Docs & Writing

blu1606 Bundle

Author VLearn Markdown Labs from a confirmed brief. Use whenever a user asks to create, rewrite, review, import, or publish a Lab, Codelab, assignment, starter repo exercise, or hint-python lesson.

blutui Bundle

Build Blutui Canopy Blocks — reusable page-section templates that content editors add, fill in, and arrange in the Canopy editor. Use this skill whenever creating or editing block templates (.canvas files in views/canopy/), writing {% canopy %} config/template/head/scripts sections, defining block settings, rendering block areas with canopy.blocks, canopy.render, canopy.head, or canopy.scripts, constraining areas with allow/limit/locked or hiding blocks from the Add Block picker, building nested/parent blocks (galleries, sliders, accordions, tabs) with the children config or canopy.children, canopy.child, or canopy.childList, or migrating deprecated cms_* Canopy elements to blocks. Always load this skill when the user mentions Canopy blocks, block templates, block areas, nested blocks, child blocks, slides, gallery items, accordion items, editable sections, hidden blocks, locked areas, the Canopy editor, or making part of a Blutui page editable — even if they don't say "block" explicitly.

bouffalolab Bundle

Use when the user asks to "collect WiFi lowpower issue information", "gather Bouffalo chip power consumption problem details", "create customer background report for WiFi issues", "survey customer for power consumption debugging", or needs to systematically collect diagnostic information for Bouffalo chip WiFi low power problems. Provides structured interview workflow and generates comprehensive customer reports in multiple languages.

bpodhalicz Skill

Bullet-proof research mode — no hallucinated sources, no unverified numbers, no vague dates, no stale facts. Every claim traces to a real, fetched, on-topic, date-checked source, or it is labeled or dropped. Use whenever a response would contain specific numbers, statistics, prices, dates, named studies, quotes, vendor or tool capabilities, "latest in X," "current state of Y," market data, due diligence, or comparisons presented as fact — anything repeatable to a client, team, or audience. Especially in fast-moving fields (AI, models, tools, frameworks, pricing, regulation) where last year's truth is already wrong. Don't wait for the word "research": if the output could be screenshotted with the user's name on it, trigger. When in doubt, trigger.

breslee1707 Bundle

Translate local PDFs, including safe prose on image-only scans, into Vietnamese or another supported Latin-script language while preserving layout, formulas, tables, and figures. Use for PDF translation, OCR-assisted scan translation, batch translation, terminology-sensitive handoff translation, or diagnosing incomplete output. Do not use for targets requiring CJK, right-to-left, or complex-script shaping.

brycewang-stanford Bundle

Pick an AI slide-deck skill and a concrete visual style from a curated registry, filtering on the requirements that decide it — editable in PowerPoint, speaker notes, a mandated corporate template, offline, PDF — with sample imagery and the style ids each project actually uses. Use when the user wants to make a presentation, deck or slides and has not already chosen a tool; asks which slide skill to use or what the difference between them is; wants to know what a style looks like before committing; or names a style id such as soft-editorial or swiss-grid. This skill routes to the skill that makes the deck — it does not make decks itself.

cardano-foundation Bundle

Parametric multi-run Antithesis triage entry point. Lists recent runs for a given tenant + GitHub repo, presents a digest as a Markdown GitHub gist, and hands off to antithesis-triage for per-report drill-down. Use when the user asks "what's going on in Antithesis", "summarize last N hours", or starts a triage session without a specific report URL in hand.

cardano-foundation Bundle

Publish weekly Antithesis platform status reports to the cardano-node-antithesis GitHub wiki (pragma engagement). Use when asked to "upload the wiki report", "publish weekly Antithesis report", "Antithesis-Report", "platform status for pragma", or fill Antithesis-Reports. Report body format is owned by Antithesis — this skill only uploads. Runs tools/antithesis-wiki-report/scripts/upload-report.sh.

castorini Bundle

Configure, run, evaluate, compare, summarize, and report Piika research and retrieval benchmarks. Use for Piika package setup; built-in, prebuilt, or custom benchmark manifests; local Anserini or remote Pyserini backends; single, shared, or sharded runs; answer, ranked-list, or combined outputs; supplied-document bundles; and reproducible evaluation workflows.

castorini Bundle

Install, run, evaluate, and report NanoKnow NQ-Open or NanoKnow SQuAD through Piika using the ClimbMix-supported query sets and climbmix-400b backend. Use for NanoKnow runs with normal retrieval or supplied-document bundles, multi-answer ground-truth preparation, smoke tests, full runs, and side-by-side experimental comparisons.

crmne Skill

Contribute to the RubyLLM AI framework - set up the repo, run and record specs, work on conversations, individual AI operations, providers, protocols, Rails integration, and docs. Use when fixing a bug, building a feature, writing specs, or changing documentation in the RubyLLM codebase.

cvk0524 Bundle

汇报框架构建器——输入汇报背景、听众、素材、时长，自动匹配最合适的方法论（金字塔原理/SCQA/BLUF/AAR/6-Pager/Nancy Duarte 等 20+ 方法论），输出结构化的逻辑框架和初版汇报内容。触发词：汇报框架、汇报梳理、汇报结构、方法论汇报、结构化汇报、金字塔原理汇报、SCQA、准备汇报、给老板汇报、述职、复盘汇报、周报框架、业绩汇报、项目提案、准备演讲、report framework、structured reporting。

cvk0524 Bundle

汇报语言优化器——输入初版汇报稿（无论是零散笔记还是完整初稿），按咨询公司（麦肯锡/BCG）+ 大厂（阿里/字节/华为）+ 反AI感规则，优化成老板级"结论前置、数据精准、动词优先、精炼有力、明确行动"的表达。触发词：汇报语言优化、汇报稿优化、老板级表达、精炼汇报、语言精简、汇报润色、麦肯锡表达、结论前置、汇报改稿、report polish、executive polish、汇报稿精炼。

davehowell Bundle

Simplify and proofread any technical writing against rules adapted from ASD-STE100 — Confluence pages, Jira tickets, PR review comments, PR bodies, READMEs, runbooks, ADRs, dbt/Cube descriptions, error strings. Use when asked to "simplify this doc", "de-slop this", "run an STE pass", "make this readable", or "run WALL-E over it", or when drafting/reviewing Confluence, Jira, or PR-comment prose. Review mode reports findings. Rewrite mode edits only when the user explicitly asks for a rewrite.

davidsanz21 Bundle

Run a complete job search as a coordinated team of career experts — intake of all career documents, a structured career-profile interview, master CV creation, per-posting fit assessment with capability and preference scores (1–10), tailored truth-only CVs and cover letters rendered as PDFs, a persistent application database, and question-by-question interview coaching that ends in a printable cheatsheet PDF. Use this skill whenever the user wants to start or run a job search, says things like "help me find a job", "build my career profile", "make my CV", pastes a job posting or job description (even without further instructions), asks whether they should apply to something, asks for a tailored CV or cover letter, wants to log or track applications, or says they have been invited to an interview and need to prepare.

dbhq-uk Bundle

Turn Outlook mail into organised markdown archives - from a PST export, or from live mail exported by the outlook-graph skill. Use when needing to convert PST files to markdown, extract email archives, process Outlook exports, create searchable email collections, or keep an existing archive current. Trigger on phrases like "extract pst", "convert pst", "pst to markdown", "outlook to markdown", "email archive", "extract outlook", "update my email archive".

deepsense-ai Skill

Update Builder Journal documentation references after changes to ragbits-example repository. Use when commits in ragbits-example changed and documentation SHA references need updating.

delta-hq Bundle

Produce a long-form, shareable markdown writeup on whether Claude has regressed on this user's work. A bundled Python script scans `~/.claude/projects/`, computes every metric, and renders a markdown skeleton with tables already filled — in ~2.5s. Claude fills a dozen short narrative placeholders and saves. Writes `./cc-canary-<YYYY-MM-DD>.md` suitable for pasting into a GitHub issue or gist.

dimdasci Bundle

Transcribe existing audio/video recordings into speaker-labeled markdown transcripts. Handles meetings, interviews, calls, voice notes. Optionally extracts screenshots from screen-share and produces structured topic documents. Use when user has a recording file and wants a transcript, notes, or summary — even if they just say "process this" or drop a file. Not for audio editing, format conversion, or live captions.

diskd-ai Bundle

Inspect and summarize local Codex/Claude session logs using the ccbox CLI (projects, sessions, history). Use when asked to list discovered projects, find sessions for the current repo/folder, print a session timeline, or produce an evidence-based “what happened” report from a session .jsonl log under CODEX_SESSIONS_DIR.

dizhouid-lgtm Bundle

Pixboom 招聘搜人筛人作业流程(猎聘 liepin-cli),为任一岗位搜候选人、筛简历、提报、 维护候选人池/去重台账/JD 记录。当用户说"搜人""下一轮""继续搜""筛简历""提报候选人" "开简历给我看""出 PDF""更新候选人池",或要为某岗找人/筛人时使用;岗位招满或用户说 "这个岗招完了/先暂停"时,走本流程的收官复盘(步骤 7)。岗位标准看该岗 JD,本流程岗位中立。

dlomibao Bundle

Use when the user is building, outlining, or revising a slide deck, presentation, talk, pitch, board update, or briefing — any time someone needs to decide what to say, in what order, and what to cut. Use when a draft feels too long, too generic, doesn't land, or sounds AI-generated. Use when someone says "help me make a deck about X" — structure is where decks fail. Do NOT use when the user only wants visual polish on already-finalized content. Style enforcement (slop-phrase list) is English-only; structural rules apply to any language.

gibbok Skill

Review and editing guide for TypeScript book and reference content in the style of The Concise TypeScript Book. Use when reviewing or editing educational prose, translated or non-English content, code examples, chapters, table-of-contents entries, or Markdown formatting in this repository to identify and fix typos, grammar mistakes, formatting problems, and minor clarity issues without altering the original meaning or the book’s concise, practical, example-driven style.

github Skill

Review and refine GitHub Well-Architected Framework (WAF) documentation under the content/ folder for clarity, precision, consistency, and publication readiness. Use this when reviewing pull requests, markdown files, or draft content in content/ to ensure guidance is unambiguous, readable, and aligned with editorial standards.

github Skill

Validate and improve GitHub Well-Architected Framework (WAF) documentation under the content/ folder for architectural correctness, decision quality, explicit trade-offs, and actionable guidance. Use this when reviewing pull requests, markdown files, or draft content in content/ to ensure recommendations are technically sound, context-aware, and guide readers toward correct architecture and design decisions.

given-dream Bundle

Download scholarly PDFs serially through a lawful live Chrome, Edge, or Firefox session when direct HTTP is blocked by login, institutional authentication, bot checks, attachment handling, or an internal PDF viewer. Use for ScienceDirect/Elsevier, Wiley Online Library and AGU/Wiley, Canadian Science Publishing, AIP Publishing, IEEE Xplore, and other publisher pages that expose an authorized PDF route.

gonzalochale Bundle

Generates viral-style TikTok slide scripts with multiple formats, angles, and voices. Use this skill whenever someone asks for TikTok content, slide scripts, short-form video hooks, or content that needs to stop the scroll — even if they don't say "TikTok" explicitly. Avoids repetition by rotating hook structures, slide counts, emotional angles, and content styles. Includes natural product integration without sounding salesy.

grafana Bundle

Look up official k6 documentation with `<binary> x docs` when writing, debugging, or configuring a k6 test, or reaching for any k6 API, option, executor, or CLI flag. k6 syntax changes between versions, so consult it instead of recalling k6 from memory or searching the web.

hanlinlibham Bundle

把源材料增量编译为持久化 Markdown + SQLite wiki，实现跨会话知识积累。用于建立或使用个人/领域知识库、Obsidian wiki，以及取材、编译、查询和治理已有 wiki。八模式按意图路由： survey（我已经有笔记了、勘察存量、冷启动、看看我现有的资料）→ 只读结构扫已有目录，反推 init 提案与种子草案，不建库不写盘； init（初始化、从零建库、搭建 Obsidian）→ 访谈真实工作流并创建首个领域； source（取材、找资料、按清单搜）→ fan-out 搜集，收口 Inbox/raw，不碰正典； recall（打开 wiki、基于积累、之前研究过）→ 持续加载已有知识； ingest（整理、消化、归档、加入知识库）→ 比较新旧后编译材料； query（根据 wiki 回答、查查看）→ 单次查询； lint（检查健康、矛盾、断链、重复）→ 治理知识库； deep-dive（查漏补缺、上强度）→ lint 找缺口，经确认后搜索并 ingest。 无 wiki 且用户要建库时走 init；有新材料走 ingest；人给索引并要求找资料走 source；只提 wiki/既有领域知识走 recall。不确定则询问。

harehare Bundle

Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.

harrycain72 Skill

PDF Skill

hec-ovi Skill

Search and read the Tor network: onion search engines (Ahmia, and SearXNG's onions category) and .onion pages as clean Markdown, through a local Tor this tool starts itself. Use it when the user asks to search Tor or the dark web, to open a .onion address, to find onion services or mirrors, or to run searches through Tor for anonymity. It is the same CLI as the web-search skill with one layer turned on, so everything else (paging, the untrusted-content fence, arxiv, github) works unchanged. Off by default: nothing goes through Tor until `websearch tor up` runs.

hegeldev Skill

This skill should be used when creating or modifying conformance tests in hegel-core, when adding a new ConformanceTest subclass, when writing a conformance binary for tests/conformance/tests/, or when instrumenting the hegel server to report metrics for conformance validation. Also use when debugging conformance test failures or understanding how library implementations (hegel-go, hegel-rust) are validated.

heyman333 Skill

Converts a file path or URL to Markdown using markitdown. Usage: /convert <file-path or URL>

lee-117 Bundle

Execute, validate, and debug Midscene YAML automation files. Handles dry-run, execution, report analysis, and iterative debugging.

letta-ai Bundle

Migrates agents from the retired Python Letta server's PostgreSQL database into Letta Code's local backend/App Server. Use when moving legacy agents, message history, and attached memory blocks into the current local backend and converting block memory to Git-backed MemFS Markdown files.