Docs & Writing

rogerchappel Skill

External Report Skill

rogerchappel Skill

External Report Skill

rogerchappel Skill

External Report Skill

rogerchappel Skill

Email Report Skill

shali10 Skill

Use when adapting a single piece of Markdown content into tailored, platform-compliant formats for Telegram, WeChat, Zhihu, Twitter/X, and QQ.

shali10 Bundle

Use when sending Markdown tables to Telegram, resolving table degradation, CJK East Asian character alignment, and mobile viewport wrapping.

whitebit-exchange Skill

Analyzes closed WhiteBit trades and computes win rate, net P&L, R:R ratio, fee drag, and behavioral patterns from trade history. Use when the user wants to understand their trading performance over a period. Use when the user says "review my trades", "win rate", "how did I do", "P&L this month", "my biggest losses", "trading performance", or "weekly report".

whitebit-exchange Skill

Computes technical indicators (RSI, MACD, Bollinger Bands, EMA) from WhiteBit OHLCV data and produces a scored market signal report. Use when the user wants a technical view before entering or exiting a trade. Use when the user says "analyze", "technical analysis", "RSI", "MACD", "is X a good buy", "chart analysis", "indicators", "support and resistance", or "signal for".

frenzymath Bundle

Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second. Use when a markdown proof cites statements from external papers.

frenzymath Bundle

Verify a markdown proof in the order it is written. Use when the task is to check local correctness, theorem applicability, and reasoning gaps statement by statement through a paper-style proof.

frenzymath Bundle

Aggregate all detected errors and gaps into the final verification report, apply strict accept/reject logic, and produce repair hints when rejected.

songyw2003 Bundle

Turn a research paper, a paper2assets package, or an existing PPT deck into a narrated MP4 video. Prefer the shared paper2assets package when present so paper2poster, paper2blog, paper2slides, and paper2video use the same section order and narration. Preserve the advanced deck route by delegating slide authoring to the external `hugohe3/ppt-master` project, then synthesize audio with `skills/paper2poster/scripts/generate_audio.py`, render with `skills/paper2video/scripts/render_video.py`, and burn final subtitles with `skills/paper2video/scripts/add_subtitles.py`.

songyw2003 Bundle

paper2assets — paper PDF → reusable assets

cooltheworld Skill

Research a subject along two axes — how it got here and how it compares today — and cross them into a traceable report on where it goes next.

devantler-tech Skill

The run loop for an autonomous AI engineer acting as a portfolio's primary engineer — pre-flight, resume in-flight work or survey every product's live state, select the highest-value work (operate before advance), act through isolated per-run working copies and draft PRs self-promoted on genuine readiness (driving trusted-author PRs to merge), then report and bank learnings. Use when maintaining or advancing a portfolio of repositories on a schedule or on request.

grinchenkoedu Skill

Fix what is wrong — the findings from a review still in this conversation, a review report file, or a symptom you describe in a sentence. A described symptom gets investigated first, the way /gku:plan investigates, until the cause is proven; then it acts instead of writing a plan. Re-checks every finding against the current code before touching it, lands the smallest change per finding, and re-runs the tests. Asks how far down the list to go — blockers only, warnings too, or nits as well — and recommends one of those for this change; nits left for later go into the task file in progress, or into a new one under .tasks/.

grinchenkoedu Skill

Turn a request — a sentence you type, or a markdown brief — into a grounded plan you can hand to /gku:implement. Works out what is really being asked (bug, feature, question, data fix), checks it against the actual code and data, and writes an ordered plan with acceptance criteria. Asks you in the chat, in one batched round, whatever only you can answer — and writes your answers into the plan instead of leaving them open. With --manual it writes the plan for you to build by hand instead, detailed enough to follow and to pick up again in a new session. Plans only; writes no production code.

grinchenkoedu Skill

Find the right answer across this repository and the internet — a question, a choice between libraries or approaches, a symptom that may be a known upstream bug, a feature that needs an outside API understood first. Investigates the way /gku:plan does, then reads the documentation, the upstream source, its issues and advisories for the versions this project actually runs. Asks you in the chat, in one batched round, whatever only you can answer, and writes your answers into the result. The result decides the shape — something to build here becomes a task file in /gku:plan's shape that /gku:implement reads; anything else is an answer in the chat with a TL;DR on top. Read-only; writes no code.

grinchenkoedu Skill

Build a task step by step in the current session — from a plan file, a markdown brief, or a sentence. Works through ordered steps, ticking each one off in the task file as it lands, so an interrupted run resumes exactly where it stopped instead of starting over. With --auto it runs the whole cycle unattended — build, self-review, fix, test, repeat — and opens the pull request at the end, stopping only for something that genuinely needs you. Everything it noticed and left alone is written down and put in front of you before it calls the plan done. It never merges or deploys on its own, and an unattended run never merges at all.

huangserva Bundle

markdown-illustrator

smturtle2 Bundle

Compose popups with inputs, Markdown documents, and image or document file paths, then return the user's response to the conversation.

tavily-ai Bundle

Build a structured, deduplicated list of entities matching a description you give — companies, people, products, laws, anything — instead of a pile of articles you have to read yourself. Use this skill when the user doesn't have a starting list and wants one built from criteria, or says "find all companies that...", "find every X that does Y", "list all the...", "who are all the...", "build me a list of...", or describes a filter/criteria they want matched across the web. Returns a clean table of matching entities with supporting sources. Do NOT use this when the user already has a list and wants fields added to it (see fill-missing-fields), or wants one exhaustive report on a single known entity (see tavily-research).

tavily-ai Bundle

Look up a past research run by what you asked, not by remembering its run ID. Use this skill when the user wants to revisit a previous tavily-research task and doesn't have the request_id handy, or says "what did that research on X find again", "pull up my last research on Y", "show me past research tasks", or "find that report I ran earlier". Also use it right after a research run to log it, so it can be found later. Do NOT use this for a fresh research task — start there with tavily-research directly.

comsky Bundle

Format and publish rich Notion documents with structured sections, code blocks, tables, callouts, quotes, mermaid diagrams, and emojis. Use when the user asks to organize, write, or save content to Notion (e.g., "notion에 정리해줘", "notion에 저장해줘"), or when invoked with /notion-format. Detects content type (tech-doc, meeting-notes, analysis, tutorial, bug-report) and applies the appropriate formatting template automatically.

cookaihq Bundle

Use when the user wants to convert a PDF into Markdown / LaTeX / DOCX — phrases like "把这个 PDF 转成 markdown"、"PDF 转 md/docx"、"提取 PDF 里的公式和表格"、"PDF 转可编辑文档"、"pdf2md"、"doc2x". Wraps aihubmax.com Doc2X V3; handles formula recognition and cross-page table merging, returns a ZIP that is auto-extracted into a date-time-prefixed folder. Do NOT use for plain text extraction of a single short page (read it directly), image generation, OCR of photos, or non-PDF documents.

rlaope Bundle

Invoke when writing any status, completion, or result report — calibrates claims to the evidence actually gathered, marks the unmeasured as open, reports failures plainly, and distinguishes "verified at layer X" from "should work".

get-convex Skill

Send THIS coding session's transcript (Claude Code or Codex) to the Convex quickstart backend (anteater) for an AI post-mortem that improves the whole system — the runbook, bootstrap script, and skills. Use after a quickstart run (success or failure), or whenever the user wants to "send feedback", "report how that went", or "help improve the quickstart".

sociotechnica-org Skill

Decompose a decided plan, spec, issue, or design conversation into dependency-ordered tracer-bullet tickets written as local markdown files. Use when asked to "break this into tickets," "create implementation tickets," or "decompose into work items" — any time a decided scope needs slicing into executable vertical-slice tickets with blocking edges.

ractive Skill

Run a dogfooding session for hyalo — build from source, exercise the CLI against real knowledgebases (own KB, MDN, GitHub Docs, VS Code docs), find bugs, verify recent fixes, assess UX, measure performance, and write a structured report. Use this skill whenever the user says /dogfood, "dogfood", "run a dogfood session", "test hyalo against real data", or wants to exercise hyalo on real knowledgebases to find issues.

ractive Bundle

Search and edit structured markdown knowledgebases with the Hyalo CLI: frontmatter, tags, tasks, links, and document structure.

ractive Bundle

Maintain Markdown Architecture Decision Records with Hyalo's MADR profile and table-of-contents commands.

opsmill Bundle

Audits an Infrahub repository against best practices and rules, producing a structured compliance report. TRIGGER when: reviewing repo for compliance, onboarding to existing project, pre-deployment validation, catching issues. DO NOT TRIGGER when: creating schemas, writing checks/generators, querying live data, populating objects.

otonashiz Bundle

Analyze one public TikTok video URL by extracting video metadata, platform-provided caption text, and visible top-level comment signals, then write a Markdown report with hot comments, audience questions, conversion signals, and practical insights. Use when Codex receives a TikTok video link and needs more than caption extraction, especially for comment analysis, audience intent understanding, or conversion-oriented insight.

otonashiz Bundle

Extract TikTok video metadata and platform-provided caption/transcript tracks from one public TikTok video URL into a Markdown report. Use when Codex receives a TikTok video link and needs to produce the same Markdown layout as the legacy TikTok analyzer, but with browser-based Playwright extraction instead of Whisper. If the transcript is neither English nor Chinese, append a complete English translation after the original transcript. If the video has no platform transcript/caption track, fail clearly instead of inventing text.

otonashiz Bundle

Export the publicly visible Videos and Shorts from one YouTube channel or profile URL into a Markdown report containing title, canonical video URL, view count, publish date, and Video/Short type, plus a plain one-URL-per-line block for Google NotebookLM. Use when the user provides a YouTube channel URL and asks to list, inventory, scrape, export, or save its public video metadata without using the YouTube Data API or downloading media.

norman-else Bundle

Product Recap — git history → product story → slide deck