Docs & Writing

liyu0524 Bundle

Manage Google Docs and Google Drive with full document operations and file management. Includes Markdown support for creating formatted documents with headings, bold, italic, lists, tables, and checkboxes. Also supports Drive operations (upload, download, share, search).

liyu0524 Bundle

End-to-end paper research support for arXiv/literature surveys, reproducibility-focused paper shortlisting, and experiment design. Use when you need to (1) search arXiv with complex queries, (2) download PDFs, extract text/sections, and fetch BibTeX, (3) dedupe/cluster results into a structured report, and (4) turn findings into a lit-review plan, benchmark/evaluation suite, and representation/probing experiment checklist (e.g., implicit reasoning, hidden-CoT, multilingual reasoning, cross-lingual alignment).

llnl Bundle

Review SUNDIALS pull requests using the repository’s correctness, numerical, API, documentation, testing, portability, and maintainability review patterns. Use for GitHub PR reviews or when asked to review changed SUNDIALS source, bindings, build files, examples, or documentation.

dkyazzentwatwa Skill

Universal Markdown-to-Apple-Pages formatting skill for Apple Flow. Use when converting `.md` files into polished `.pages` documents with accurate structure (headings, lists, tables, code blocks, links) and clean business-ready styling.

egermano Bundle

Clean up local git branches that have been removed from the remote repository. Use when the user wants to tidy up their local git branches, remove stale branches, clean up after merging PRs, or mentions 'cleanup branches', 'remove old branches', 'prune local branches', 'git branch cleanup'. Safely handles uncommitted changes, preserves local-only branches, and provides a detailed report.

emiliosheinz Bundle

Root-causes complex bugs through a structured loop and saves a verified fix proposal — it diagnoses, it never fixes. Builds a fast deterministic feedback loop, reproduces, then probes ranked falsifiable hypotheses with parallel subagents and confirms the cause adversarially before writing the report. Use when a bug, error, crash, exception, failing or flaky test, regression, or unexplained behavior needs root-causing — especially when it is intermittent, subtle, cross-system, or resisted a first fix.

emiliosheinz Bundle

Creates Architecture Decision Records (ADRs) — concise, durable documents that capture the context, decision, and consequences of significant architectural choices so future team members understand *why* things are the way they are. TRIGGER when: the user asks to create or write an ADR, document a decision, record why something was chosen, capture an architectural decision, or preserve the reasoning behind a finalized technical choice. SKIP for: decisions that have not been made yet (use `/create-rfc`), implementation planning or breaking work into tasks (use `/forge plan`), or general documentation that is not a decision record.

evindunn Bundle

Improve code documentation by adding useful logical block comments, docstring-style comments for functions/classes/modules, and top-level file comments. Use when asked to document code, add comments, improve docstrings, explain entrypoints, make code easier for engineers or future AI agents to scan, or perform documentation passes across source files in any programming language.

evotecit Bundle

Build and maintain PSPublishModule/PowerForge documentation pipelines, including generated cmdlet docs, external help XML, and about-topic source workflows.

akiru6 Bundle

从中国增值税发票（图片、PDF或OCR文本）中提取结构化JSON数据。

animaresearch Bundle

Analyze folders of Markdown/text research notes, Obsidian vaults, paper cards, invention notes, or memory exports as a practical knowledge map. Use when asked to find center topics, noisy or low-signal notes, possible contamination, overgrown topic groups, orphan notes, cleanup actions, or a useful public knowledge-hygiene workflow.

appsflyersdk Skill

Run or triage AppsFlyer Cordova E2E/smoke via ./scripts/af-scenario-runner.sh, sibling E2E copy, smoke dir, and JSON reports. Use for local reproduction, CI log triage, or report summaries.

argos-ci Skill

Render a syntax-highlighted code card on the Argos brand background with scripts/code-card.mjs. Use whenever a social post, changelog, or slide needs a snippet shown as an image — never paste a raw terminal screenshot or use a third-party service.

artifact-kit Skill

Generate route-aware bbox review JSON for PPT slide images using the DeckKit PPT replica bbox schema, hierarchy, route, editability, and granularity rules, without Workbench finalization or PPT reconstruction.

artifact-kit Bundle

Reconstruct a reference slide image into an editable PowerPoint using DeckKit, route-aware bbox JSON, optional browser Workbench review, lucide/icon semantic reconstruction, source crops, and image-generation prompts for hard bitmap assets.

artifact-kit Bundle

Reconstruct SVG-ready PPT slide assets from bbox/crop inputs using Iconfont reference search, golden base SVG selection, explicit SVG assembly, batch SVG preview QA, and manifest output.

mizchi Skill

Add a new test-result adapter to flaker (parses an external report format into TestCaseResult[]). Use when the user asks to "add a flaker adapter for <X>", "make flaker import <some format>", "support <some test runner> in flaker import", or otherwise extends `flaker import --adapter <name>` with a new format. Encodes the file layout, registration step, test pattern, CHANGELOG convention learned from the chaosbringer adapter (#79).

mondaycom Skill

Generates structured project status reports from monday.com - a customizable AI work platform with dedicated products for work management, CRM, dev, service, and campaigns. Surfaces overdue items, blockers, workload distribution, and recent activity across one or more boards. Use when user asks for "project status", "board summary", "what's overdue", "status report", "how's the project going", "weekly update", "board overview", "progress update", or "team workload".

mudlet Skill

Fuzz Mudlet's parsers and scripting API for crashes and undefined behaviour: build a sanitizer binary, run the seeded in-process fuzzers with fresh seeds, extend them to new surfaces, triage what falls out. Read before triaging any sanitizer report.

nomicfoundation Bundle

Migrate a Solidity project from Foundry to Hardhat 3. Maps `foundry.toml` to `hardhat.config.ts`, converts dependencies and imports, gets compilation and Solidity tests passing, and produces a migration report with feature-parity gaps and a cleanup checklist.

numerai Skill

Write a complete Numerai experiment report in experiment.md (abstract, methods, results tables, decisions, next steps) and generate/link the standard show_experiment plot(s). Use after running any Numerai research experiments, or when a user asks for a “full report”, “write up”, “experiment.md update”, or “generate the standard plot”.

lattifai Skill

Use when transcribing audio/video to text with timestamps, speaker labels, and chapters. Supports YouTube URLs and local files. Produces structured markdown output.

lfortran Skill

End-to-end fix of an LFortran bug, from issue to review-ready pull request. Takes an issue (most commonly a GitHub issue number or URL at lfortran/lfortran, but also a pasted snippet, error report, or third-party failure), then orchestrates fresh subagents that run repro-issue, then create-mre and fix-mre repeatedly (one MRE per underlying bug) until the original issue is fully fixed, open a draft PR from the user's fork with `gh`, review it with pr-review, and keep fixing CI failures and review blockers until the PR is green and clean, then add the Tests::Run-Exhaustive label, fix any exhaustive CI failures, and mark it ready for review. Unrelated pre-existing bugs found along the way are filed as separate issues and linked from the PR. Triggers: fix issue, fix github issue, issue to PR, resolve issue, send PR for issue, end-to-end fix.

lihaoze123 Bundle

Use when creating structured best practices guides, organizing technical documentation, or establishing reference materials for teams or agents

linkupplatform Bundle

ONLY when the user explicitly wants a thorough, exhaustive, or comprehensive multi-source investigation or report that can run for minutes — due diligence, market landscapes, "compare X across many entities", verified fact-finding. Slower and more expensive than linkup-search. For normal lookups and research use linkup-search instead; for bulk records from a page use linkup-extract. Uses Linkup's async /v1/research REST endpoint. Requires LINKUP_API_KEY.

linuxfoundation Skill

Post-commit empirical-pattern review for lfx-v2-email-service. Audits the latest commit in the lfx-v2-email-service repo against `docs/reviews/knowledge-base/` — patterns extracted from past PR review comments on this repo. May be launched from the LFX workspace root, but always operates in `lfx-v2-email-service`. Findings are gated by KB matches: every finding must quote a pattern entry; unsourced findings are dropped. Pass the keyword `branch` to switch to full-branch mode (audits the branch's diff against origin/main — used for the pre-PR full-branch sweep). Renders a markdown review. Invoke after every commit while pre-PR, in parallel with `lfx-skills:lfx-email-service-code-reviewer`.

llnl Skill

Use when updating Sphinx documentation, changing docs/source/conf.py, adding Sphinx extensions, or validating documentation builds for this repository.

luis63e Bundle

Trigger: Google Slides, decks, slides, charts, thumbnails, create/template. Verify structure and visual limits.

luizsiqueira-eng Bundle

Segundo cérebro do dia a dia em um vault Obsidian (markdown com wiki-links): tudo que você aprende trabalhando — investigações, debugs, decisões, reuniões, gotchas de sistemas e integrações, aprendizados — registrado com data e ligado por links. CONSULTAR antes de investigar, decidir ou responder ('o que já sabemos sobre X?') e ALIMENTAR ao fechar uma investigação, diagnóstico, decisão ou reunião. Na primeira execução cria o vault (estrutura, índice, templates) e oferece instalar o Obsidian. Invocar ao iniciar debug/investigação, ao encontrar comportamento estranho já visto, ao fechar um diagnóstico, ao tomar decisão de arquitetura, ou quando pedirem para 'registrar no cérebro', 'anotar isso', 'consultar o cérebro', 'o que já sabemos sobre X'.

luochang212 Bundle

Markdown to PDF Converter

luochang212 Bundle

Use whenever the user wants to understand, evaluate, or analyze a GitHub repository, even without the word "analyze", or when they simply paste a github.com link and ask about it. When the question is asked inside a local repo directory, analyze that directory's own repository by default (no link required). Covers basics, purpose, tech stack, usage examples, and architecture.

luongnv89 Bundle

Prepare French 2025 income-tax declaration filed in 2026: collect inputs/PDFs/profiles, fetch official rules, compute IR, render markdown. Don't use for tax optimization, filing/submission, non-France tax, or impots.gouv.fr login.

phodal Skill

Generate comprehensive documentation from code

pixeval Skill

Pixeval 国际化资源维护规范，涵盖用户可见字符串、JSON/Markdown 资源、XAML/C# 引用、BlockedContent 共享文案、非默认语言增删规则以及 Language.tt 生成验证。Use when adding, moving, removing, or changing localized text in Pixeval.

posit-dev Bundle

Review and improve Python docstrings for Great Docs API reference generation. Covers NumPy and Google style conventions, parameter documentation, return types, examples, cross-references, and Great Docs directives (%seealso, %nodoc). Use when auditing, writing, or fixing docstrings in a Python package.

postplusai Skill

Design and critique visual hooks for TikTok, Reels, Shorts, slideshows, and AI-generated media workflows. Use when the first frame, first slide, or first 1-3 seconds need a stronger reason for the viewer to keep watching.