tronghieu

Run lint.mjs --json, summarize findings by severity, offer to apply --fix for auto-fixable checks (L01/L03/L06/L07/L09), self-check re-run to confirm 0 errors, and surface advisory warnings for user attention. Use this whenever the user asks to "check the wiki", "run lint", "verify the graph", "are there broken links?", "what's wrong with the wiki?", "health check", or "are there missing reverse links?". Also fires for: weekly review requests, before committing wiki changes, after a bulk ingest session, or any time the user wants to know the structural state of the wiki.

Guided wiki page authoring and refactoring: apply user-directed edits to a wiki page with schema validation and bidirectional-edge integrity preserved. Use this whenever the user asks to update, fix, revise, rewrite, correct, or clean up a wiki page — even if they don't say "edit". Also fires for: "fix the reverse link on X", "update the summary for Y", "set importance to 4 on Z", "the lint check found a missing link in ...", or any request that modifies one wiki page without ingesting a new source.

Turn a raw source file into structured wiki pages: source page, concept and person stubs, wiki.mjs-managed graph edges, citation edges, and a log entry. Pauses at four checkpoints (draft, lint, verify, finalize) so you can review before the work is committed to the wiki — accept, revise, or quit at any checkpoint without losing progress. Resumable across sessions. Use this whenever the user says "ingest", "add", "file", "process", "summarize into the wiki", "create a wiki page for", or drops a filename from raw/sources/. Also fires for: "I added a PDF to raw/sources/", "add this paper to the wiki", "parse this article", "what should I do with raw/sources/X?", or any request to bring a new source into the wiki graph. Also accepts Mode B input — paper title, arxiv ID, or URL, without a local file path. Examples: "ingest paper 2604.03501v2", "ingest arxiv:2604.03501", "ingest https://arxiv.org/abs/2604.03501". The skill fetches the PDF automatically in that case. Also handles whole books, theses, and other 50+ p

Check that wiki notes match the sources they cite. Flags statements that appear in a wiki page but are not supported by the cited material, statements that contradict other parts of the same page, and (with --external) statements contradicted by current web search results. Reports findings for the user to review; never edits notes automatically. Run on one page (`/lumi-verify <slug>`), the whole wiki (`/lumi-verify --all`), or only recently-changed pages (`--since <date>`). Use after AI adds new wiki pages, before sharing or exporting the wiki, or as a periodic health check on older pages. Trigger on phrases like "verify", "fact-check the wiki", "is this page accurate?", "check sources", "retro verify". Operates on sources/* pages in v0.9; other page types are skipped.

Ingest one book chapter into the wiki and extract character mentions, theme tags, and plot beats into the graph. Use whenever the user wants to ingest, file, or process a chapter — including phrasings like "I just finished chapter 3", "add this chapter to the wiki", "file chapter 2 of [book]", or "track what happened in chapter 5".

Answer questions from what the wiki already knows, citing the wiki pages behind every claim so the user can open and verify them. Reads only — never changes the wiki unless the user explicitly asks to save the answer as a page. Use this whenever the user asks a question whose answer should come from the wiki — even if they don't say "ask". Also fires for: "what does the wiki say about X", "compare X and Y from what we've ingested", "summarize the wiki's coverage of X", "what concepts relate to Y", "find all sources that mention Z", "what have we learned about X", or any synthesis or retrieval request over accumulated wiki content. If a question could be answered from raw/ but isn't in the wiki yet, surface the gap, list the matching raw/ files so the user can open them directly, and suggest /lumi-ingest instead of reading raw/.

Bootstrap a fresh Lumina wiki workspace: verify config, materialize directory structure, seed wiki/index.md and wiki/log.md, and write the first log entry. Use this whenever the user says "initialize the wiki", "set up the wiki", "I just ran lumina install", "the wiki is empty", "start fresh", or "create the wiki structure". Also fires for: "wiki/index.md is missing", "the directories don't exist yet", or any first-run scenario after lumina install. Run once per workspace. Safe to re-run (idempotent).

Backfill missing schema fields (provenance, confidence) on legacy wiki entries after a Lumina version upgrade. Use proactively when /lumi-check reports L01/L11 findings on multiple entries, when manifest shows legacyMigrationNeeded:true, or when user mentions "lint do", "upgrade", "missing provenance", or "schema gap" after running install.

Facilitate structured brainstorming sessions as a coach and hybrid thinking partner: run divergent ideation on any topic using a library of ~20 named techniques (SCAMPER, Six Thinking Hats, reversal, analogical thinking, question storming, role playing…), one technique at a time, with the user generating ideas first and the AI building on them with clearly labeled additions — then converge, categorize, and deliver a session document with priorities and next steps. Use this skill whenever the user wants ideas or wants to think out loud together — "brainstorm with me", "give me ideas for…", "help me come up with…", "let's explore options for…", "I'm stuck on the name / the features / the campaign angle" — in any language (e.g. Vietnamese "brainstorm cùng tôi", "cho tôi ý tưởng", "nghĩ cùng tôi xem", "gợi ý phương án giúp tôi"; Spanish "ayúdame a generar ideas"; Japanese 「アイデア出しを手伝って」), even when they never say the word "brainstorm". Trigger for open-ended exploration of a topic, product, name, feature set, camp

Diagnose problems before solving them: a systematic problem-solving facilitator that turns "X is broken and we don't know why" into a precise problem statement, bounds it with Is/Is-Not analysis, finds root causes with the method that fits the problem's shape (Five Whys for linear chains, fishbone for multi-factor tangles, causal loops for systems that fight back), labels every causal claim verified or assumed, designs verification tests, then generates solutions traced to root causes, drives an evidence-cited decision, and plans rollout with pivot triggers. Use this skill whenever the user reports something failing, breaking, slowing, or recurring without a known cause — "sales dropped and we don't know why", "this keeps happening", "orders keep arriving late", "why does X keep failing", "find the root cause", "run a post-mortem", "5 whys" — in any language (e.g. Vietnamese "sao cứ bị vậy hoài", "tìm nguyên nhân gốc", "X đang hỏng mà không rõ vì sao"), even when they ask for solutions directly: "give me idea

Act as a disciplined project-management copilot (PM/PMO) that runs the delivery loop — initiation & charter, planning & scheduling, estimation with reference-class checks, risk management (ROAM), honest status reporting, scope change control, stakeholder communication, meetings turned into tracked actions, lessons learned, and portfolio roll-ups — methodology-agnostic (predictive, agile, hybrid) inside a fixed per-project `_project/` workspace where every status color, percent-complete, and estimate declares its evidence. Use this skill whenever the user wants to start, plan, track, rescue, or report on a project — "kick off this project", "make a project plan / timeline / WBS", "estimate how long this will take", "what date can I commit to", "build a risk register", "run a pre-mortem", "write the weekly status report for the steering committee", "the deadline slipped, what now", "turn this meeting transcript into action items and decisions", "prepare the steering-committee pack", "review my project portfolio

Audit the reasoning of any document or argument — a memo, proposal, investment analysis, board paper, article, or the user's own draft — and return its skeleton: claims, evidence, unstated assumptions, logical gaps, fallacies, and what would falsify it, with every finding anchored to exact quoted text. Runs a commit-first coaching loop that asks for the user's own judgment before revealing the audit, tracks their recurring blind spots in a persistent reasoning profile, and turns every audit into a rep that sharpens the user's thinking instead of replacing it. Use this skill whenever the user wants reasoning examined — "audit this argument", "is this analysis sound", "poke holes in this proposal", "review the logic of my draft", "what's wrong with this reasoning" — in any language (e.g. Vietnamese "phản biện giúp tôi", "soi lập luận này", "tài liệu này có lỗ hổng gì", "đánh giá đề xuất này giúp tôi", "góp ý bản nháp của tôi"; Spanish "analiza los argumentos de esta propuesta"; Chinese "帮我审一下这份提案的论证"; Japanese

Act as a disciplined product manager copilot that turns evidence into product decisions and operating artifacts: opportunity backlogs, RICE prioritization with sensitivity analysis, PRDs with story maps and user stories, north-star metrics and OKRs, experiment designs, launch plans with rollback criteria, feedback triage, platform-vs-feature decisions, and light pricing/packaging — all inside a persistent per-product workspace where every number declares its origin. Use this skill whenever the user wants to decide what to build, spec it, or ship it — "write a PRD for…", "prioritize our backlog / these features", "what should we build next", "plan OKRs for the quarter", "define our north star metric", "design an A/B test for…", "plan the launch of…", "triage this pile of customer feedback", "should this be a platform or a feature", "help me manage this product" — in any language ("viết PRD", "ưu tiên tính năng nào", "quản lý sản phẩm", "lập kế hoạch ra mắt", "プロダクト管理", "产品经理"), even when the user never says "p

Facilitate a full design-thinking engagement — Empathize, Define, Ideate, Prototype, Test — as a disciplined facilitator and thinking partner that never fabricates user insight: it designs the research (interview guides, observation plans, experiments with pass/fail criteria), the user brings back real data, and every insight traces to registered evidence. Use this skill whenever the user wants to understand users deeply and design a solution or experience for them — "run design thinking", "understand our users", "design user interviews", "synthesize these interview notes", "build personas", "write How-Might-We questions", "brainstorm solutions for…", "prototype this concept", "design an experiment / usability test to validate…", "our users are churning and we don't know why" — in any language ("tư duy thiết kế", "nghiên cứu người dùng", "phỏng vấn khách hàng", "デザイン思考", "设计思维"), even when the user never says "design thinking". Also trigger when the user drops raw interview notes, transcripts, or survey expor

A C-level strategy advisory board, run as a team of named specialist agents, that takes an executive from a raw strategic question to a defended, board-ready recommendation. Use this skill whenever the user faces a significant business decision or wants strategic analysis — market entry, build-vs-buy, M&A, digital transformation, annual planning, portfolio prioritization, pricing, a big investment, a competitive threat, a turnaround. Trigger on requests like "should we invest in / build / buy / enter…", "develop a strategy for…", "evaluate this opportunity", "make the business case", "stress-test this plan", "run a pre-mortem", or "prepare a board presentation" — in any language, even when the user doesn't say the word "strategy". Also trigger when the user names a board member (Drucker, Porter, Christensen, Graham, Grove, Wack, Taleb, Minto) or asks to convene the board / open a boardroom session.

Conduct rigorous, citation-backed desk market research: quick go/no-go market scans, market sizing (TAM/SAM/SOM), competitor analysis, customer demand signals, and trend/macro (PESTEL) analysis. Use this skill whenever the user wants to research, size, validate, or enter a market — "is there a market for…", "how big is the market for…", "who are the competitors of…", "should I build/launch/sell…", "validate this business idea", "market research for…", "market entry" — in any language and for any country's market (e.g. "nghiên cứu thị trường", "étude de marché", "市場調査", "análisis de mercado"), even when the user never says the words "market research". Also use it when another skill or workflow (strategy-board, design-thinking, a product brief) needs external market facts delivered into its fact base or research folder.