Start with the job, then find an open-source answer

paper-explainer reads the full paper, including appendices, tables, and figures, then builds an anchored knowledge graph for a structured explanation. It covers positioning, limitations, methods, experiments, critical analysis, and future work, with quick, full, and reproduction depth levels. Follow-up questions return to the cited section before answering, making it a comprehension tool rather than peer review.

de-ai-writing-skill rewrites supplied prose by replacing connective em dashes, not-X-but-Y constructions, LinkedIn vocabulary, stacked aphorisms, and manifesto-style endings. It keeps the original specifics, dates, numbers, and personal register, and does not add or remove claims. Use it for emails, submissions, blogs, landing pages, and other copy judged by people, not for code comments or internal notes.

zuiti-huabing reads workplace promises such as “take this on now and promotion comes later,” separates encouragement from cost shifting, and produces three reply styles: polite, pointed, and firm. Each response aims to clarify the result, timing, and written record without insults, threats, retaliation, or deciding whether you should stay. It is a scenario-specific package within the broader 嘴替.skill ecosystem.

zuiti-cuihun interprets marriage questions by distinguishing comparison and pressure from genuine parental anxiety. It offers polite, pointed, and firm replies that acknowledge care while keeping your timeline and choices yours. The package is designed for family messages and conversations; it preserves workable boundaries without assuming every relative is acting in bad faith.

Speech Writer transforms an existing talk draft into one of two delivery voices: a commanding Visionary or a first-principles Professor. It preserves every fact, number, and argument, then returns a spoken script and a light beat outline with rough timing. An audience-calibration step and fidelity check flag any added framing or examples, so the skill changes delivery rather than inventing content.

product-design-partner first identifies one of nine lifecycle phases, then routes the work through strategy, discovery, design, validation, shipping, measurement, growth, AI UX, or portfolio modes. It produces concrete artifacts such as assumption maps, interview guides, usability plans with sample-size math, positioning, and rollout metrics. Sourced numbers are cited or labeled illustrative, making it more actionable than generic product advice.

testfrisk inspects branches added by a diff, such as if, case, catch, and throw paths, and checks that a test actually drives execution through each one. It focuses on per-branch risk instead of an average coverage percentage and can write the missing test when the behavior is clear. The skill works across several coding agents and needs no key, account, or extra dependency.

handout-generator reads PDFs, PowerPoint files, screenshots, text, and Markdown, then builds a DOCX handout with explanations, analogies, worked examples, key-point boxes, and a self-test. It adds headings, page numbers, tables, and syntax-highlighted code, and works without Microsoft Word on Windows, macOS, or Linux. The first run may install Python and packages such as pypdf and python-docx.

suite-whisperer reads hotel, dates, confirmation number, room, and booking channel from a screenshot, then distinguishes a contractual loyalty benefit from a courtesy request and drafts the right message in English or Chinese. It verifies the channel and a writable outreach route before producing the card, handles replies and paid offers, and never invents status, anniversaries, or threats. Nothing is sent without per-message confirmation.

rabbit-hole asks up to three playful questions, proposes angles that must pass a Banality Test, and researches them under explicit source rules. It outputs Markdown plus an optional single-file HTML page or landscape magazine PDF, with bilingual slop checks, duplicate-punchline detection, and subject-derived palettes. HTML needs no build step; PDF output depends on weasyprint.

lofi.css adds a paper-scribble look to semantic HTML through one CSS file with embedded handwriting fonts, grayscale styling, annotations, and a 1,745-icon sprite. It uses no JavaScript, dependencies, build step, or external requests, making it suited to early flow discussions rather than polished UI. Its companion Claude skill can generate constrained mockups from descriptions, notes, websites, or whiteboard photos.

generate-walkthrough investigates entry points, journeys, data models, parameters, and boundaries, then writes a self-contained HTML walkthrough whose claims carry file:line evidence. A schema-pinned JSON sidecar can feed the companion extractor for OpenAPI 3.0.3, Postman, and AWS-call artifacts, with unrecoverable details marked as coverage gaps. It is experimental and works best on small to medium codebases or a scoped monorepo slice.

funasr-transcribe runs FunASR and SenseVoiceSmall locally to transcribe m4a, mp3, wav, and other audio, with support for 50-plus languages, voice-activity segmentation, punctuation, filler removal, and automatic device selection. It needs no API key and uploads nothing, but the first transcription downloads roughly 1.2 GB of models and requires Python 3.9–3.11. A follow-up workflow can organize the transcript into meeting notes.

Pixel Surgeon offers Build, Operate, and Deslop modes for designing, reviewing, or tightening interfaces. Its searchable base contains 504 practices and 40 style recipes, while a 12-point exam covers hierarchy, typography, color, spacing, controls, states, and accessibility. It can inspect screenshots, URLs, React components, or Figma frames and return fixes with exact values. It requires Python but no extra library dependencies.

This Claude Code skill audits repositories, database schemas, APIs, and features against Chile’s Law 21.719. It inventories personal data, checks 13 control areas, ranks code-level gaps, and produces a versionable report with file-line evidence, legal references, and remediation priorities. A focused mode covers one feature or pull request; the result is an engineering audit, not legal advice.

sci-figure renders molecules, crystals, slabs, and nanoparticles from common structure data, then composes them with native draw.io elements. Its Python modules cover atom rendering, reusable figure layout, low-level XML building, and export to PNG, SVG, or PDF while keeping the editable source beside each image.

This Claude Code skill examines a digital project under Russian law and returns three views: technical and security risks, a lawyer-ready document brief, and business readiness. It derives processes from existing code or asks questions for a new idea, then highlights priorities and launch blockers without presenting legal advice.

slide-verify checks the text of medical slide decks to confirm that cited papers exist and actually support each number or claim. It then corrects errors, reorders the narrative, splits overloaded slides, and can rewrite dense passages in plain language. It does not read PPTX binaries directly and relies on PubMed MCP plus available search or document sources.