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.
-
rweisssieker-xp Skill Release Readiness ReportProduce a release readiness report across production blockers, connector status, and health assessment.
-
zts212653 Skill Debugging系统化 bug 定位:根因调查 → 模式分析 → 假设验证 → 修复。 Use when: 遇到 bug、测试失败、unexpected behavior。 Not for: 新功能开发、重构、已知原因的简单修复。 Output: Bug report(5件套)+ 根因 + 修复(含回归测试)。
-
zts212653 Skill Ppt ForgePPT 制作全链路:内容分析 → 分页规划 → 低保真 MD → imagegen 精美图。 架构猫写低保真 MD(ASCII art 结构图 + 视觉指引),imagegen 猫逐页出精美图。 Use when: 做 PPT、做演示文稿、做 slide、帮朋友做 PPT、画架构图、画技术蓝图。 Not for: 纯代码开发(用 worktree/tdd)、纯文档写作(直接写)。 Output: 低保真 MD + AI 原生精美图(raster PNG)。
-
zts212653 Bundle Expert Panel多猫专家辩论团:在现有协作习惯上加一层轻量编排 + WHY 链标准 + 交付链。 Use when: 用户明确要求 expert panel、专家辩论、多猫分析或三猫讨论。 Not for: 普通“帮我分析一下”、单猫能搞定的问题、代码实现、bug fix、日常聊天。 Output: 洞察卡片(rich block) + 语音总结 + 正式报告(DOCX/PDF)。
-
luissambrano Bundle PPTX OpsPPTX creation, editing, and analysis
-
luissambrano Bundle FirecrawlDeep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API
-
bestdeejay-design Bundle VelesDocumentation statistician — finds orphan documents (no inbound references), computes documentation metrics, detects dead zones (folders unlinked from main docs), validates link hierarchy L1→L2→L3→L4. Use when: "find orphans", "orphan docs", "unreferenced documents", "documentation stats", "doc metrics", "dead zones", "link hierarchy", "veles".
-
bestdeejay-design Bundle CensorFact-checker for documentation — detects duplicates (similarity >70%) and broken internal links in markdown files. Skips code blocks, inline code, and external URLs. Use when: "check duplicates", "find duplicate docs", "broken links", "broken references", "validate links", "censor".
-
bestdeejay-design Bundle Commit LintValidate git commit messages against Conventional Commits v1.0.0. Script commit_lint.py reads `git log` (subprocess) of one or more repositories (or stdin with --stdin), parses each commit into type/scope/subject, and reports violations: missing type, invalid type, type case, scope, subject length (default 50), subject capitalization, trailing dot/space, header length (100), body line length (72). Plain-text Markdown-friendly report or JSON (--json). Exit codes: 0 all clean, 1 violations found, 2 error. Pure Python 3 stdlib, offline, read-only. Closes the loop for commit-message-writer and version-bumper.
-
bestdeejay-design Bundle Doc CompareВизуальное сравнение markdown-документов бок о бок (side-by-side) с ПОДСВЕТКОЙ ПРАВОК. Скрипт scripts/compare_docs.py режет документы на блоки (заголовки/абзацы/списки/таблицы), через difflib находит изменённые блоки и подсвечивает: слева красным (удалено/изменено), справа зелёным (добавлено/изменено); внутри правок — пословная подсветка (зачёркнутое красным / добавленное зелёным). Кнопка «Только изменения» прячет неизменённые блоки. Поддерживает подтягивание версии из публичного GitHub-репозитория через gh (префикс gh:owner/repo@ref:path) и режим --diff (построчная таблица difflib). Триггеры: 'сравни документы', 'doc compare', 'side-by-side', 'визуально сравнить', 'diff docs', 'сравнение оферт', 'сравнить с опубликованным', 'покажи где правки', 'подсвети изменения'.
-
bestdeejay-design Bundle Docs SystemMeta-guide + router for documentation: the two branches (docs-product for 'why/what', docs-project for 'how'), the phase order, completeness levels L1/L2/L3, and the completeness checklist. Load a branch directly when the task is clearly product or engineering; load this skill for the big picture, ordering and completeness gates. Triggers: 'документация', 'набор документации', 'каталог документов', 'документация структура', 'полная документация', 'docs catalog', 'documentation structure', 'какую документацию писать'.
-
bestdeejay-design Bundle Skill ForgeMeta-skill and design compass for creating new skills and upgrading existing ones with a deliberate push toward being maximally technological, creative, and aesthetically disciplined. Use when the user wants to create a skill from scratch, reshape an existing skill, make a skill more reliable/technological, more creative/varied, or more visually polished — or when a skill feels templated, generic, or mechanically weak. Trigger on phrases like "создай скил", "новый скил", "улучши скил", "сделай скил креативнее", "эстетичный скил", "технологичный скил", "скилл выглядит шаблонно", "перепиши SKILL.md", even if the user does not say the word "skill" explicitly. Also use when reviewing a skill before release.
-
bestdeejay-design Bundle Video Script WriterСоздание структурированного сценария видео из темы: Hook (захват внимания в первые секунды), Body (сцены с тайм-слотами: проблема, основы, разбор, ошибки, совет), CTA (призыв к действию). Скрипт video_script_writer.py генерирует markdown-сценарий с таймкодами, хронометражем (секунды), языком (ru/en), кастомным CTA, выбором полного сценария или outline. Триггеры: 'сценарий видео', 'video script', 'напиши сценарий', 'план видео', 'структура ролика', 'video outline', 'сценарий для youtube', 'план ролика'.
-
bestdeejay-design Bundle API Contract TestingValidate an API contract against an OpenAPI 3.x specification (JSON or YAML) and an optional manifest of expected endpoints. Script api_contract.py enumerates operations (paths + webhooks), checks spec internal consistency (unresolved $refs, duplicates, missing responses), compares the manifest against the spec offline, and in live mode probes each manifest endpoint over HTTP and compares the actual status with the expected one. Pure Python 3 stdlib (argparse, json, pathlib, sys, urllib.request) with a built-in minimal YAML subset parser — no PyYAML, no requests. Emits a machine-readable JSON report (endpoints_count, missing_from_spec, contract_violations, conformant, errors) and uses exit codes 0/1/2. Closes the loop for api-doc-generator and test-generator.
-
smicolon Bundle Execution Context BuilderSynthesizes the chosen (or only) candidate flow into the canonical execution-context Markdown + JSON artifacts under .claude/clarifications/. Activates after flow-detector returns a single candidate, or after flow-selector confirms the user's choice. Never asks follow-up questions.
-
erikpr1994 Skill Domain ExpertMeta-skill for rapidly learning new domains. Covers domain research process, expert consultation simulation, knowledge validation, and documentation generation.
-
erikpr1994 Skill Writing DesignUse when creating design documents, technical specs, architecture decisions, or system documentation. Covers structure, audience, and validation.
-
erikpr1994 Skill Linear Project HealthGenerate health report for a Linear project. Progress vs plan, blocked issues, overdue items, risk assessment. Triggers - project health, project status, project report.
-
matejformanek Skill LockingPick a PostgreSQL backend lock primitive (atomic / spinlock / LWLock / heavyweight / predicate / buffer-pin-content) or debug a lock-ordering bug, silent LWLock hang, deadlock-detector report, or a multixact / tuple-lock interaction — the six-layer PG lock taxonomy in operational form. Covers `pg_atomic_u32 / u64` ordering + memory barriers, `SpinLockAcquire / SpinLockRelease` (with the "no calls / no ereport / no CHECK_FOR_INTERRUPTS" rules), `LWLockAcquire LW_SHARED / LW_EXCLUSIVE` and tranches (lwlocklist.h + wait_event_names.txt), heavyweight `LockAcquire` / `LockRelationOid` / `LOCKTAG_*`, predicate (SSI) locks, buffer pin / content locks, the `BufferMapping / LockManager / PredicateLockManager` partition rank rules, multi-XID `HEAP_XMAX_IS_MULTI` interaction with `FOR UPDATE / FOR KEY SHARE`, parallel-worker lock-group semantics, and the lldb-attach recipe for silent-LWLock-deadlock diagnosis. **Use this skill proactively whenever the user is writing or reviewing C in `src/backend` or `dev/src/backend`
-
understudy-ai Skill ObsidianWork with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
-
understudy-ai Skill ResearcherResearch current topics with multiple sources and produce a structured brief, comparison, recommendation, or fact-check. Use when the user asks for investigation, market/product landscape scans, option evaluation, due diligence, source-backed validation, or a research report. Do not use for summarizing a single provided URL/document, or for GitHub issue/PR operations.
-
droodotfoo Bundle Writing VoiceWriting voice calibration from studied authors. Accepts combinatorial voice arguments to blend multiple writer influences. TRIGGER when: user invokes "/writing-voice" or asks to "write like", "in the style of", "voice of", "blend voices", or references a specific writer influence for their prose. Also when user asks to review writing for voice/tone/style quality. DO NOT TRIGGER when: user asks to humanize existing text (use humanize skill), write code, generate commit messages, or produce technical documentation where voice is irrelevant.
-
droodotfoo Bundle Codebase OnboardingAuto-generate onboarding documentation from codebase analysis, tailored to the reader's experience level. TRIGGER when: user asks to onboard someone to a codebase, document this codebase, generate project documentation for new team members, write a codebase walkthrough or tour, create a getting-started guide, or explain a codebase to a specific audience. DO NOT TRIGGER when: user wants API reference docs (use language-specific tooling), or wants to understand a single file (just read it).
-
oceanfsdfsvfdsvs Bundle Customer Escalation TimelineReconstruct customer support escalation timelines from exported tickets, event logs, handoff notes, and account context so CS, support, engineering, and CX leaders can produce a structured handoff packet, SLA/ownership risk report, and closure plan without connecting to Zendesk, Intercom, Slack, Jira, or a CRM.
-
oceanfsdfsvfdsvs Bundle Workers Comp Denial PreflightReview workers' compensation claim denial, delayed care, medical causation, pre-existing condition, late reporting, employer dispute, hearing, or appeal packets before an injured worker, caregiver, HR partner, union steward, legal-aid intake helper, or claims advocate organizes evidence or seeks owner review. Use when the user needs denial-letter, deadline, medical-record, incident-report, witness, work-restriction, health-insurance-crossover, evidence-exchange, and live-action guardrails without giving legal advice or contacting an insurer, employer, agency, or court.
-
oceanfsdfsvfdsvs Bundle Credit Report Dispute PreflightPreflight credit report error disputes before a consumer, caregiver, housing or financial counselor, benefits advocate, or legal-aid intake helper sends a bureau dispute, furnisher dispute, identity-theft packet, CFPB complaint, or follow-up letter. Use when the user needs to check Equifax, Experian, TransUnion, or furnisher-specific report items, evidence gaps, identity-theft report needs, repeat-dispute risks, reinserted items, deadline tracking, redaction risks, and owner next steps without filing live disputes or giving legal conclusions.
-
oceanfsdfsvfdsvs Bundle Expense Reimbursement PreflightReview employee reimbursement or expense-report exports for missing receipts, duplicate claims, policy-limit issues, attendee or purpose gaps, mileage-rate errors, stale submissions, and coding gaps before approval, payroll, or ERP export. Use when finance, operations, managers, or founders need local-first reimbursement exceptions without logging into expense software.
-
oceanfsdfsvfdsvs Bundle Invoice Three Way Match PreflightReview supplier invoice lines against purchase orders and receiving records before payment release. Use when AP, procurement, receiving, operations, or founders need a local three-way match exception report that flags missing POs, unapproved or closed POs, vendor mismatches, quantity/price variance, missing receipts, and already-approved invoices with unresolved exceptions.
-
redhat-developer Bundle Mutation GateSupplies the approval rule another RHDH skill applies when it is already about to change something outside the session: how to state each operation, what approval binds to, what to report afterwards, and how to keep credentials out of a plan preview. Cited by name from the skill doing the work. Not an entry point — it performs no forge, Jira, or repository action itself, and a request to open, comment, transition, push, or post belongs to the skill that owns that target.
-
redhat-developer Bundle Rhdh Plugin Bug FixReproduces, diagnoses, and fixes a defect in a Backstage plugin inside the rhdh-plugins or community-plugins repositories: resolve the report from a RHIDP, RHDHBUGS, RHDHPLAN or RHDHSUPP Jira key, a GitHub issue, or plain prose; locate the owning workspace; write a throwaway reproduction test that fails for the stated reason; record before and after Playwright video evidence for a UI defect; then apply the smallest fix and verify it. Use for "fix this plugin bug", "reproduce RHIDP-1234", a plugin that renders the wrong thing, or a regression that needs evidence before and after.
-
redhat-developer Bundle Rhdh Jira Sprint ReportSummarizes an RHDH sprint that has finished or is finishing, from Jira RHIDP, RHDHPLAN, RHDHBUGS, and RHDHSUPP: committed versus completed story points, scope added mid-sprint, per-member breakdown, epic progress, the demo checklist with RHDH file and slide naming, and the velocity trend. Use for "sprint report", "what did we complete this sprint", "sprint review prep", "how did the sprint go", or "which demos do we owe". Looks back at work already done; preparing the sprint that has not started yet is a different job, and a single issue such as RHIDP-1234 is not a sprint.
-
seed-forge Bundle Patent Disclosure WorkflowEnd-to-end project workflow for Chinese patent technical disclosure drafting, polishing, pre-review, and conditional Word export. Use for patent writing, structure alignment, anti-AI-tone polishing, client pre-review preparation, and export coordination.
-
seed-forge Bundle Work Sc DOCX Comment ReplyWord 批注回复:提取 Word 文档批注上下文,生成回复并以 threaded replies 写回 docx。depends on docx(社区上游)。用户提到'回复批注''批注回复''逐条回复'时使用。
-
seed-forge Bundle Work Sc Document Sop Builder参考文档 SOP 提取:从参考文件中提取结构规则、内容要求、格式规范和导出模板,沉淀为可复用的文档编制 SOP。depends on docx/pdf(社区上游)。用户提到'参考文档做模板''提取文档规则''文档 SOP'时使用。
-
ntaffzii Skill Thai TranslateUse this skill for any task translating between English and Thai where tone, register, or pronoun choice matters — not just literal word substitution. Trigger on "แปลเป็นไทย", "แปลเป็นอังกฤษ", "translate to Thai", "translate to English", "EN-TH", "TH-EN", or any translation request involving Thai. If the source text is purely technical/machine-readable (e.g. translating a JSON key, a code comment with no audience), plain literal translation is fine and this skill's register guidance doesn't apply.
-
ntaffzii Bundle Thai Text ProcessingUse this skill for any task involving Thai word segmentation/tokenization, Unicode normalization of Thai text, Thai-aware sorting/collation, or romanization (Thai script to Latin script). Trigger on "ตัดคำภาษาไทย", "tokenize Thai", "normalize Thai text", "Thai collation", "romanize Thai", "RTGS", "PyThaiNLP". If the task is just reading/writing Thai text without any programmatic string manipulation (segmentation, sorting, comparison), this skill isn't needed — plain text handling is fine.
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 skill-forge, release-readiness-report, debugging. 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.