Docs & Writing

dss-time Skill

Perform a lightweight, read-only, text-only Word check only when the user explicitly limits the task to wording, heading hierarchy, simple grammar, obvious consistency, and unresolved placeholders without editing the source, preserving complex formatting, or handling tracked changes, comments, complex tables, images, headers, footers, or visual layout. Do not use for an unqualified Word or document review; use document-review for holistic structure, logic, facts, revisions, formatting, tables, links, comments, or rendered DOCX verification. 仅在用户明确把任务限定为基础、轻量、只读、纯文本检查时，检查 Word 文档的文字、标题层级、简单语法、明显一致性和未解决占位符，不编辑源文件、不保留复杂格式，也不处理修订痕迹、批注、复杂表格、图片、页眉页脚或视觉版式。不得用于未限定范围的通用 Word 或文档审查；整体结构、逻辑、事实、修订、格式、表格、链接、批注或 DOCX 渲染验证应使用 document-review。

shuwanito Bundle

Family communication and partnership specialist for educational settings. Use when designing family-school communication features, creating parent report templates, building mediation workflows, improving family engagement, or proposing accessible communication channels. Focused on clear, solution-oriented family-school partnerships.

shuwanito Bundle

Multilingual and cultural bridge specialist for educational content. Use when you need educational translations, bilingual materials, or culturally-adapted content. Ensures translations preserve educational intent and cultural sensitivity rather than being literal word-for-word conversions.

zeenie-ai Skill

Output human-readable text in pretty formats instead of raw markdown or code blocks

jordangaston Bundle

Build and critique static image ads for paid social — the three-layer method (strategy, design, copy), the seven core formats, and the copy mechanics behind winning image creative. Use this skill whenever the user is making, reviewing, or troubleshooting static ads, image ads, banner creative, or asks why their statics aren't performing. Also trigger when the user mentions ad formats (infographic, headliner, benefits callout, comparison, us-vs-them, before/after, transformation, grid, text-only, founder's letter), visual hierarchy in ads, ad headlines, ad copy for images, creative diversity, or when they say 'video is the only thing that works for us,' 'statics are just for retargeting,' or want to turn a working message into more creative. Trigger even when phrased casually ('make me an ad for X', 'is this ad any good', 'roast my creative', 'we need more ad variations') and even if they never say the word 'static.'

jordangaston Skill

Evaluate the quality of a long-term investment — career moves, startup ideas, business opportunities, job changes, personal brand bets, or any major commitment of time/money/reputation lasting months or years. Use this skill whenever someone asks things like "should I take this job," "is this startup idea worth pursuing," "should I invest in X," "evaluate this opportunity," "is this a good career move," "help me decide between these paths," or any variant of "is this investment worthwhile." Also trigger when someone describes a big decision they're weighing and wants a structured way to think about it, even if they don't use the word "investment." This includes side projects, business pivots, market entries, and major life bets. Based on Jason Cohen's investment evaluation framework (longform.asmartbear.com/investment).

jordangaston Bundle

Write UGC hooks that stop the scroll and testimonial scripts that sell, for AI-generated UGC clips (VEO, Sora, Kling). Use this skill whenever the user wants to write, script, batch, critique, or fix UGC ads, spokesperson scripts, testimonial scripts, or hooks — including requests like "write hooks for this product", "write me a UGC script", "give me 3 hook angles", "why isn't my UGC converting", "make this sound less like an ad", or any mention of hook lines, the first 3 seconds, scroll-stopping openers, skeptic-to-believer testimonials, the 5-beat script, or scripts for faceless/AI creator clips. Also trigger when the user pastes a product and asks for ad copy a real person would say to camera, even if they never say the word "UGC."

jordangaston Skill

Run a full feature sprint from user stories to verified, demoed, shipped code with minimal supervision. Use when the user hands over a set of user stories / acceptance criteria and wants them built end-to-end overnight (or unattended): analyze reference material, ask ONE batch of clarifying questions, (optionally, on request, hold one design review), write per-story specs, run a pre-mortem, implement without stopping (decide-and-log every blocker), demo each story, and write a sprint report. Trigger on "run this sprint", "build these stories overnight", "complete this sprint autonomously", "/autonomous-sprint", or any hand-off of a story list with an expectation of unattended completion.

jordangaston Bundle

Structure writing and thinking using Barbara Minto's Pyramid Principle — lead with the answer, group supporting ideas, and open with a Situation-Complication-Question-Answer story. Use this skill whenever the user is writing or restructuring a memo, report, email, executive summary, recommendation, proposal, board update, slide deck, or any document where the order of ideas matters; whenever they ask how to organize, structure, or sequence their thinking; or whenever they say things like "make this clearer," "bottom line up front," "BLUF," "this is rambling," "tighten this up," "what's my main point," or "how should I lay this out." Also trigger for consulting-style deliverables, problem analysis, and any time a wall of points needs to become a clear argument.

jordangaston Bundle

Create high-performing faceless TikTok slideshows (Photo Mode carousels) using the hook/build/payoff structure. Use this skill whenever the user wants to create, write, script, critique, or improve TikTok slideshows, photo carousels, slide posts, or faceless TikTok content — including requests like "write me a slideshow about X", "give me hooks for a carousel", "why isn't my slideshow getting views", "plan my TikTok content", or any mention of hook slides, build slides, payoff slides, swipe-through rate, or faceless accounts. Also trigger when the user asks for slide-by-slide copy, slideshow ideas for a niche, or a TikTok carousel posting strategy, even if they never say the word "slideshow."

jordangaston Skill

Evidence-based rules for what actually moves short-form video performance (TikTok, Reels, Shorts), distilled from Layers Research's 2026 TikTok Posting Report (23M videos, 13.3T views). Use this skill whenever the user asks about posting strategy mechanics — best time to post, posting frequency, how many posts per day, spacing, taking breaks, video length, slideshows vs. videos, caption length, hashtags, resolution/aspect ratio, deleting flops, shadowbans, follower counts vs. reach, or what to post after a viral hit or a flop. Also trigger when the user repeats posting folklore ("post at 6pm", "don't post twice a day", "keep it under 30 seconds", "the algorithm punishes X") so their plan can be checked against the data, or when auditing a posting schedule or content calendar.

jordangaston Skill

Source and curate scene images for a faceless persona account (TikTok slideshows, IG carousels) so every published image reads as a real photo the persona took herself. Covers candid-biased scraping queries, dimension forensics to reject AI/stock images, the persona plausibility test (no stray arms, foreign UIs, or strangers' names), per-deck camera-roll cohesion, targeted PII retouches, and deterministic text-overlay rendering via headless Chrome (TikTok-style caption bubbles without AI image editing). Use this skill whenever the user wants to find, select, vet, or prune background/scene images for a virtual persona or faceless content account — including 'find images for this slideshow,' 'does this image work for our character,' 'these look like stock photos,' 'build a scene library,' 'add text overlays to slides,' or auditing an existing image library for authenticity.

jordangaston Bundle

Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.

x-cmd Skill

Comprehensive rule-based check. Triggered by "/check [target]" to evaluate all source files against project rules and report every violation.

x-cmd Skill

Multi-phase project assessment with scoring. Triggered by "/assess" to evaluate project health across dimensions and generate a comprehensive report.

andresnator Bundle

Expert in pedagogical book chapter synthesis. Use this skill WHENEVER the user wants to summarize a book chapter, analyze text or document content, study a chapter, extract key ideas from a reading, or when they mention words like "summary", "chapter", "book", "analyze this text", "summarize this", "cornell", "TL;DR" of long-form content. Also trigger when the user uploads a PDF, EPUB, or document and asks to understand or study it in parts. También se activa en castellano: "resumen", "resumen del capítulo", "resumir esto", "resumir el capítulo", "analizar este texto", "capítulo", "libro", "ideas clave", "resumen del libro", "estudiar el capítulo", "síntesis", "notas cornell", "extraer ideas principales", "dame un resumen", "qué dice este capítulo", "resumir documento", "analizar lectura".

andresnator Bundle

Trigger: slidev, slides, presentation, deck, retro console, CRT, terminal theme. Build a Slidev presentation with a retro-console visual identity — three packaged themes (crt-phosphor, dos-terminal, synthwave-arcade), each with day and night schemes — themed Mermaid diagrams, and a mandatory PNG-export verification loop that checks every slide for overflow. También se activa en castellano: "hazme una presentación con Slidev", "presentación estilo consola retro".

andresnator Skill

Trigger: Cornell note, lesson notes, standalone learning summary. Transform supplied material into self-contained Markdown inline.

blacklanternsecurity Skill

Post-engagement lessons-learned retrospective. Reads the engagement directory, analyzes skill routing decisions, identifies knowledge gaps and missing skills, and produces an actionable improvement report.

blyatiful1 Bundle

Design and build the cart surface and its state — the add-to-cart feedback moment (never a full page reload), the slide-over drawer vs dedicated /cart page decision, line-item anatomy with quantity steppers and remove-with-undo, an empty cart designed as a merchandising moment, honest server-computed running totals with a free-shipping progress bar, exactly ONE cross-sell slot under the anti-three-cards rule, and optimistic updates wired to server actions. Three named variants (slide-over drawer, dedicated page, mini-cart popover). Invoke in Phase 6/7 whenever a commerce build needs a cart — add-to-cart, mini-cart, cart drawer, /cart page, quantity steppers, free-shipping bar, or "nothing owns the cart" — or when the user says "add a cart", "mini cart", "cart drawer", "the cart reloads the page", "update the cart total", or "cross-sell in the cart".

blyatiful1 Bundle

Print-derived page furniture for genuinely long-form pages — a scroll-linked running folio (current-section head), a marginal read-o-meter (reading time + percent as small-caps type, never a progress bar), a sticky scrollspy section rail, Tufte-style footnote/sidenote gutters in a reserved margin column, and marginal pull-quotes — all set in layout-grid's outer column and degrading to inline superscript + native popover below the gutter breakpoint. Invoke in the Build phase for essays, case studies, docs, reports, or annual-report pages (never a landing page), or when the user says "running header", "reading progress", "table of contents rail", "scrollspy", "sidenotes", "footnotes in the margin", "Tufte sidenotes", "pull quote", or "margin notes".

blyatiful1 Bundle

Design the print stylesheet (@media print) as a real surface for document-shaped pages — hide nav/consent/chrome, expand meaningful link URLs, control page breaks, set print type and @page margins, and economize ink — with a DACH focus on the Impressum, AGB, and Datenschutzerklärung, invoices, and quotes that German business practice routinely saves to PDF for compliance records. Invoke in the craft phase for any legal page, engagement letter, invoice/order confirmation, quote, case study, or annual report, or when the user says "the print version looks broken", "make it print/PDF cleanly", "print stylesheet", "save as PDF", "Impressum/AGB/Datenschutz to PDF", or "print-to-PDF".

devexpress Bundle

Build WPF property editors with the DevExpress PropertyGridControl — bind any object via SelectedObject (or multiple via SelectedObjects), define which properties show via PropertyDefinition, edit collections inline via CollectionDefinition (with NewItemInitializer for add/remove), group properties via [Category] attribute and CategoryDefinition (flat / Visible / Tabbed modes), and control expandability of nested objects via TypeConverter / ExpandableObjectConverter / AllowExpanding. Use when building visual designers, settings dialogs, diagram property panels, report designers, or any view that lets a user inspect and edit an arbitrary object's properties at runtime. Also use when someone mentions "PropertyGridControl", "PropertyDefinition", "CollectionDefinition", "CategoryDefinition", "ShowCategories", "ShowProperties", "ExpandableObjectConverter", "AllowExpanding", or "dxprg:". Covers .NET 8+ and .NET Framework 4.6.2+.

devexpress Bundle

Build .NET applications with the DevExpress PDF Document API for creating, reading, editing, merging, signing, and extracting content from PDF files programmatically. Use when working with PDF documents, PDF generation, PDF graphics API, interactive PDF forms, digital signatures, PDF/A compliance, text extraction, image extraction, PDF merging/splitting, bookmarks, hyperlinks, annotations, or XMP metadata. Also use when someone mentions "DevExpress PDF", "PdfDocumentProcessor", "PdfGraphics", "DevExpress.Pdf", "create PDF in C#", "merge PDF .NET", "sign PDF", "extract text from PDF", or asks about any PDF automation with DevExpress. Covers both .NET and .NET Framework.

devexpress Bundle

Create, load, modify, secure, and print PDF documents using the new DevExpress.Docs.Pdf API — a modern object-oriented DOM approach for .NET. Use when building .NET applications that need to programmatically generate or edit PDF files using the new DevExpress PDF Document API (CTP). Also use when someone mentions "DevExpress.Docs.Pdf", "new PDF API", "PdfDocument class", "pdf fragment", "pdf pages collection", "pdf form fields", "pdf redaction", "pdf structure tree", "tagged pdf", "pdf/ua", "pdf encryption", "pdf annotations new API", or asks to migrate from PdfDocumentProcessor to the new API. Covers both .NET and .NET Framework.

devexpress Bundle

Expert skill for creating and modifying DevExpress XtraReport layout code in Visual Studio and JetBrains Rider — writing and editing *.Designer.cs files, InitializeComponent structure, bands, controls, expression bindings, styles, parameters, and data source wiring. Use this skill whenever someone asks to create a DevExpress report, add controls to a report, modify a *.Designer.cs file, fix designer-generated code, work with XRTable/XRLabel/XRPictureBox/bands, set up data binding expressions, define report parameters, or troubleshoot why a report won't open in the Visual Studio or JetBrains Rider designer. Also use when someone asks about XtraReports InitializeComponent patterns, report band hierarchy, Criteria Language expressions, summary functions, or JetBrains Rider report designer limitations.

devexpress Bundle

Build .NET applications with the DevExpress Presentation API for creating, reading, modifying, and exporting PowerPoint presentations programmatically without Microsoft Office. Use when working with .pptx files, slides, shapes, text, tables, slide masters and layouts, themes, slide backgrounds, notes, headers/footers, or exporting presentations to PDF. Also use when someone mentions "DevExpress Presentation", "Presentation API", "DevExpress.Docs.Presentation", "create PowerPoint in C#", "pptx automation .NET", "merge presentations", or asks about any PowerPoint/presentation processing with DevExpress. Covers .NET.

devexpress Bundle

Build .NET applications with the DevExpress Word Processing Document API for creating, reading, modifying, and exporting Word documents programmatically without Microsoft Office. Use when working with .docx, .doc, .rtf, .odt, .txt documents, paragraphs, tables, styles, mail merge, headers/footers, fields, track changes, or document conversion. Also use when someone mentions "DevExpress Word", "Word Processing Document API", "RichEditDocumentServer", "DevExpress.XtraRichEdit", "create Word document in C#", "docx automation", "mail merge .NET", or asks about any Word/document processing with DevExpress. Covers both .NET and .NET Framework.

bm629 Bundle

Use when surveying the PUBLISHED user-research evidence for a product's design questions BEFORE an interface is designed — deriving a research vocabulary map, executing ONE search angle across scholarly indexes, preprint servers, practitioner-research corpora and standards-body findings, deep-reading ONE source into the findings it contains, or synthesising the evidence register and report. One source yields N finding-records, because how many findings a paper holds is only knowable after the read. Certainty uses GRADE's four-level vocabulary assigned BY RULE and re-derived by the validator; transferability stays a separate field, because excellent evidence from another population is strong evidence and weak guidance at once. Keywords: user research prior art, HCI literature, usability evidence, published findings, evidence synthesis.

bm629 Bundle

Use when judging a produced open-source prior-art SEARCH, EXTRACT, or SYNTHESIS artifact — a keyword map (typed search vocabulary), a per-angle search output (coverage cells + candidate repositories), a per-repo extraction, or a synthesis report + borrow-index — to decide whether it is sound enough to feed the survey's downstream stages. An acceptance gate, not authoring: a twenty-two-condition bar single-sourced with the producer, covering the keyword map and search (1–11), proportionality (12), extraction due-diligence (13–18) and synthesis (19–22), delegating the deterministic schema checks to the producer's validator. Emits exactly one verdict — a terminal VERDICT: approve|revise line, or the caller's named equivalent — with condition-named findings. Review-only; no false-revise — a thin-but-honest result meets the bar. Keywords: prior art review, keyword map review, search coverage review, extraction review, synthesis review.

bm629 Bundle

Use when surveying the competitive and market landscape for a product BEFORE it is built — deriving a market vocabulary map (category, capability, job-to-be-done, audience and seed- product terms with typed expansions and exclusion terms), executing ONE search angle across alternatives directories, review corpora, app stores, package registries, corporate and funding records, product graveyards and practitioner discussion, deep-reading ONE competing product into a dated record, or synthesising the competitor register and report that downstream document authoring consumes. Produces schema-validated artifacts whose coverage grid records every query as run, so a market with no competitor is distinguishable from a search that never ran. Dates every commercial fact and keeps a dead product as evidence. Keywords: market research, competitor analysis, competitive landscape, competitive intelligence, market prior art, alternatives, substitutes.

bm629 Bundle

Use when reviewing an artifact produced by regulatory-prior-art-survey — a regulatory scope map, one angle's search output, one instrument's extract record, or the regulatory register and its report — and deciding whether it can be built on. Judges numbered conditions covering canonical terms the corpus uses, the sector receipt, per-angle verdicts in both directions, verbatim query recording, the recorded zero, cause evidence with observable status, the date separations, authority as a rank and binding force as an orthogonal fact, and the claim-versus-quote boundary that fabricated citations cross. Also judges whether a paywalled clause was paraphrased, whether a merge crossed a non-comparable dimension, and whether a conflict was escalated rather than resolved. Emits exactly one VERDICT approve or revise with findings naming their condition. It does not revise a thin-but-honest result. Keywords: regulatory review, compliance survey review, citation check, survey quality gate.

bm629 Bundle

Use when judging a finished user-research prior-art artifact before it is accepted — a research vocabulary map, a per-angle search output, an extract container, or the evidence register and report. An acceptance gate, not authoring. Judges a single-sourced bar: a recorded zero is distinguishable from an unreachable source; a claim stays within what its method could measure; recorded facts match the source; transferability carries a weighable reason and is never folded into certainty; numbers are the source's own; findings in one container are genuinely distinct; population and platform describe the study rather than the project; convergence is across INDEPENDENT sources; certainty is never averaged; absence is phrased as a search result. Approves a thin-but-honest result and revises only on a named, unrecorded gap. Emits exactly VERDICT: approve|revise plus actionable findings.

bm629 Bundle

Use when judging a finished market and competitive prior-art artifact before it is accepted — a market vocabulary map, a per-angle search output, an extract record, or the competitor register and report. An acceptance gate, not authoring. Judges a single-sourced bar: a recorded zero is distinguishable from an unreachable source and from one excluded on its terms; queries are reproducible as run; ratings carry their denominators; vendor claims are attributed rather than asserted; a tier is argued from capability overlap rather than fame; point-in-time facts are dated; a dead product is recorded as dead with its date; a register row says what its record says; white space is phrased as a search result. Approves a thin- but-honest result for a thin market and revises only on a named, unrecorded gap. Emits exactly VERDICT: approve|revise plus actionable findings. Keywords: competitive analysis review, market research review, competitor set critique.

bm629 Bundle

Use when reviewing an artifact produced by platform-ecosystem-prior-art-survey — a vocabulary map, one angle's search output, one mechanism's extract record, or the decision index and its report — and deciding whether it can be built on. Judges numbered conditions covering slug provenance, applicability verdicts, verbatim query recording, the zero-hit cell, cause evidence on every unreached source, enumeration framing, and the anecdote-aggregation trap — plus whether a reversibility call is right, whether an authority band means the platform PRESCRIBES it, and whether a divergence was presented rather than resolved by dropping a source. Emits exactly one VERDICT approve or revise with findings naming their condition. It does not revise a thin-but- honest result: on this corpus most marketplaces publish no ranking function, and recording that is the expected outcome. Keywords: prior-art review, platform ecosystem review, survey quality gate, coverage review.

equinor Bundle

Select and apply prose_english or standard_engineering_english only when generating a final engineering report or summary. USE WHEN: the reporting step is ready to compose final narrative content, or the user explicitly requests either writing style for a generated document. Do not activate during analysis, working notes, ordinary chat, code generation, or source extraction.