agentsclimarketplace

Docs & writing

16,614 rows, by stacks then stars

3,030 of these skill files have been read, by 1,951 distinct authors, and what they tell an agent counted. What Docs & writing authors agree on, and what they forbid

  • Write technical prd

    rvdsmaile/working-backwards/.agents/skills/write-technical-prd Skill

    no license0★ repo

    Write a repository-aware technical PRD from an approved Working Backwards handoff and technical grill. Use after target-repository discovery and technical design approval, before implementation planning or issue slicing.

  • Marineconnect qc reporting

    Marineconnect/marineconnect-agent-skills/plugins/marineconnect-ops/skills/marineconnect-qc-reporting Skill

    no license0★ repo

    Create MarineConnect MCP QC evidence reports. Use when the user asks to QC tools, show prompt/tool/params/output, verify end-to-end agent behavior, run read-only smoke checks, compare expected vs actual tool routing, produce checklist evidence, or avoid blind QC for MarineConnect MCP and operations skills.

  • Write focused tests

    swd3k/skills/agent-skills/programming/write-focused-tests Skill

    0★ repo

    Write high-value unit and integration tests without brittle UI snapshots. Use when adding coverage, fixing regressions, or deciding what not to test.

  • Product docs page

    swd3k/skills/agent-skills/web-design/product-docs-page Skill

    0★ repo

    Structure product documentation and README-style pages for clarity and scanability. Use when writing docs sites, GitHub README, or in-app help.

  • Write blackbox tests

    cleudice/kiro-ai-team/skills/write-blackbox-tests Skill

    0★ repo

    (Somente qa-blackbox) Escreve os testes de aceitação usando APENAS requirements.md e os contratos do design.md — proibido ler src/ e docs/context/. Use em paralelo à implementação, quando pedirem 'testes do PBI', 'testes de aceitação', 'cubra os critérios'.

  • Write design

    cleudice/kiro-ai-team/skills/write-design Skill

    0★ repo

    Gera .kiro/specs/<slug>/design.md — arquitetura da mudança, contratos públicos completos (base do teste black-box), decisões com alternativa descartada e raio de impacto. Use após requirements aprovado, ou quando pedirem 'design', 'arquitetura da mudança', 'defina os contratos/endpoints'.

  • Write requirements

    cleudice/kiro-ai-team/skills/write-requirements Skill

    0★ repo

    Gera .kiro/specs/<slug>/requirements.md — user stories com critérios EARS testáveis — a partir do brief, perguntando TODAS as ambiguidades antes de congelar. Use ao iniciar o trilho feature, ou quando pedirem 'requisitos', 'spec', 'user stories', 'critérios de aceitação', 'especifique a feature'.

  • Write tasks

    cleudice/kiro-ai-team/skills/write-tasks Skill

    0★ repo

    Gera .kiro/specs/<slug>/tasks.md — checklist executável com os gates G1–G5 embutidos no final. Trilho feature (do design) ou manutenção (mínimo, direto do brief). Use quando pedirem 'tasks', 'plano de implementação', 'quebre em tarefas', ou ao fechar a spec.

  • Present

    prateek11rai/tldraw-canvas-kit/skills/present Skill

    0★ repo

    Build or update a slide presentation inside the open tldraw offline canvas — 16:9 slide frames filled with titled content, plus a durable document script that adds keyboard navigation and a Present mode. Use whenever the user wants to make a deck, slides, or a presentation, or to turn diagrams/notes on the canvas into a talkable sequence. Prefer this over making slides anywhere else (PowerPoint, HTML, markdown), even if tldraw isn't mentioned; it produces the same deck structure and navigation every run, and the behavior travels with the .tldraw file.

  • Whitepaper

    prateek11rai/tldraw-canvas-kit/skills/whitepaper Skill

    0★ repo

    Draft or update a structured whitepaper / design doc / architecture write-up directly on the open tldraw offline canvas — as titled section frames with prose, laid out as a readable long-form document that can embed the canvas's diagrams. Use when the user asks to write a whitepaper, a design doc, an RFC/ADR-style write-up, or an architecture explainer on the canvas (not slides). Produces the same section skeleton and layout every run. When the user wants a maintained, visual design doc, prefer the canvas over a plain markdown file — even if tldraw isn't mentioned.

  • Apex spec

    lhbsaa/apex-discovery/skills/apex-spec Skill

    0★ repo

    Spec-driven development workflow. Propose features with specs, design docs, and tasks before writing code. Triggers on: /apex:spec, propose, write spec, design feature.

  • Clinical reports

    lhbsaa/apex-discovery/skills/clinical-reports Skill

    0★ repo

    Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools.

  • Docx

    lhbsaa/apex-discovery/skills/docx Skill

    0★ repo

    Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

    The same file is in 1 other repository

  • Markdown mermaid writing

    lhbsaa/apex-discovery/skills/markdown-mermaid-writing Skill

    0★ repo

    Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.

    The same file is in 3 other repositories

  • Peer review

    lhbsaa/apex-discovery/skills/peer-review Skill

    0★ repo

    Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.

  • Prd

    lhbsaa/apex-discovery/skills/prd Skill

    0★ repo

    Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

  • Scientific writing

    lhbsaa/apex-discovery/skills/scientific-writing Skill

    0★ repo

    Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

  • Statistical analysis

    lhbsaa/apex-discovery/skills/statistical-analysis Skill

    0★ repo

    Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required sample sizes, or write up results - even if they never name a specific test. Covers t-tests, ANOVA, chi-square, correlation, regression, non-parametric and Bayesian methods. For low-level model APIs, see the statsmodels and pymc skills.

    The same file is in 1 other repository

  • Writing plans

    lhbsaa/apex-discovery/skills/writing-plans Skill

    0★ repo

    Use when you have a spec or requirements for a multi-step task, before touching code

  • Writing skills

    lhbsaa/apex-discovery/skills/writing-skills Skill

    0★ repo

    Use when creating new skills, editing existing skills, or verifying skills work before deployment

  • What changed

    arsenstorm/skills/skills/what-changed Skill

    0★ repo

    After finishing a unit of work, produce a self-contained HTML before/after report — each change shown with its reasoning, and cropped screenshots for anything visual. Use when the user says "what changed", "/what-changed", "before/after report", "show me what changed", "write up the changes", or asks for a visual summary of work done.

  • Write reproducible demo

    jonathan-arteaga/agent-skills/.agents/skills/write-reproducible-demo Skill

    0★ repo

    Use when a repository needs a short demo path that another person can run, inspect, and verify without private data or hidden setup.

  • Root cause investigator

    artaasd95/SLM-skills/root-cause-investigator Skill

    0★ repo

    Find the exact root cause of a bug or error using a temporary investigation markdown file. Use when debugging, analyzing stack traces, logs, failing tests, or unexpected behavior. Do not use for feature planning or code writing.

  • Experiment reporting

    zl3311/alpha-mining/.cursor/skills/experiment-reporting Skill

    0★ repo

    End-of-session recording. Creates session files, updates knowledge base, creates/updates factor and book entries, and opens a PR. Trigger on: report, record, document, end session, wrap up, create PR.

  • Polish tyrant tech writing

    TyrantLucifer/awesome-skills/skills/polish-tyrant-tech-writing Skill

    0★ repo

    精修、润色、校正 TyrantLucifer 的中文技术文章,尤其适用于 Agent/LLM 生成的博客草稿、源码解析、架构分析、教程、开源项目体验和技术复盘。去除模板化 AI 腔,同时复现 tyrantlucifer.com 历史原创文章中稳定的个人表达:从真实问题或实践切入,跟随代码和现象逐步推演,穿插克制的第一人称判断与轻微吐槽,并诚实说明局限。保留并校验代码、命令、API、产品名、版本、数字、链接、引用和不确定性;也可仅审阅 AI 痕迹、技术表达和文风偏差而不改写。

  • Technical learning docs

    TyrantLucifer/awesome-skills/skills/technical-learning-docs Skill

    0★ repo

    Create Chinese technical learning documents that teach unfamiliar engineering/AI concepts progressively, especially when a user is preparing for a new technical domain and needs both a detailed guide and a plain-language primer.

  • Humanize writing

    Brennan-Lewis/writers_voice/skills/humanize-writing Skill

    0★ repo

    Revise prose so it sounds natural, specific, and appropriate to its writer while preserving meaning, facts, citations, formatting, and authorship. Use for humanizing, de-AI-ing, de-slopping, polishing, or auditing emails, posts, memos, documentation, reports, resumes, and other drafts for repetitive AI-style patterns.

  • Summarize ticket

    sorinLupaIonut/digital-fte/.claude/skills/summarize-ticket Skill

    no license0★ repo

    Turns one support ticket or thread into a five-section handoff note — Customer Context, Issue, Resolution Steps Taken, Current Status, Recommended Next Action — so a colleague can pick the case up cold. Use whenever someone needs to hand a case off, brief a lead, take over another agent's thread, catch up on where a case stands, or establish the current state before escalating, including phrasings that never say "summarize": "write a handoff note for #4471", "TL;DR this thread", "where does this stand before I escalate", "what's the story on 1042", "bring me up to speed on Sam's case". Do not use it for drafting a reply to the customer, for triaging or ranking a batch of tickets, or for reporting on ticket volume, trends, or metrics.

  • Technical content structure

    ProstDev/skills/plugins/content/skills/technical-content-structure Skill

    0★ repo

    Readability + structure for long-form technical content — blog posts, concept explainers, and capability overviews people actually finish reading. Use when drafting or revising a prose article that feels dense, or for a scannability/voice/structure pass: reader-first framing, text chunking, the inverted pyramid, headline patterns, intro/conclusion anatomy, and calibrating content depth to the reader (runnable specifics for developers, trade-offs and rationale for architects). For SEO/frontmatter facts see [[blog-seo-standards]]; for numbered walkthroughs [[tutorial-writing]].

  • Tutorial writing

    ProstDev/skills/plugins/content/skills/tutorial-writing Skill

    0★ repo

    How to write step-by-step technical tutorials and setup/how-to guides a reader can follow top-to-bottom and succeed on the FIRST try — UI-fidelity, dependency-ordered steps, front-loaded values, scope/permission tables, "verify it worked" checkpoints, and the accuracy discipline that keeps commands from going stale. Use when writing or revising a hands-on numbered walkthrough, getting-started guide, or install/config how-to. For prose explainers see [[technical-content-structure]]; for SEO/frontmatter [[blog-seo-standards]].

  • Context7

    martonpaulo/skills/context7 Skill

    0★ repo

    Fetch current documentation snippets and code examples for an indexed third-party library, framework, SDK, or CLI tool from the Context7 index, using the ctx7 command line tool. Use when implementation depends on a library's present API surface, configuration options, or usage patterns, training data may be stale, and a fast indexed lookup is enough. Defer Apple platform documentation to apple-docs. Escalate to deep-docs when the conclusion must be traced to an official versioned source, when the library is not indexed, or when compatibility, deprecation, or migration has to be proven. Do not use for the project's own code, general web research, product comparisons, build-versus-buy decisions, or managing skills from the Context7 registry.

  • Deep docs

    martonpaulo/skills/deep-docs Skill

    0★ repo

    Perform authoritative, version-aware documentation research for software, frameworks, SDKs, libraries, APIs, CLIs, databases, developer tools, and platforms used in the current task or project. Detect the exact product and installed version from project files or safe local commands, then search official versioned documentation, release notes, API specifications, official source repositories, local CLI manuals, and explicitly configured read-only documentation sources. Use when implementation correctness depends on precise behavior, version compatibility, availability, deprecation, configuration, migration, or documented constraints. Prefer primary sources and return source-linked evidence. Defer Apple development documentation to apple-docs. Do not use for general web research, product recommendations, build-versus-buy decisions, debugging without a documentation question, or broad architecture decisions.

  • Grill and document

    martonpaulo/skills/grill-and-document Skill

    0★ repo

    Start a focused one-question-at-a-time interview that also preserves resolved domain vocabulary and genuinely consequential architectural decisions without creating tickets or implementing the plan.

  • Setup agent docs

    martonpaulo/skills/setup-agent-docs Skill

    0★ repo

    Configure lightweight per-repository conventions for optional domain glossaries, ADRs, research notes, handoffs, and disposable prototypes. Use when the user directly requests these artifact paths or when setup-project delegates this step after establishing root guidance. Do not use for complete project setup, ordinary documentation edits, personal-skill configuration, trackers, tickets, labels, or backlog workflows.

  • Build readme

    gitt510/agent-skills/skills/build-readme Skill

    0★ repo

    Write a README from scratch or fully rebuild one. Collects observable facts from the system itself (code, terraform, actual behavior), composes sections from those facts, and writes one fact per bullet; decision rationale and internal how-it-works are left out. An existing README is broken down sentence by sentence and only facts verifiable against the implementation survive. Use when creating, rewriting, condensing, or restructuring a README. Not for a few added lines to an existing README — a normal edit covers that.

  • Weed comment

    gitt510/agent-skills/skills/weed-comment Skill

    0★ repo

    Remove context-leak prose from comments and docstrings in AI-agent-written code: edit-history narration, reviewer-directed self-justification, session references, redundant code restatement, and commented-out code. Preserve durable contract documentation, constraints, non-obvious rationale, business rules, TODO/FIXME, and tool directives. Use after an agent coding session, before committing agent-written changes, when a diff review flags comment noise, or when the user says "clean up the comments", "remove AI comments", "comment slop", "コメント整理して", "コメント抜いて", or invokes /weed-comment. Edit comments and docstrings only; never change executable code or perform a general simplify pass.

  • Write docs

    kevinb361/agent-skills/skills/write-docs Skill

    no license0★ repo

    Draft or revise technical documentation, specifications, proposals, ADRs, and README content for readers who do not share the current session context. Use when durable written guidance is the deliverable.

  • Autoxeo report

    stella-dust/autoxeo-marketplace/skills/autoxeo-report Skill

    0★ repo

    Layered GEO report generation — Boss/Operator/Specialist reports from audit, visibility, and analysis data for different decision-making levels.

  • Video to notes

    bgevorkian/agent-skills/skills/video-to-notes Skill

    0★ repo

    Convert a local video or supported video URL into structured Markdown notes and a searchable PDF using native subtitles or optional Whisper transcription plus perceptual frame deduplication and visual analysis. Use for video-to-notes, video-to-document, tutorial summaries, meeting or lecture notes, and extracting on-screen code, terminal commands, slides, or UI steps. This is multimodal video understanding, not merely speech-to-text.

  • Maintain project docs

    ImYourBoyRoy/agent-continuity-stack/skills/maintain-project-docs Skill

    0★ repo

    Create or update a project's required README and authoritative contributor, operator, API, migration, and troubleshooting documentation. Use when documentation is missing, stale, publication-bound, or affected by material behavior; verify commands and avoid duplicates.

  • Forge docs

    seroneyemmanuel4-afk/fullstack-forge-skill/src/fullstack-forge/commands/forge-docs Skill

    0★ repo

    Verify that user, contributor, architecture, operations, security, and release documentation is accurate and executable. Use for every maintained or distributed project.

  • Forge i18n

    seroneyemmanuel4-afk/fullstack-forge-skill/src/fullstack-forge/commands/forge-i18n Skill

    0★ repo

    Find locale, translation, formatting, expansion, fallback, and bidirectional-layout defects. Use for localized or locale-sensitive products.

  • Documentation sync

    lubochka/xiigen-mvp-engine/.agents/skills/documentation-sync Skill

    0★ repo

    Session-end canonical documentation sync for the XIIGen engine. Maps TypeScript file changes to the canonical docs that must be updated. Prevents the failure mode where code changes are committed but ENGINE_ARCHITECTURE_MERGED, TASK_TYPES_CATALOG_MERGED, or AGENTS.md are left stale. Invoked at session end — not at session start.

  • Ui screen grammar

    lubochka/xiigen-mvp-engine/.agents/skills/ui-screen-grammar Skill

    0★ repo

    The standalone catalogue of the seven screen grammars (G1 PROGRESS_STRIP, G2 VERDICT_GRID, G3 CARD_LIST, G4 TOPOLOGY_CANVAS, G5 KIOSK, G6 DASHBOARD, G7 SETTINGS_TABS) with a Pre-Code Declaration gate and a Grammar Violation Signals table, mapped to React page templates. One page = one grammar, declared in writing before any JSX.

  • Documentation sync

    lubochka/xiigen-mvp-engine/.claude/skills/universal/documentation-sync Skill

    0★ repo

    Self-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.

  • Mindforge session report

    sairam0424/MindForge/.agent/skills/mindforge-session-report Skill

    0★ repo

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

  • Mindforge skill creation

    sairam0424/MindForge/.agent/skills/mindforge-skill-creation Skill

    0★ repo

    Use when creating new skills, editing existing skills, or verifying skills work before deployment

  • Plan

    sairam0424/MindForge/.agent/skills/plan Skill

    0★ repo

    Plan mode: write an actionable markdown plan to .planning/plans/, no execution. Bite-sized tasks, exact paths, complete code.

  • Research paper writing

    sairam0424/MindForge/.agent/skills/research-paper-writing Skill

    0★ repo

    Write ML papers for NeurIPS/ICML/ICLR: design→submit.

  • Web pentest

    sairam0424/MindForge/.agent/skills/web-pentest Skill

    0★ repo

    Authorized web application penetration testing — reconnaissance, vulnerability analysis, proof-based exploitation, and professional reporting. Adapts Shannon's "No Exploit, No Report" methodology with hard guardrails for scope, authorization, and aux-client leakage. Active testing against running applications you own or have written authorization to test.

  • Documentation

    sairam0424/MindForge/.mindforge/skills/documentation Skill

    0★ repo

    MindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.

  • I18n architecture

    sairam0424/MindForge/.mindforge/skills/i18n-architecture Skill

    0★ repo

    MindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.

  • Plan

    sairam0424/MindForge/.mindforge/skills/plan Skill

    0★ repo

    Plan mode: write an actionable markdown plan to .planning/plans/, no execution. Bite-sized tasks, exact paths, complete code.

  • Research paper writing

    sairam0424/MindForge/.mindforge/skills/research-paper-writing Skill

    0★ repo

    Write ML papers for NeurIPS/ICML/ICLR: design→submit.

  • Technical writing

    sairam0424/MindForge/.mindforge/skills/technical-writing Skill

    0★ repo

    MindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.

  • Writing plans

    sairam0424/MindForge/.mindforge/skills/writing-plans Skill

    0★ repo

    MindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.

  • Writing skills

    sairam0424/MindForge/.mindforge/skills/writing-skills Skill

    0★ repo

    MindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.

  • Mindforge session report

    sairam0424/MindForge/plugins/mindforge/skills/mindforge-session-report Skill

    0★ repo

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

  • Mindforge skill creation

    sairam0424/MindForge/plugins/mindforge/skills/mindforge-skill-creation Skill

    0★ repo

    Use when creating new skills, editing existing skills, or verifying skills work before deployment

  • Update project

    amanahmed2222/skills/skills/update-project Skill

    0★ repo

    Use when updating docs, syncing CLAUDE.md or README.md, fixing stale documentation, or refreshing project rules and skills. Keeps docs aligned with code changes.