Loading...
Loading...
Found 13 Skills
When you want to read and extract structured notes from a book — PDF, EPUB, MOBI, markdown, .txt, pasted text, or URL to a public-domain work. Reads in chunks (by chapter when a TOC exists, by 50-page blocks otherwise), extracts per-chapter TL;DR + key concepts + quotes + action items + frameworks, and offers to capture to second-brain raw/ as a highlights- file. Four modes — notes (default, chapter-by-chapter), summary (whole-book TL;DR + 3–5 takeaways), quotes (pull-quote highlights only), study (notes + Q&A spaced-rep prep). Triggers on "/read-book," "read this book," "extract notes from this PDF," "what's in this book," "summarize this ebook," "pull quotes from this." Sibling to watch-video (same content-consumption pattern, different medium).
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki pages, update INDEX.md), query (answer from the corpus with trust weighting, save to outputs/), review (triage queue — verify / deprecate / supersede unreviewed and stale captures so wrong info never becomes context), lint (orphans / stale / contradictions / gaps), connect (suggest new wikilinks), search (quick lookup). Structured raw dirs (people/, companies/, meetings/, sops/, decisions/, customer-language/, recurring-questions/, sales-objections/) instead of second-brain's flat type-prefixed raw/. Multi-author aware — every capture stamps author + timestamp + trust status. Optional auto-sync from Fathom/Gong/Granola call transcripts, Slack/email exports, CRM. Defaults to a vault at ${COMPANY_BRAIN_VAULT:-$HOME/Documents/CompanyBrain}/. Triggers on "/company-brain," "/cb," "capture this into the team brain," "log this meeting," "add this person to the team brain," "save this SOP," "compile the company wiki," "query the team brain," "what does the team know about X," "review the company brain," "cull the team brain," "lint the company brain," "who's the internal expert on X."
When you want to model personal financial scenarios — house purchase + rental income (ADU, bedroom rentals, house-hacking), renovation budgets, monthly cash flow forecasts, big-purchase decisions, savings/investment what-ifs. For personal life: a household (you + partner), household budgets, real-estate decisions. v0.1 ships with the house scenario template (purchase + rental scenarios) as the first use case. Architected so other personal-finance scenarios (refi, car, education, retirement, side income) slot in as additional templates. Outputs scenario comparison tables in markdown. Saves every scenario to ~/Documents/personal-cfo/ with an index at ~/.config/makerskills/personal-cfo/archive/ for revisit + comparison. Composes with decide (formalize the call after modeling), deep-research (rental comps, mortgage rates, market data), business-brainstorm (when the scenario is a small business / side hustle), second-brain (capture the analysis to outputs/). Triggers on "/personal-cfo," "model this scenario," "house math," "rental forecast," "monthly cash flow," "what if I rent out the ADU," "compare these housing scenarios," "should we buy this house," "house-hack math," "renovation budget."
When you want to extract content from a video — YouTube, Loom, Vimeo, Riverside, Zoom recording, local MP4, X/IG video, anything yt-dlp supports. Three depth modes user picks per invocation — transcript (just words, fast/free), visual (transcript + ffmpeg frame extraction + Claude vision pass on key moments), multimodal (Gemini native video ingestion if $GEMINI_API_KEY set, else dense Claude vision). Uses MLX-Whisper local on Mac for transcription, falls back to platform-provided transcripts when available (Loom, Riverside, YouTube auto-subs). Saves to ~/Documents/videos/<source>-<slug>-<date>/ and optionally captures summary to second-brain raw/ as call-/meeting-/note-. Triggers on "/watch-video <url>," "watch this video," "transcribe this loom," "analyze this video," "summarize this recording," "key moments from this," "what happened in this video." This skill replaces and broadens the prior youtube-transcript skill.
Turn a process that lives in the owner's head into a written SOP their staff can actually follow: one guided sitting ending in a markdown note with a step-by-step RACI table and a swimlane map filed beside it. Works with or without a second-brain vault. Use when the user wants a process documented as an SOP ("write an SOP", "document this process", "SOP for <anything>", "帮我写 SOP", "把流程变成 SOP"), and when they resume a draft left mid-sitting ("continue the SOP", "接着上次那个 SOP"). NOT for setting up a second brain, building a vault, capturing a business into rooms, weekly maintenance, or giving an AI a persona: those belong to the my-second-brain skill, which is installed and updated separately from this one.
Take a brand from seeded stubs to a real brand foundation inside a second-brain vault: the seven pillars in `<Brand>-Brand-Assets/Brand-Strategy/` carried off `status: empty` one lock at a time, with the 6Cs research and the founder's own convictions filed as dated evidence underneath them. Use when the owner starts or resumes the brand intake ("run the brand intake", "my brand rooms are empty", or a brand pillar stub sends them here), asks to work one pillar by name (positioning, DNA, personality, proposition, relationship, sensory cues, or the style pillar), or asks for the decode research on its own ("6Cs", "founder backbone"). NOT for writing marketing copy or a campaign, and NOT for changing the vault's law (that is breakthrough-vault-guardian).
Design a Lark Base for the user's business through a guided interview: find the one unit of work the business repeats, then derive the tables, links, formulas and a phased build order from the numbers the owner actually wants to see. Ends with a Base Blueprint document plus an acceptance test, ready to hand to whoever builds it. Use when the user wants a database designed for their business ("design my Lark Base", "what tables do I need", "help me build a database for my company", "帮我设计多维表格", "我的业务要怎么建表"), when their existing base has become one giant table and they want it restructured, or when they are unsure whether something should be a field, a select, or its own table. NOT for physically building or editing a Base via API or lark-cli (this skill produces the blueprint; building is a separate job), NOT for turning an already-filled database into reports or dashboards (that is breakthrough-database-to-dashboard), and NOT for setting up a second-brain vault (that is my-second-brain, installed separately).
Use this skill when the user wants to organize, classify, or maintain a PARA-method second brain. Triggers include asking where to file something, distinguishing projects from areas, processing an inbox, setting up a new project, completing or archiving a project, running a monthly review, validating system structure, or finding stale/orphaned content.
Set up a new Obsidian knowledge base with the LLM Wiki pattern. Use when the user wants to create a second brain, initialize a vault, set up a personal knowledge base, or says "onboard". Guides through an interactive wizard to configure vault name, location, domain, agent support, and tooling.
Answer questions against the knowledge base wiki. Use when the user asks a question about their collected knowledge, wants to explore connections between topics, says "what do I know about X", or wants to search their wiki.
Use this skill when managing persistent user memory in ~/.memory/ - a structured, hierarchical second brain for AI agents. Triggers on conversation start (auto-load relevant memories by matching context against tags), "remember this", "what do you know about X", "update my memory", completing complex tasks (auto-propose saving learnings), onboarding a new user, searching past learnings, or maintaining the memory graph - splitting large files, pruning stale entries, and updating cross-references.
Use when users ask to capture conversation decisions, problems, and lessons into persistent notes (e.g. 'harvest', '/harvest', 'save this to second brain', 'document this work').