Analyze Chinese notes, articles, manuscripts, and digital card-box material with FIRE 2.0: Full-D numbering, Index keyword webs, Route thinking paths, and Evolution over time. Use when Codex needs to prepare material for semantic search, turn temporary notes into permanent or project notes, build table-of-contents/index/search structures, create compact Chinese FIRE cards, or maintain this skill's original discussion thread provenance.
npx skills add https://github.com/twhsi/skills --skill fire-analysis-card
Transform Chinese notes, short articles, manuscripts, or book-system material into semantic-search-ready digital card-box structure using FIRE 2.0:
F = Full-D: give every temporary note a stable full number, then refine it into a permanent note; if publishing, turn it into a project note with complete book/project numbering.I = Index: build keyword indexes and re-entry points so a tree-shaped manuscript can also become a spider-web knowledge structure.R = Route: design thinking routes through the material so cards can support narrative, search paths, and the next creative card.E = Evolution: track how notes evolve through time grids, plans, reviews, and conversations with the digital card box.Strategic frame:
> 戰場上核心戰略只有一個:火力與移動。
> 不移動,局勢就由別人決定。不開火,就會被別人釘在原地。
> ─ Joel Spolsky
FIRE 2.0 treats Full-D and Index as search firepower, and Route and Evolution as knowledge movement. The goal is not just to summarize source text, but to prepare it for table-of-contents search, exact keyword search, and semantic search.
2.0Full-D / Index / Route / EvolutionFact / Index / Relation / EncyclopediaEolution, normalize it to Evolution unless quoting the source.019ed5d7-9b24-7581-b98e-9e29027e85f3各章節內容Desktop的改善 目標 $fire-analysis-card $pdca $project-...2026-06-17/Users/twhsi/.codex/session_index.jsonl has updated_at: 2026-06-17T13:49:43.934892Z.fire-analysis-card with pdca and project-note-json-to-epub to produce a Skill-ecology EPUB, placing FIRE as the card-analysis layer in the user's Skill ecosystem.When the user asks to find, verify, or update the original discussion thread for this skill:
list_threads with query fire-analysis-card, then read thread 019ed5d7-9b24-7581-b98e-9e29027e85f3./goal prompt that invokes $fire-analysis-card, $pdca, and $project-note-json-to-epub together.rg for fire-analysis-card, FIRE Analysis Card, 知識成頁, or Fact 事實 in ~/.codex/session_index.jsonl, ~/.codex/archived_sessions, and ~/Documents/Codex.待證.text code block.Full-D / Index / Route / Evolution. for visual alignment.Full-D 全編號.◎.待編, 待證, 推論, or 需補例.Ⓕ Full-D 全編號: assign stable IDs to temporary notes, convert them into permanent notes, and when publishing, produce project notes with complete part/chapter/section/item numbering.Ⓘ Index 索引: create keyword indexes, categories, tags, questions, aliases, and retrieval handles. For book-scale material, prefer eight major keyword categories and 64 core keywords when the source supports it.Ⓡ Route 路徑: build thinking paths through the material. Routes can follow table of contents, keyword webs, narrative arcs, or target-person formulas, and should help generate the next card.Ⓔ Evolution 演化: show how cards change through present notes, daily plans, weekly plans, yearly plans, life plans, reviews, and Mandala-style time grids until the card box becomes a dialogue partner.Use the flow:
Raw Notes -> Full-D -> Index -> Route -> Evolution -> Semantic Search -> AI Dialogue
Copy this template first, then replace the phrases.
【Ⓕ Full-D 全編號】
編號:____
定稿:____
出版:____
↗ ↘
【Ⓘ Index】 中【◎核心】 【Ⓡ Route】
關鍵字網 ◎____ 思考路徑
──────── ──────── ────────
____ ____ ____
____ ____ ____
____ ____ ____
↖ ↙
【Ⓔ Evolution】
當下:____
計劃:____
對話:____
Ⓕ Full-D: the numbered source tree: temporary note, permanent note, project note, and full part/chapter/item path.Ⓘ Index: the keyword web: categories, aliases, questions, and exact-search handles.Ⓡ Route: the thinking route: narrative path, search path, cross-branch path, and next-card path.Ⓔ Evolution: the time process: now, day, week, year, review, life plan, and card-box conversation.◎核心: the search object or knowledge object, not the mood or slogan.Arrow meanings:
↘ means Full-D -> Route: numbered notes become traversable paths.↙ means Route -> Evolution: routes generate next cards and long-term change.↖ means Evolution -> Index: evolved notes create better keywords and re-entry points.↗ means Index -> Full-D: indexes reveal missing notes, duplicate notes, or notes needing better numbers.◎核心詞 in 8 Chinese characters or fewer.Ⓕ Full-D with a numbering proposal, note status, and project/book path. Mark unknown IDs as 待編.Ⓘ Index with retrieval handles: one title-like entry, one tag/category entry, and one question or exact-search keyword.Ⓡ Route with three route lines: one table-of-contents or structural route, one keyword/cross-link route, and one semantic or next-card route.Ⓔ Evolution with time-based movement: present state, plan/review rhythm, and how the card box becomes a dialogue partner.Full-D / Index / Route / Evolution bullets.Use FIRE 2.0 to support three kinds of digital card-box search:
目錄索引搜尋: use Full-D numbering and book/project structure to find material by part, chapter, section, or item.精確關鍵字搜尋: use Index categories and exact keywords like Google-style search handles.語意搜尋: use FIRE's attention-friendly structure: numbered nodes, keyword signals, route paths, and evolving contexts.For an article around 1000 Chinese characters:
Prefer concise compounds:
幫每一張臨時筆記加上編號 -> 全編號把臨時筆記加工成永久筆記 -> 永久化出版時生成專案筆記並保留完整編號 -> 專案全碼部章節項目構成整本書目錄 -> 樹狀目錄八大類與六十四個核心關鍵字 -> 八類六四從樹狀結構變成蜘蛛網狀結構 -> 樹網互轉八大分類形成八條思考路徑 -> 八路徑靶心人公式的敘事結構 -> 靶心敘事數位卡片盒自生產生成下一張卡片 -> 下一卡當下、日計劃、週計劃、年計劃、百年人生計劃 -> 時間九宮語意搜尋的肥沃土壤 -> 語搜土壤If the user asks for more than a card, append this compact structure after the text card:
**F|Full-D**
- ...
**I|Index**
- ...
**R|Route**
- ...
**E|Evolution**
- ...
**搜尋判斷**
- ...
Keep this add-on short unless the user asks for a long encyclopedia entry or book-system plan.
If the user asks for a visible spacing version, show a second debug block where:
□ means one full-width space .· means one half-width space.Visible debug example:
□□□□□□□□□□【Ⓕ·Full-D·全編號】
□□□□□□↗□□□□□□□□□□□□□□□□□↘
□□【Ⓘ·Index】□□□中【◎核心】□□□【Ⓡ·Route】
□□□關鍵字網□□□□◎語搜土壤□□□□思考路徑
【Ⓕ Full-D 全編號】
編號:部章節項
定稿:永久筆記
出版:專案全碼
↗ ↘
【Ⓘ Index】 中【◎核心】 【Ⓡ Route】
關鍵字網 ◎語搜土壤 思考路徑
──────── ──────── ────────
八類六四 樹狀目錄 目錄路徑
精確搜尋 蜘蛛網索 靶心敘事
語意入口 時間九宮 下一卡
↖ ↙
【Ⓔ Evolution】
當下:臨時筆記
計劃:日週年宮
對話:卡盒夥伴
Comprehensive web quality audit covering performance, accessibility, SEO, and best practices in a single review. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website" across multiple areas at once. Orchestrates specialized skills for depth. Do NOT use for single-area audits — prefer core-web-vitals, web-accessibility, seo, or web-best-practices for focused work.
| Use when launching a new product end-to-end from market research through post-launch monitoring. Orchestrates 15+ specialist agents across 5 phases in a 10-week coordinated workflow including research, development, marketing, sales preparation, launch execution, and ongoing optimization. Employs hierarchical coordination with parallel execution for efficiency and comprehensive coverage.
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting session data.
| Create visually strong landing pages, websites, and app UIs with restrained composition. OpenAI's production frontend playbook.
Pre-build product and feature risk review for founders, product managers, and AI-assisted builders. Use this skill when the user is about to build a landing page, MVP, SaaS product, internal tool, agent workflow, or major feature and needs to check demand, positioning, monetization, retention, trust, distribution, and adoption risk before implementation starts.
This skill helps users extract structured best-selling product data from Amazon via the BrowserAct API. Agent should proactively apply this skill when users express needs like search for best selling products on Amazon, extract Amazon product data based on keywords, find top rated Amazon products, monitor Amazon competitor prices and sales, discover trending products on Amazon marketplace, extract Amazon product titles prices and ratings, gather Amazon product sales volume for market research, search Amazon best sellers in specific region, collect Amazon product reviews and promotion details, analyze Amazon product availability and badges, get Amazon product data for market analysis.
This skill is designed to help users automatically extract product data from Amazon search results. The Agent should proactively apply this skill when users request searching for products related to keywords, finding best-selling items from specific brands, monitoring product prices and availability on Amazon, extracting product listings for market research, collecting product ratings and review counts for competitive analysis, finding specific products with a maximum count, searching Amazon in different languages for localized results, tracking monthly sales estimates for brand products, gathering product URLs and titles for a product catalog, scanning Amazon for Best Seller tags in a specific category, monitoring shipping and delivery information for brand items, building a structured dataset of Amazon search results.
This skill is designed to help users automatically extract reviews from Google Maps via the Google Maps Reviews API. Agent should proactively apply this skill when users request to find reviews for local businesses (e.g., coffee shops, clinics), monitor customer feedback for a specific brand or location, analyze sentiment of reviews for competitors, extract reviews for a chain of stores or services, track reputation of a local restaurant, gather user testimonials for a specific venue, conduct market research on service quality of local businesses, monitor reviews for a new retail location, collect feedback on public attractions or parks, identify common complaints for a specific service provider, research the best-rated places in a city, analyze recurring themes in reviews for a specific industry.
Take twhsi/fire-analysis-card from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.