risk report with pre-compliance test plan. Supports FCC Part 15, CISPR 32, CISPR 25 (automotive), MIL-STD-461G. SPICE-enhanced when available. Use when the user asks about EMC, EMI, radiated/conducted emissions, FCC compliance, CE marking, CISPR, ground plane issues, decoupling strategy, clock routing EMC, switching noise, differential pair skew, or whether their board will pass EMC testing. Also for "will this pass FCC?", "check my EMC", "is my ground plane okay?", "check my decoupling", or "generate an EMC test plan".
-
jawahars07 Bundle Cv TailorBuild a tailored one-page LaTeX CV and matching cover letter from a job description, compile them with tectonic, and verify the PDF the way an ATS parser reads it. Use for any resume, CV, cover letter, LaTeX, or ATS document request. Never fabricates a fact that is not in the facts file.
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 knowledge-management-standards, deep-research, teach. 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.