Docs & Writing

oracle Bundle

DBN user docs guide. Use when Codex is creating, editing, normalizing, reviewing, or planning Markdown user documentation for DBN under docs/, especially feature guides, settings references, index updates, Confluence-style formatting, topic ordering, related documentation links, troubleshooting tables, database object icons, or table-vs-bullet formatting decisions.

palkan Skill

Use this skill whenever organizing tutorial content into parts, chapters, and lessons. Trigger when the user says 'create a lesson', 'create a chapter', 'create a part', 'add a lesson', 'tutorial structure', 'content.md', 'meta.md', 'lesson ordering', 'callout', ':::tip', ':::info', ':::warn', 'code import', 'expressive code', or asks about the content hierarchy, directory naming, or markdown features — even if they don't explicitly mention content structure. This skill documents TutorialKit's specific directory conventions, metadata file roles (meta.md vs content.md), numeric prefix ordering, the recommended tutorial root config for Rails, callout syntax with all attributes, code block file imports, and expressive code features. These are framework-specific patterns that cannot be inferred from general knowledge. Do NOT use for frontmatter option reference (use tutorial-lesson-config) or file/template organization (use rails-file-management).

parallel-web Skill

Discover entities (companies, people, products, etc.) matching a natural-language description. Use when the user asks to 'find all X' or 'list every Y that…' — e.g., 'Find AI startups that raised Series A in 2026', 'List roofing companies in Charlotte NC', 'Show me YC W24 dev tools companies'. Different from web-search (which returns webpages) and deep-research (which returns a narrative report). Use this when the user wants a structured list of entities.

parallel-web Skill

ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than parallel-web-search. For normal research/lookup requests, use parallel-web-search instead. Supports multi-turn: pass --previous-interaction-id from a prior research or enrichment to continue with context.

planetabhi Bundle

Documentation style guide enforcer by @planetabhi. Applies and reviews the writing style guide when authoring or editing product documentation and tutorials. Use to check prose for voice, tense, word choice, inclusive language, formatting, code block, UI, Markdown, and number/date conventions.

portaly-ai Skill

Orientation and navigation for what Portaly's open APIs can do — subscription payments, digital products, discount codes, buyer promotion, subscriber self-service, and order/invoice queries — plus an API catalog and where to find Portaly's API docs. Trigger when the user asks "what can Portaly do", "what APIs does Portaly have", wants a list or catalog of Portaly's APIs/endpoints, is evaluating Portaly's payment or product APIs before committing to an integration, is looking for Portaly API documentation, or is deciding which Portaly skill to install.

plearaj Bundle

Report DRY, KISS, YAGNI, SOLID and module-depth findings, plus violations of rules the project has already written down, from the persisted code-flow map, with file:line evidence and honest coverage.

pluk-inc Skill

Prepare complete release PRs, publish, tag, and roll back Markdown Preview releases — branch/PR naming, exactly what scripts/release.sh and scripts/rollback-release.sh do (including that release.sh publishes live), and the already-wired Amore distribution config (codesign identity, notary profile, EdDSA key). Use when the user asks to create a release PR, release, ship, cut a version, bump the version, tag a release, roll back or unpublish a release, or asks about this project's Amore-specific config (codesign identity, notary keychain profile, EdDSA key, custom domain).

quarto-dev Bundle

Capture or update documentation screenshots for the Quarto website using Playwright. Use when screenshots need refreshing, new screenshots are needed for docs pages, or the user mentions screenshots, screen captures, or visual documentation.

rajnandan1 Skill

Specialized skill for creating and editing high-quality Kener documentation. MUST be used whenever creating or editing documentation files in the src/routes/(docs)/docs/content/ directory or updating docs.json navigation.

raphaelmansuy Skill

Write and generate Packt publisher manuscripts as pixel-perfect DOCX using edgemint. Use this skill when the user is authoring a Packt book chapter, applying Packt house styles, generating or reviewing a Packt-style Word document, or converting Markdown to a Packt-compliant manuscript. Knows every Packt paragraph style, character style, callout, list level, and code block variant. Triggers on: "Packt chapter", "Packt style", "publisher manuscript", "Packt template", "write a chapter for Packt", "generate Packt DOCX".

muratcankoylan Bundle

Posts content to WeChat Official Account (微信公众号) via Chrome CDP automation. Supports article posting (文章) with full markdown formatting and image-text posting (图文) with multiple images. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "图文/文章".

77652189 Bundle

Establish and maintain a five-document set (requirements, architecture, execution plan, handoff, ADR index) split by decay rate, plus guard tests that enforce it. Use whenever the user asks to write, update, fix, tidy, or check project documentation — 更新文档, 先写文档, 写文档, 改文档, 补文档, 文档先行, 整理文档, 文档治理, 建立文档结构, 记一条决策, "update the docs", "docs first", "write the docs" — and when starting a new project's docs, taking over a codebase whose docs are missing or stale, recording a decision as an ADR, or auditing for doc drift. Not for authoring one-off prose documents, generating API reference, or code review.

sandipb Bundle

Compose, edit, or review reader-oriented technical articles from supplied authoritative context. Use for technical blog posts and explanatory articles that may need stronger restructuring, pacing, explanation, or information selection than work-oriented documentation permits.

sandipb Bundle

Compose, edit, or review work-oriented technical documentation from supplied authoritative context while preserving technical meaning and distinct information. Use for READMEs, runbooks, procedures, reports, design documents, API documentation, PR descriptions, commit messages, warnings, and code comments.

autumnsgrove Bundle

Design and document RESTful and GraphQL APIs with OpenAPI/Swagger specifications, authentication patterns, versioning strategies, and best practices. Use for: (1) Creating API specifications, (2) Designing REST endpoints, (3) GraphQL schema design, (4) API authentication and authorization, (5) API versioning strategies, (6) Documentation generation

quarkusio Skill

Writing style guide for the Quarkus LangChain4j workshop documentation. Apply whenever writing or editing docs in docs/docs/. This skill must be consulted before writing or editing any file under docs/docs/ — do not rely on defaults.

weizhena Skill

Summarize deep research results into markdown report, cover all fields, skip uncertain values.

alexanderop Skill

Deep research on a technical problem using parallel subagents for web docs, Stack Overflow, and codebase exploration, saving a markdown report to docs/research/. Use when the user says "research X", "investigate X", "find out how X works", or needs evidence-based recommendations before implementing.

shinyorg Bundle

Review past MAUI DevFlow sessions. USE FOR: DevFlow friction reports, classifying `maui_tap`/`maui_hittest`/`maui_screenshot`/`maui_cdp_webviews` issues vs app bugs, markdown Environment/Findings reports, scrubbed dotnet/maui-labs issue drafts, workaround summaries. Does not run live `maui devflow`. DO NOT USE FOR: fixing bugs, onboarding, live debugging, or memory search.

slogsdon Skill

Apply ASD-STE100 Simplified Technical English (STE) — the aerospace and defense controlled-language standard — to technical writing: procedures, descriptions, maintenance records, and safety warnings. Use when Shane says: "apply STE100 to this", "apply STE to this", "simplified technical english", "make this STE-compliant", "review for ASD-STE100", "STE check this", "rewrite this as a procedure in STE". Also invoke proactively when reviewing step-by-step instructions, work cards, or safety-critical warnings that must be unambiguous for a non-native-English reader.

smter Bundle

Use when 中文小说项目已经具备完成且审查通过的书稿，并需要做导出就绪检查、基于 Pandoc 的 PDF/EPUB 打包或交付诊断

someant Bundle

Use this skill when the user wants to write, rewrite, or template content for WeCom/Enterprise WeChat documents, especially news briefs, research digests, daily reports, weekly reports, or other information-dense content that must read well after pasting into a WeCom doc. This skill is for formatting around WeCom's lightweight Markdown support, stable heading/list structure, and scannable Chinese business writing.

specstoryai Skill

Prove every room of an Everwyn story is reachable from the start — run the reachability harness, play every route through the real engine, and report PASS or a detailed FAIL. Use when working an "Evaluate" sub-issue of a Game Story. Reports only; never fixes.

wyattblue Skill

Transcribe a media file or live microphone to text or subtitles with auto-editor's whisper subcommand, then edit by spoken content — cut to keep (or drop) sections whose subtitles match a word or regex. Use when someone wants a transcript, captions, live speech transcription, or to cut a video based on what is said rather than on loudness.

xpera-ch Bundle

Use this skill when explicitly asked to perform an adversarial review of code before a merge, tag, or release — trigger phrases like "adversarial review", "review this before we merge/tag", "review this phase", "review before release", "pre-merge review", or "pre-tag review". This is a deliberate, explicitly-invoked review discipline for phase boundaries, not an automatic code-review pass — do not trigger it for casual "can you check this" requests or as a background habit. It produces a PASS/FAIL/CONCERN verdict built from re-derived, live evidence (commands actually run, tests actually written and executed) rather than the implementer's self-report, fixes nothing during the review, and stops after the report to wait for instructions.

xyz-ai-lab Skill

Review git-staged changes (a specific file if given, otherwise all staged files) for correctness bugs, coding-style and codebase-consistency issues, and suggestions for modularization, maintainability, efficiency, and readability. Report findings without applying fixes unless the user asks.

yamada-ui Skill

Create a GitHub Issue for yamada-ui. Use when the user says they want to create an issue, report a bug, request a feature, report a documentation problem, or file an issue against yamada-ui.

yansongda Skill

Use when preparing to publish a new version of a PHP Composer package and need to write or update CHANGELOG, upgrade guides, and documentation before tagging and releasing

yibie Bundle

Search and summarize weekly tech news from multiple angles into a report

yotharit Skill

Risk radar for a Huly tracker project — surfaces overdue issues, at-risk milestones, unassigned high-priority work, stuck in-progress, bottlenecks, and over-budget items. Output only, no writes to Huly. Trigger on: /pm-risks, 'project risks', 'what's at risk', 'risk report for PROJ', 'PM risks', 'risk radar'.

yuezhiai Bundle

Use when the user asks about content in their OpenKB knowledge base — research topics, concepts compiled from their documents, cross-document synthesis — or mentions `openkb`, an `.openkb/` directory, or a `wiki/` tree generated by openkb. The user may invoke you from any working directory; the active KB resolves via `openkb status`. Do NOT use for arbitrary Markdown directories, Obsidian vaults, or documentation sites not built by openkb.

zeybek Bundle

Use this skill when investigating a failure whose cause is not yet known — a production incident or outage, a regression, an intermittent or flaky failure, a performance degradation, corrupted or surprising data, or a bug report you must diagnose before fixing. Apply it to triage severity and mitigation, gather and preserve evidence, form and test hypotheses, bisect and localize the cause across components and time, read logs, metrics, and traces, confirm a root cause by mechanism, and record findings in a blameless writeup. Do not use it when the change is already understood and only needs implementation (use apex-implement) or when reviewing a proposed change (use apex-review).

zhanlincui Bundle

Use when illustrating a Markdown article with high-finish editorial visuals, visual-bible planning, structured prompts, optional Qiniu upload, and inserted image references for article publishing workflows.

zhoujiakai Bundle

用纯 Markdown 创建和维护个人任务看板，以聚焦目标为第一组织维度。管理工作任务、个人任务、日常习惯。当用户需要以下操作时触发：(1) 创建或初始化任务看板、任务管理系统 (2) 添加、更新、完成、归档任务 (3) 设定或更新聚焦目标 (4) 评估目标完成风险 (5) 日常习惯打卡 (6) 看板定期回顾、复盘、清理。触发关键词：看板、kanban、任务管理、聚焦目标、目标设定、习惯打卡、任务归档、风险评估、周回顾、复盘、goal setting、task board。

zhylq Bundle

Use when illustrating a Markdown article with high-finish editorial visuals, visual-bible planning, structured prompts, optional Qiniu upload, and inserted image references for article publishing workflows.