Claude Skills by peter-tu-zynkr

- **Status:** Built 2026-09-18 - **Size / DoD:** L / D2 *(new subsystem + fleet-wide convention + new CI gate; no schema, secret, auth, money or cron ⇒ not D3)* - **Created:** 2026-09-18 · **Repo(s):** `zynkr-skill-builder` - **Links:** `docs/house-style/README.md` (the binding seed) · `scripts/check-house-style.ts` (the gate) · 《[2.0] Zynkr 通用風格指南 House Voice》 `10bOIQwRm9Pxwgct4hlwCwK_B4Pipai1HqBPZKzyRHSE` (new) · 《[3.2] 禁用詞清單》 `1N5sHLP4qzmmhpCGsi6KElxi1z0MFe4QZ0Q_35T10Uyg` (unchanged)

Turn ONE teammate's shared 1:1 Doc (weekly WB entries), their LOB plan Doc and the tracker rows they own into a zh-TW 「年度計畫＿<name>」 Google Doc in the planning hub folder — six fixed sections (過去一年成果總覽 · 策略透鏡 C1–C4 · 復盤 放大／收割／停止或改造 · 年度計劃 3–5 主軸 · OKR · 接下來) with every claim tagged to its WB date, plus a 12-line slide summary block for that person's session one-pager. Trigger on /planning-1on1-annual-digest or when Peter says "幫 <name> 整理年度計畫", "從 1:1 文件整理 <name> 的年度回顧", "把 <name> 的 1:1 筆記變成年度...

The "looking back in numbers" scoreboard for a Zynkr planning cycle (H1 / H2 / YE). Seeds KPIs from the session workbook's Pre-work by LOB tab + the OKR tracker's KRs, routes each to ONE readable source (Main Tracker 完成 counts · planning-tracker-sync's `tracker-snapshots` tab · OKR status · Calendar event counts by title pattern · Gmail Fireflies recap counts · numbers the user pastes; zynkr-gm's kpi-map.md when installed), writes a `Scoreboard` tab (KPI · source · <cycle>-start · <cycle>-end...

Audit ONE line of business (an L1 LOB such as 3.0 Operations) after a planning cycle: inventory its Drive folder, read its plan Doc + Refresh addendum and its rows in the planning Main Tracker, and cross-check five gap classes — P0/P1 items with no doctrine/SOP or owner-named plan, role docs / SOPs that contradict the plan (stale tools, stale owners), docs the plan cites that do not exist, superseded snapshots without a [SUPERSEDED] banner, and open decisions the plan needs from the founder. ...

Build the BEFORE-THE-ROOM pack for a Zynkr planning session (H1 / H2 / YE): copy the session-workbook template Sheet and re-fill its five tabs for the new cycle (Read Me · Agenda 8 blocks · Pre-work by LOB 8 rows · Laundry List + Eisenhower seeds · Eisenhower Matrix) from the Main Tracker, the OKR tracker, the per-LOB plan Docs and the 1:1 Docs; write per-owner one-pager text blocks into a 「Pre-work — <cycle>」 Doc; hand a 16-slide template-fill request to /zynkr-slide (or print the slide text...

Same-day digestion of a Zynkr planning offsite (H1 / H2 / year-end): turn the session transcript + whiteboard photos into the Main Tracker's working tabs — verbatim 「② 白板原文」 (pen colour + 判讀信心 高/中/低), the MECE re-cut 「③ 去重與歸類決策」 + 「④ MECE 檢查」 with every merge/split/move ruling written down, the 「<cycle> 回顧總結」 retro table with 5 重點結論, the README tab, a normalized item list handed to planning-tracker-builder, and the recap mail as a Gmail DRAFT (never sent). Trigger on /planning-session-synth o...

Propagate a FINALIZED planning Main Tracker into Zynkr's satellite planning suite after an H1 / H2 / YE planning session: for the integrated plan Doc and every per-LOB plan Doc it composes and inserts a dated top-of-body Refresh addendum (thesis sharpened · what changed vs the previous plan · open decisions · the P0 list with owners · management fixes from the retro), and for the OKR & KPI Tracker it rebases the OKRs (Objective = 策略主軸, KR = P0 items with Owner + Tracker #) and mirrors P0+P1 I...

Build or extend Zynkr's planning Main Tracker (the cycle's system of record) from a NORMALIZED item list — the planning-session-synth handoff or a pasted table. Fresh cycle: copy the template tracker (never edit it) → 「<year> <cycle> Planning Main Tracker」 → cycle-named tabs → fill the SOR tab with L1 header rows + N.NN numbering, 重要×緊急 → Priority formula, the 專案項目小記 pivot, 狀態 colours. Existing tracker: fill the empty SOR tab session-synth left, append rows under the right L1 block, or add a ...

Team-side weekly heartbeat on the COMPANY Planning Main Tracker (SOR tab of the H1 / H2 / YE cycle) — zynkr-gm's record-side companion. Reads the `<cycle> 專案項目` tab, derives per-item state with zynkr-gm's rules VERBATIM (ENDS_SOON · OVERDUE · UNDATED · STALLED · PROPOSE_DONE · DIRECTION_UNLABELLED — its scripts when installed, else the copied rules) and prints the zh-TW Team Weekly agenda block in one fixed six-section shape (cadence → OVERDUE／ENDS_SOON → UNDATED／掛 All → 各 owner P0/P1 + Δ → P...

The GM operating-rhythm skill for a small company run from Google Docs/Sheets. Reads the source-of-record chain in precedence order (strategy alignment section → H2 project tracker (status SOR) → the ops team's weekly log → OKR & KPI tracker → per-function progress sheets), derives per-item state (ends-soon · overdue · undated · propose-done · direction-unlabelled), and produces a fixed-shape WEEKLY GM BRIEF: runway line first, the ≤3 things only the GM can unblock, two clocks, P0/P1 status b...

Article fission — extract outline + summary from any popular article, then run 3 rounds of reflective dialogue to surface the writer's own refined take, ending with a new actionable outline ready for style + writing handoff.

Put a newsletter in its proper place — reconcile it between Google Docs and the Notion Content DB in EITHER direction (Doc-first OR Notion-first), and file the Doc into the newsletter Drive folder. The goal is that the content ends up correctly placed and cross-linked regardless of which was created first. Use whenever the user shares a Google Doc and/or a Notion Content-DB page and wants them synced, filed, archived, or "put in the right place". Triggers on "幫我放上 Notion", "sync to Notion", "...

Drafts Peter's weekly Chinese newsletter from the user's article outline or topic idea, shaping it into a structured handoff for the /zynkr-content-writer pipeline. Use this skill whenever Peter says "幫我寫電子報", "來寫電子報", "寫newsletter", "電子報大綱", or shares a topic/outline and wants it shaped into a newsletter. Trigger even if Peter only gives a rough idea — the skill will structure it into a full outline.

Translate English (or any source language) into natural, conversational Traditional Chinese using Taiwanese expressions and tone. Removes the 'translation smell' that comes from word-for-word renderings. Also supports a reverse zh-TW → English mode for producing English 'flagship' versions of SEO articles (used by seo-article-pipeline for AEO reach in English-dominant AI engines).

Third leg of the SEO pipeline: working from an SEO expert's perspective plus competitor URLs, surface the content angles and differentiation opportunities for 'where we can do better.' Maps to the v2 flow diagram step 'think about strengthening from the SEO angle + reference competitor URLs to think about strengthening.' Triggers when the user hands over a Questions handoff packet, provides competitor URLs, or says 「找 SEO 切角」. It only finds angles — it does not build the keyword map and does ...

The final leg of the SEO pipeline: add internal/backlinks, a meta description, and structured data (schema) to an already-proofed article, then assemble it into a publish-ready Google Doc (article body + a 「SEO 交付物」block carrying slug/seo_title/meta_description/keywords/category + links/schema) for seo-publish-article. Corresponds to node (11) of the v2 flow diagram — 'list which paragraphs can take links + add the meta description' and 'article settings'. Triggers when the user hands over an...

The orchestrator for Zynkr SEO content production: it chains the stages of the v2 flowchart into one pipeline running from brand material all the way to a published article on the live website. The first half (persona → seed questions → angles → keyword map → intent classification → demand validation → Brief → outline/FAQ) calls each SEO skill; the second half (drafting → titling → proofreading) reuses the existing write-article sub-agents; then it does SEO setup (`seo-article-finalizer` prod...

Seventh stage of the SEO pipeline: for one selected topic, find the value proposition and winning angle, and produce a complete SEO writing Brief. Corresponds to the v2 flowchart step 「選擇主題：設計 Brief」. Triggers when the user hands over a Topics handoff packet, provides reference articles/forums/expert opinions, or says 「寫 Brief」. Only writes the Brief — does not design the outline and does not write the article.

Sixth stage of the SEO pipeline: validate the real demand and competitive difficulty of keywords, compare the common patterns across the current SERP, prune unnecessary terms, and consolidate a list of target keywords and topics. Corresponds to node (6) in the v2 flow diagram. Triggers when the user hands over a Classified handoff packet or says 「驗證需求」 (validate demand) or 「整理主題清單」 (organize the topic list). It only validates and converges — it does not write the Brief and does not write the ...

Fifth leg of the SEO pipeline: classify the keyword map \"by search intent\" (not by product category), and offer several grouping versions to choose from. Maps to the v2 flowchart step \"classify by different classification methods, provide different versions\". Triggers when the user hands over a KeywordMap handoff packet, or says '關鍵字分類' or '按意圖分群'. Only classifies — does not validate demand or difficulty, and does not write articles.

Fourth leg of the SEO pipeline: use keyword tools (Ubersuggest / AnswerThePublic) to expand angles and seed terms into a complete keyword map. Maps to the v2 flow diagram's 'filter keywords to build the keyword map + compile the complete keyword map'. Triggers when the user hands over an Angles handoff packet, pastes a keyword-tool export, or says '做關鍵字地圖'. Builds the map only — it does not classify intent and does not write articles.

Stage 8 of the SEO pipeline: turn the SEO Brief into an article outline and FAQ section, outputting a handoff summary compatible with content-draft. Corresponds to the v2 flow diagram's 'Structure article: outline design' and 'Build FAQ'. Triggers when the user hands over a Brief handoff packet and says '設計大綱' or '做 FAQ'. Only handles the outline and FAQ; the actual writing is handed off to content-draft.

First leg of the SEO content pipeline: reads brand material (from the SEO knowledge-base folder or a brand-material pack) and builds personas / consumer profiles of the target readers and prospects, to serve as the basis for downstream keyword and topic work. Triggers when the user says '幫我建立 SEO 人物誌', '先做受眾輪廓', '開始 SEO 流程', or hands over a brand-material pack. Does personas only — no keyword work, no article writing.

The Stage-0 program-scale SEO strategy planner for any Zynkr product or website — it sits UPSTREAM of seo-article-pipeline and turns 'plan the whole product/site's SEO' into a repeatable, callable orchestration. It reuses the existing single-topic seo-* strategy skills at program scale (seo-persona-builder → seo-question-miner → seo-angle-finder → seo-keyword-mapper → seo-keyword-classifier → seo-demand-validator) AND adds the program-level synthesis those skills never do — defining content p...

Publishes a FINISHED SEO blog article to the live website (e.g. zynkr.ai/blog) by writing it straight into the CMS's Supabase `articles` table — the fast path, because the CMS admin page (e.g. cms.zynkr.ai/content) is an auth-gated dashboard, not a write API. Reads the article from a Google Doc (body + the embedded 「SEO 交付物」block for slug/seo_title/meta_description/keywords/category), converts it to CMS-safe Tiptap JSON + content_html (tables→lists, ▋ headings, schema-validated so it never co...

Second leg of the SEO pipeline: based on the persona, brainstorm the questions your target readers actually ask before buying, then work backward from those questions to seed keywords. Maps to the v2 flowchart step 'brainstorm common questions + interview-answer common questions and list keywords'. Triggers when the user hands over the persona handoff packet or says '發想常見問題' or '挖種子關鍵字'. Only brainstorms questions and seed keywords; it does not do difficulty analysis and does not write articles.

Turn an ideated business workflow into a slide-ready FE/BE/DB architecture diagram: three horizontal lanes (前端 Front End · 後端 Back End · 資料庫 Database) with the workflow's IPO units stitched LEFT→RIGHT across them — human inputs drop ↓ from the FE lane into dark octagon process nodes chained → across the BE lane, stored knowledge feeds ↑ from the DB lane, and the output document rises ↑ back to FE at the far right, closed by exactly ONE orange 'law line' verdict bottom-right. Trigger when the ...

The second leg of the slide-assistant three-leg relay: take the storyline approved by the previous leg (SLIDE_PACKET ▸ Storyline) and, following paging principles, slice it into a page-by-page slide list — deciding which beat each page maps to, what title it carries, how many bullet points it holds, and how dense its information should be. Trigger me immediately when the user hands over a ▸ Storyline handoff packet, or says 「幫我分頁」, 「把故事線切成投影片」, 「每頁放什麼」, 「規劃投影片頁數」, 「slide 分頁設定」. I only handle ...

The 'rendering engine' that comes after the three-stage slide relay (the fourth stage, maintained by Anthropic): it takes the SLIDE_PACKET ▸ Visuals handed off by slide-visual-selector and renders it page by page into a real .pptx file, and can also read, parse, and edit existing decks in reverse. This is Anthropic's official slide-pptx skill; Zynkr does not redistribute its code — this card is only a reference and a hand-off pointer, so install it from the Anthropic source.

Leg 1 of the three-leg slide relay: take the raw slide material / topic + the message you want to land, and shape it into a logically smooth storyline — confirm the presentation's goal and audience, fix the core claim that runs through the whole talk, lay out an ordered narrative arc (beats), and check each transition one by one for leaps or gaps, producing the SLIDE_PACKET ▸ Storyline narrative skeleton that gets handed to slide-page-splitter for paging. Trigger me proactively when the user ...

The third leg of the slide-assistant three-leg relay (picks up after slide-page-splitter, then hands off to the slide-pptx skill for rendering): once it has the SLIDE_PACKET ▸ Pages, it decides page by page \"what is the most effective visual treatment for this page?\" (chart / bullets / diagram / image / comparison / big statement…), and converges each page into a render-ready per-page visual spec SLIDE_PACKET ▸ Visuals, handing it off to the installed slide-pptx skill to render into a .pptx...

Publishes a finalized post to your SOCIAL channels — Facebook, Threads & Instagram — via the Buffer API, with per-channel formatting, Instagram image support, and a preview-confirm gate before anything posts. Use when you say 'publish my post', 'post this to Threads/IG/FB', 'push this draft live to social', or 'schedule this post'. The SOCIAL publisher — not the website/blog one (seo-publish-article).

Orchestrates the full article writing pipeline — from ideation through drafting, editing, titles, and CTA. Invoke with /zynkr-content-writer or when the user wants to start writing an article from scratch.

The conductor of the slide relay (sitting above the three-stage relay): fires when the user says '做一份簡報／做個 deck／幫我把這些做成投影片／做季報簡報／all-hands 簡報／deep dive 簡報／pitch deck'. I do a one-shot intelligent intake — detecting which kind of deck this is (deep-dive / business-review / data-presentation / all-hands / planning / pitch / update / teach / fundraise), taking stock of the material and storyline the user has already given, proposing a page count for the user to confirm, and gathering the must-in...

Pull a consulting client's AI-assistant usage out of platform telemetry (crm_ai_usage, READ-ONLY), compute adoption metrics — WAU, actions per user per week, week-over-week trend, top features, at-risk users — and render a zh-TW "[Adoption] {{COMPANY}} — YYYY-MM" report Doc into the client's [N] Drive folder, backlinked to the CRM deal, plus an optional ask-only Gmail draft. Trigger on /consult-adoption-reporter or when Peter says "客戶用量報告", "採用率追蹤", "這個客戶有沒有在用", "使用狀況分析", "adoption report for...

Turn a consulting engagement's raw discovery material — consult-discovery summaries, shadowing transcripts / recording notes, process findings — into a client-grade requirements document as a Google Doc in the client's numbered [N] Drive project folder, backlinked to the CRM deal. Two modes: BRD (default — business-facing, zh-TW) and PRD (an SDD-conformant buildable spec with a per-client spec ID, EARS-lite ACs and Verify lines). Trigger on /consult-brd-writer or when Peter says "幫我寫 BRD", "把...

Turn a client bug report — a Gmail thread, a forwarded mail, or pasted text — into tracked work in one pass: a well-formed GitHub issue in the right repo (routed via a local bug-routing-config.md), a CRM follow-up task on the client's deal, and a threaded acknowledgment reply left as a Gmail DRAFT (never sent). Trigger on /consult-bug-ticket or when Peter says "開 bug 單", "把這封信開成 issue", "回報這個 bug", "客戶回報問題", "file this bug", "turn this bug mail into a ticket", "log this defect and reply", or ...

Two-stage consulting discovery — pain-point intake then company vision exploration — to produce a needs definition and strategic discovery summary before any solution work.

Visualize a consulting engagement's operations on Lucid as a paired AS-IS / TO-BE process chart set — drawn from the engagement's own documents (session notes, 痛點 ledgers, [Plan] docs, BRD) and recorded back on the CRM deal. ALL drawing, editing, and lint mechanics are delegated to the installed product-flow-design skill; this wrapper adds engagement resolution, the as-is/to-be pairing discipline, chart naming, and CRM linkage. Trigger on /consult-flow-design or when Peter says "畫客戶的 as-is/to...

The weekly hygiene sweep across the WHOLE consulting portfolio — inventory every numbered [N] engagement folder under the consult Drive parent AND every open consult deal in the CRM, diff the two against six invariants (deal↔folder backlink, kickoff-doc presence, session-note recency, [N] numbering continuity, activity pulse, artifact chain), and emit a zh-TW ready-to-apply changelist in the chat. Strictly READ-ONLY — it proposes fixes named to the owning skill but never applies one: no Doc c...

Run a client info session (說明會) for a consulting engagement end to end on the D-14 → D+3 checklist — schedule and invite, prep, run and record, then produce the client-facing five-section recap — with every artifact filed in the client's numbered [N] Drive folder and noted on the CRM deal. Re-entrant: each run shows the checklist with today's position and advances the due stage. Trigger on /consult-info-session or when Peter says "幫客戶辦說明會", "導入說明會", "說明會回顧", "安排 kickoff 說明會", "run the client ...

Turn this week's inbound "AI 顧問服務" consulting inquiries (the website discovery-call emails from website@zynkr.ai) into tracked work: for each real lead it creates a CRM deal in Supabase, a numbered Google Drive project folder, and a kickoff doc inside that folder. Use this skill whenever Peter runs /consult-intake or says things like "process this week's consult inbounds", "處理本週顧問諮詢", "有沒有新的顧問諮詢", "check for new consulting leads", "turn the discovery-call inquiries into deals", "intake the co...

Draft the go-to-market communications for a consulting engagement's rollout — the client-internal 上線公告 (rollout announcement) and the 說明會 invite, written in the client sponsor's voice, filed as [Comms] Google Docs in the client's numbered [N] Drive project folder and backlinked to the CRM deal — plus an optional, ask-only ANONYMIZED case-study seed handed to the public content pipeline. Trigger on /consult-launch-comms or when Peter says "寫導入上線公告", "幫客戶寫內部宣布信", "上線溝通信", "寫說明會邀請", "draft the r...

Turn a single sales / consulting meeting into tracked work. Give it a meeting transcript or notes — pasted text, a Google Doc, or a Gemini Notes link — and it produces a structured Weekly Project Update, then lays down the three things the engagement needs: a numbered Google Drive project folder, a kickoff/context Doc inside it, and a CRM deal in Supabase with a meeting + links-note + one task per "What's Next" item. Trigger on /consult-project-specialist or when Peter says "turn this meeting...

Turn a consulting-session transcript or messy notes — a discovery call or a shadowing observation — into the four-section session summary (Summary Update · Progress · Blockers · What's Next) PLUS a 痛點 ledger (one row per pain actually voiced or observed), filed as a [Notes] Google Doc into the engagement's EXISTING numbered [N] Drive folder with a note on the CRM deal; the ledger is the raw material /consult-brd-writer consumes. Trigger on /consult-session-notes or when Peter says "整理這次客戶訪談筆記...

Close the shadowing-scheduling admin loop for a consulting deal in one pass: read the CRM deal, resolve the client's existing [N] Drive project folder from the deal notes, check Peter's calendar free/busy, propose 3–5 candidate slots, and on Peter's confirm lay down the whole kit — a calendar hold, a "Shadowing — YYYY-MM-DD" subfolder inside the project folder, a client logistics Gmail DRAFT (never sent), a CRM follow-up task, and a deal-notes backlink. Trigger EAGERLY on /consult-shadowing-s...

Turn an engagement's discovery outputs — consult-discovery summaries, consult-session-notes 痛點 ledgers, the client's stated goals — into a structured solution plan: persona, operator journey, pains ranked by 影響範圍 size × 強度 intensity × 頻率 frequency, selected opportunities, MVP scope, and success metrics — filed as a "[Plan]" Google Doc in the client's numbered [N] Drive folder and ending in an explicit handoff block for /consult-brd-writer. Operationalizes MrPM-Stanley's 產品企劃力 product-planning...

Generate the weekly CLIENT-FACING status email for ONE consulting engagement. Reads the CRM deal's tasks / activities / notes plus the newest [Notes] / [Plan] / [BRD] / [UAT] docs in the client's numbered [N] Drive folder, derives health / progress / blockers / next milestone, renders the 專案狀態看板-style HTML dashboard, and creates a Gmail DRAFT addressed to the deal's client contact — NEVER auto-sends. Trigger on /consult-status-report or when Peter says "客戶週報", "顧問案週報", "寫給客戶的進度報告", "客戶進度信", "...

Turn a consulting engagement session — a discovery call or an on-site shadowing session, either already captured in Fireflies or supplied as a recording — into a clean zh-TW transcript filed straight into the client's numbered [N] Drive project folder and linked on the CRM deal. A thin delegation wrapper: it invokes the installed training-srt-transcriber (local Whisper → timestamped .srt; transcribe or retime mode) and training-srt-optimizer (minimal-edit zh-TW cleanup) for ALL transcription/...

Turn a consulting engagement's PRD (the SDD-shaped spec Doc written by consult-brd-writer) plus the deployed assistant's facts into a client-facing zh-TW UAT testing guide — a Google Doc in the client's numbered [N] Drive folder with a scenario table (one client-runnable scenario per AC), pass/fail checkboxes, bug-report instructions, and a sign-off block — plus a CRM task so the acceptance round is tracked. Trigger on /consult-uat-writer or when Peter says "寫 UAT 指南", "產驗收測試文件", "幫客戶寫測試指引", ...