Skip to main content
Jeden Skill in Manus ausführen
mit einem Klick
dzivkovi
GitHub-Creator-Profil

dzivkovi

Repository-Ansicht von 12 gesammelten Skills in 4 GitHub-Repositories.

gesammelte Skills
12
Repositories
4
aktualisiert
2026-07-23
Repository-Explorer

Repositories und repräsentative Skills

markdown-to-epub
Desktop-Publisher

Convert one or more Markdown files into a clickable, text-to-speech-friendly EPUB for e-readers (Kindle), with an optional branded cover. Use when the user wants an EPUB or ebook from markdown, a briefing or research note as EPUB, or wants to aggregate several markdown artifacts into a single self-contained topical EPUB "book" with an intro and a table of contents (common after a long session or deep research that produced many markdown files that are painful to jump between in a chat UI, and that the user wants to read or listen to on the go). Preserves clickable links, including timestamped video deep-links, and generates a navigable table of contents. Triggers: "make an epub", "turn this into an ebook", "epub for kindle", "convert this briefing to epub", "bundle these markdowns into a book", "combine these notes into one ebook", "make me an ebook of the artifacts you just created".

2026-07-23
read-along
Softwareentwickler

Guided visual walkthrough of accumulated work (a session, a PR batch, an overnight run) as an interactive storybook page plus live browser demos, with a strict stop-and-go protocol. Use after long or autonomous sessions, before demos, or whenever the operator says they cannot comprehend everything that happened.

2026-07-19
slop-check
Technische Redakteure

Fresh-eyes logic-and-slop review of prose and copy. Catches writing that reads like fine English but is logically, mathematically, or definitionally wrong, plus internal contradictions, off-brand drift, and AI tells. NOT a fact-checker - run it as a logic gate AFTER the facts are verified, before publishing. Triggers: 'slop check', 'slop detector', 'logic and slop review', 'check this for AI slop', 'fresh-eyes review', 'is this writing logically sound', 'review my copy before publishing', 'catch contradictions and AI tells', 'gate A'. Works on one file or many (fans out one reviewer per file). Report-only - it never edits.

2026-06-28
branded-docx
Desktop-Publisher

Creates Word (.docx) documents styled with a brand identity from pluggable theme files (coral, remax, jasminahomes, accessible, magma). Use whenever the user wants a branded, professional Word document - reports, briefs, memos, playbooks, CMAs, listing presentations, market reports, or any .docx where visual quality matters. Triggers: 'branded report', 'coral docx', 'remax report', 'jasminahomes style', 'Jasmina Homes', 'magma docx', 'magma report', 'my brand', 'in my style', 'Anthropic style', 'styled document', 'polished report', 'make it look professional', 'convert this markdown', 'with logo', 'add signature block', 'accessible', 'large print', 'big font', 'easier to read', 'for my father', 'for someone older', 'reading glasses', 'elder reader', 'presbyopia'. Also triggers when the user names a brand or asks for 'my usual theme'/'my usual brand'. Reads brands/ to apply the theme. Logos and signature blocks are optional, off by default. All base DOCX rules apply - see the docx skill.

2026-06-19
branded-pptx
Grafikdesigner

Creates PowerPoint (.pptx) decks styled with a brand identity from pluggable theme files (coral, magma, and more over time). Use whenever the user wants a branded, professional slide deck - leadership decks, talk slides, pitch decks, listing presentations, or any .pptx where visual quality matters. Triggers: 'branded deck', 'coral slides', 'coral pptx', 'magma deck', 'magma slides', 'magma pptx', 'my brand deck', 'in my style', 'styled presentation', 'polished deck', 'make slides look professional', 'turn this into slides', 'my usual theme'. Reads brands/ to apply the theme. This is a brand layer on top of Anthropic's base pptx skill - all base pptx technical rules still apply.

2026-06-19
video-intel
Softwareentwickler

Ingest/curate side of the video intelligence plugin. Use whenever the user wants to modify or build the corpus: scan YouTube channels for new videos and generate mind maps via Gemini; transcribe a video (URL or local MP4); run the full mindmap+transcript+concepts pipeline on a local video; extract and normalize concepts into the taxonomy; rebuild the LanceDB hybrid-search index from existing transcripts; clean up title-rotation duplicates; prune YouTube Shorts that polluted the corpus; manage channel configuration. Trigger phrases: "scan channel", "scan all channels", "what's new from [creator]" (with scan intent), "last N days of [creator]", "transcribe this video", "transcribe [creator]'s backlog", "videos I am missing from [creator]", "catch up on [creator]", "fully scan [creator]", "backfill [creator]", "add [channel] to my watchlist", "find duplicate videos", "clean up duplicates", "dedupe my corpus", "the same video got scanned twice", "why do I have two mindmaps for [video]", "creator rotated the title

2026-07-13
translate-bcs
Dolmetscher und Übersetzer

Translate YouTube videos and rich English transcripts into Bosnian/Croatian/Serbian (BCS) subtitles via Gemini. Use this skill whenever the user wants to: translate a YouTube video to Bosnian, Croatian, Serbian, or Serbo-Croatian; produce BCS captions or subtitles for a video; download just the English SRT from a YouTube video with no translation; or translate a context-rich transcript (with on-screen content and speaker labels) into BCS while preserving that context. Trigger phrases include "translate to Bosnian", "translate to Croatian", "translate to Serbian", "Serbo-Croatian subtitles", "BCS subtitles", "BCS captions", "titl na bosanski", "titl na srpski", "titl na hrvatski", "prevedi ovaj video", "prevedi titlove", "download the English SRT", "just give me the SRT", any YouTube URL followed by a request for Bosnian/Croatian/Serbian output, and any request to caption or subtitle a YouTube video in one of those languages. This skill is for subtitle translation only — for English transcription with on-scree

2026-04-28
video-intel-search
Film- und Videobearbeiter

Query a pre-built video corpus (mindmaps, transcripts, concept taxonomy, hybrid search index) produced by the video-intel skill. Use whenever the user wants to: find videos about a topic; look up what a creator said about something; retrieve evidence or quotes from transcripts; browse concepts in the library; synthesize a cross-creator brief ("nugget") grounded in indexed evidence; ask about corpus status (last scan, video counts); summarize a specific video that is already in the corpus; decide if a video is worth watching based on its indexed content. This skill is read-only against an existing corpus - it does not scan, index, or transcribe. Safe to install globally and invoke from any project. Trigger phrases: "find videos about [X]", "search my videos for [X]", "what videos cover [X]", "what did [creator] say about [Y]", "evidence for [claim]", "when did [creator] mention [Z]", "nugget brief on [X]", "consultant brief on [X]", "what do creators say about [X]", "agreements and disagreements on [X]", "synt

2026-04-26
branded-pptx
Grafikdesigner

Turn a markdown document into a branded PowerPoint (.pptx) deck: a title slide from the H1, one content slide per H2, bullets from list items, with a light brand skin (accent colour + footer). Pure-Python (python-pptx), runs on Databricks Free Edition serverless - no Node, no LibreOffice. Use when you need a real .pptx from markdown without a design toolchain. Triggers: 'make a deck', 'markdown to powerpoint', 'branded pptx', 'slides from this doc', 'pptx from markdown'.

2026-07-20
document-insights
Softwareentwickler

Analyze a text document and produce an insights report that pairs EXACT, code-computed metrics (word/character/sentence counts, reading time) with an LLM's interpretive read (sentiment, one-line summary, key themes). Use when you need a grounded document summary where the numbers must be correct, not estimated. Triggers: 'analyze this document', 'document insights', 'sentiment and word count', 'summarize with stats'.

2026-07-17
readability
Technische Redakteure

Grade how readable a text document is by pairing EXACT, code-computed readability metrics (Flesch Reading Ease, Flesch-Kincaid grade level, syllable and hard-word counts) with an LLM's plain-language coaching (who can read this, and the two edits that would lower the grade most). Use when you need a grounded readability assessment where the scores must be correct, not estimated. Triggers: 'how readable is this', 'reading level', 'grade level', 'make this easier to read', 'plain language check'.

2026-07-17
4 von 4 Repositories angezeigt
Alle Repositories angezeigt