Claude Skills by peter-tu-zynkr

9-step sales client sourcing pipeline — turn a workshop/event satisfaction survey into an enriched outbound funnel with company website, background, tailored 陌生開發 strategy, Hot Lead flag, and Well-Known firm flag. Operates in BATCH on a WHOLE survey sheet and writes back only new columns — it creates no CRM records and drafts no email. For ONE person's row — or a single DM, website enquiry, or business card — hand that signal to sales-outbound instead, which creates the contact + deal and dra...

Turn a finished sales DEMO / discovery call into a converting follow-up — the post-meeting counterpart to sales-outbound. Give it the demo transcript (a Fireflies meeting, a Google Doc URL, or pasted notes) and it does two things in one pass: (1) drafts a pre-sales follow-up reply as a threaded Gmail DRAFT in Peter's inbox (never sends), in the prospect's language and Peter's voice — opening by mirroring the exact pain points they raised, mapping each to the matching Zynkr AI 平台 capability (z...

The conductor of the Zynkr sales family — it decides which sales skill a given input needs, chains them when a job takes more than one, and reads the CRM across deals to say which ones need attention now. It owns the deal lifecycle; the five skills under it each own one step. Three modes: ROUTE (one input → the right child skill), SEQUENCE (a job that needs two or more, e.g. triage a whole event survey with sales-client-sourcing then run sales-outbound on each Hot Lead row), and REVIEW (deal-...

Turn ONE person's interest signal into a tracked CRM lead AND a ready-to-send reply. The signal can be a copied DM / chat thread (Threads, IG, LINE, FB Messenger, WhatsApp, email), a single row from an event feedback or registration form, a website enquiry, or the text off a business card — anything where one named person showed interest and left an email address. Optionally hand it their profile link too. It does two things in one pass: (1) collects who they are — parsing the signal and enri...

Turn a qualified CRM deal plus whatever the client actually sent — a requirement sheet, discovery notes, a meeting transcript, a prior proposal — into a priced client proposal published as a 交付文件 at platform.zynkr.ai/d/<token>, and keep it alive through the revision rounds. It does four things in one pass: ranks the client's asks by an openly-stated criterion and presents them as 第一順位／額外項目 (never colour codes, never our internal IDs); splits them into a recurring lane and a one-off build lane...

Runs AI background research on a company (and optionally a contact) in the Zynkr platform CRM and writes a concise, sales-context zh-TW brief into the company's 備註/description field. This is a Claude Code stand-in for the platform's own "AI 背景研究" button (app/lib/ai/research.ts) — that feature only exists in the platform.zynkr.ai web UI and is NOT exposed through the connected `zynkr` MCP server, which only offers CRUD tools (create_company, create_contact, update_company, etc.), so there is n...

Business card pipeline — OCR extraction, schema normalization, Zynkr platform contact + company creation, company research, and personalized follow-up email drafting. Takes business-card IMAGES specifically — the OCR pass is the point. When the lead signal already arrives as text (a DM thread, an event feedback row, a website enquiry), use sales-outbound instead; for a WHOLE event survey sheet, use sales-client-sourcing.

Guides the operator through preparing a complete Accupass event listing — one field at a time — then outputs a single copy-paste-ready template covering event content, ticketing, marketing emails, and a post-event follow-up checklist. Use when the user says '我要上架活動', '上架活動通', '填活動通', '活動上架', 'accupass', '幫我填模板', or '活動資訊填寫'. Does not publish to Accupass directly (the platform has no API) — it produces the filled template for manual entry.

Weekly hygiene ritual for Zynkr's local↔cloud knowledge governance. Lists Google Drive Docs modified in the last N days across the 8 LOB folders (and Drive root), diffs against local `_INDEX.md` entries in `~/Desktop/Claude/zynkr/`, and proposes specific index edits: new entries to add, broken/renamed links to fix, deleted Docs to remove. Triggers on phrases like 'drift check', 'weekly hygiene', 'sync indexes', 'check cloud changes', 'what changed in cloud this week', '/admin-governance', or ...

A scheduled, auto-running admin-meeting-prep assistant: every day at 9 AM it scans meetings within the next 7 days and sends action reminders; every day at 3 PM it sends a full briefing for the next day's meetings. Notifications are sent to yourself via Google Chat. No manual trigger needed; does not handle post-meeting follow-up.

Files loose meeting recordings sitting in a Google Drive recording inbox into the right category sub-folder, with an approval gate. For each loose video it groups the same-prefix siblings (the ` - Notes by Gemini` Doc, ` - Chat` .txt, any .srt) into one unit, reads the Gemini Notes to classify which sub-folder it belongs in, shows the user a filing plan to approve, then moves the whole group and logs the move to a `Video Index` sheet. If nothing fits it proposes a new sub-folder. Trigger on /...

Manages the full external guest-lecturer collaboration lifecycle for Zynkr events — lecturer intake and screening, contract preparation, the per-event D-30→D+3 operations timeline, and monthly fee settlement with statutory tax withholding. Use when the user says '外部講師', '講師合作', '講師結算', '講師合約', 'guest lecturer', or asks to run any stage of the lecturer program (接洽新講師 / 上架講師活動 / 月末結算). Commercial terms (revenue split, thresholds, penalty caps) come from a local program-config.md — they are neve...

Streamline and re-sequence a business process into a clean 'ideal flow' before it gets built or automated. Canonical slot (course Ch5 §5.5.2): run it right AFTER the as-is→to-be redesign re-chains the flow — polishing the redesigned ordering — though it also works standalone on any messy as-is map. Runs a lean optimization pass: validate Input→Process→Output on every step, map dependencies, eliminate friction (duplicative / looping / missing steps), then apply disciplined re-sequencing only w...

Three-stage operations transformation pipeline — process discovery (SIPOC), digital transformation assessment, then automation-ready process redesign — to turn pain points into builder-ready blueprints.

Stands up a new project from the PMO template set — resolves the filing home from the engagement type, copies the five templates into a new project folder, creates the four sub-folders, clears the example rows (鐵律 2), fills the Kickoff header, seeds 管控表 tab 1 with the five delivery-stage rows, writes the backlinks both ways and prints the pm.json entry to paste (spine + report recipients included). Trigger on /project-init or when the user says 「開新專案」「建立專案資料夾」「幫我開一個案子」「set up a new project」「複...

Close the 會議記錄 → 管控表 loop for one meeting: parse a [會議記錄] Doc's four tables (進度更新 · 提醒與阻礙 · 決議 · Action Items), then append-or-patch three 管控表 tabs — Action Items into 專案管理總表, 決議 影響 ≠ 無 into Change & Decision Log, Blocker 阻礙 unresolved ≥ 7 days into Risk Register — and print a diff of what moved. Trigger on /project-minutes-sync or 「同步會議記錄」「把會議記錄同步到管控表」「會議決議同步」「Action Items 進管控表」「阻礙開成 Risk」「sync the minutes」「把這場會的決議寫進 Change Log」. NOT project-note-specialist (3.08), which reshapes raw notes i...

Turn raw meeting notes, transcripts, voice memos, or messy unstructured updates into a clean structured Weekly Project Update (Summary · Progress · Blockers · What's Next). Trigger whenever the user pastes meeting notes/transcripts and asks to 'organize my notes', 'tidy up these notes', 'turn this into a weekly update', '整理會議筆記', '整理一下筆記', '幫我寫週報摘要', or shares messy meeting/voice-memo text wanting it cleaned into an internal-stakeholder update. Source: admin-meeting-prep agent (sheetId 3.04).

Stress-test and refine a project idea before execution via a 7-stage Socratic facilitation — WHY (5 Whys) → WHAT → HOW → WHO (RACI) → WHEN (Gantt) → MEASURES → RISKS — producing an execution-ready project charter.

Generates a weekly project status update for a project tracked in a Google Sheet. Reads the live 「專案管理總表」 task tab of a project-tracker Google Sheet you configure, reasons over task status + dates against today to derive project health, blockers, this-week actions, % complete, next milestone, recent decisions and a timeline (the 「專案狀態看板」 dashboard format), renders it as a styled HTML email, and creates a Gmail DRAFT (never auto-sends) to a configurable recipient list. Trigger this skill EAGER...

The knowledge-curator (WRITE) half of Peter's support loop: it turns resolved support threads into KB cards in the Zynkr platform 知識庫 (the source of truth), then mirrors every change to a Google Drive backup. After a support / inbound-sales ticket is resolved, zynkr-kms reads the thread, learns Peter's actual answer, and writes it as a clean, LLM-friendly card into the **Zynkr platform 知識庫** (platform.zynkr.ai/kb, via the `zynkr` MCP server) — the single source of truth since the 2026-07-15 c...

The weekly operations loop that keeps a Google Chat space and a weekly operations Google Doc in sync. Six scheduled modes run one beat each: `nudge` (Mon 09:00 — post the four-line template plus last week's decisions), `rollup` (Tue 09:00 — read the week's `#週報` posts, route each one to its department heading using the owner person-chips already in the Doc, and write a clearly-marked auto-summary block), `chase` (Tue 09:30 — @ the owners who did not post), `agenda` (Wed 17:00 — re-sweep for l...

The READ half of Peter's support loop (formerly support-reply-drafter). Parses Peter's Gmail support + inbound-sales queues, detects unreplied inquiries, identifies each inquirer's intent, and matches it against the **Zynkr platform 知識庫** (platform.zynkr.ai/kb — the single source of truth since 2026-07-15, accessed via the `zynkr` MCP server's search_kb / get_kb_article) to draft a safe reply on the thread. Drafts match the inbound language (zh-TW or EN). When the KB has no confident answer i...

Weekly transcript curation. Sweeps the 直播筆記 livestream-note Google Docs across N upstream Drive folders, extracts each doc's 逐字稿 (verbatim transcript) tab, and writes one structured zh-TW summary Doc per source into the destination SOT folder. Fully idempotent — skips any source whose target already exists. Trigger on /curate-livestream-transcripts, '整理直播逐字稿', 'curate the livestream transcripts', 'process this week's 直播筆記', or the weekly Monday routine.

Explain any topic, code, concept or error message at the exact level the listener can absorb — adapting vocabulary, analogy, tone, depth and framing to who is listening. Use this skill whenever the user says 'ELI5', 'explain like I am 5', 'explain this to my manager', 'break this down for a 5th grader', 'dumb it down', 'simplify this for a designer', '解釋給我媽聽', '講給五歲小孩聽', '用白話講', '講人話', '這個要怎麼跟老闆講', '幫我解釋給客戶聽', '講給學員聽', or asks to explain something to a named person or audience type. Also fire...

Turn a video file or transcript into a reader-friendly lecture recap structured into five fixed sections — Summary, Theme, Q&A, Tools, Call to Action — while strictly avoiding any reference-outline detail leakage.

Polish long video lecture transcripts into lecturer-friendly readout scripts in Traditional Chinese.

Post-process a livestream transcript into four parallel workstreams: an event recap Google Doc, a Q&A knowledge base diff, course lecture note proposals, and marketing content idea seeds.

Minimally clean subtitle .srt files into readable Traditional Chinese while preserving original wording, cue timing, and subtitle alignment.

Turn an audio/video file (.m4a/.mp3/.wav/.mp4…) into a timestamped .srt using local Whisper. Two modes: transcribe (fresh speech-to-text with audio-accurate timestamps) or retime (keep an existing transcript's exact wording and re-derive every timestamp from the audio via forced alignment). Use when the user says 'turn this m4a into an srt', 'transcribe this audio to subtitles', '把這段錄音轉成字幕', '幫我做 srt', 'the srt wording is right but the timing is wrong, realign it', or hands over an audio file...

Read, draft, edit, and lint Lucid charts using Peter's FE/BE/DB three-layer architecture convention. Triggers whenever the user shares a `lucid.app` URL with no further direction, asks to diagram/chart/visualize a process or workflow, asks to 'read' or 'summarize' an existing Lucid diagram, asks to add/modify nodes on a Lucid chart, or asks whether a chart follows the Zynkr convention. Should fire eagerly on phrases like '幫我畫流程圖', 'draw this workflow', 'diagram this', 'visualize this process'...

Refactor a prompt (or prompt idea) into a production-ready package via 4 phases — GUIDE intake → diagnosis → structured refactor with explicit IPO sections + system/developer/user layers → optional multi-turn conversation blueprint.

Turns an early product idea into a structured plan — persona, user journey, prioritized pain points (size × intensity × frequency), MVP scope, and success metrics. Based on the 產品企劃力 design-thinking + product-positioning framework by MrPM-Stanley. Works for software, hardware, and service products. Use when you have a raw idea and need it shaped into a planning artifact, not just brainstormed.

Recommend the right Zynkr assistant(s) for a user's task. Interprets intent, matches against the structured assistant index, filters to usable entries, and either recommends or asks a single clarifying question.

Give AI agents full browser control via CDP — navigate pages, click, fill forms, screenshot, and run multi-step web workflows without Playwright or Node.js

Helps users discover and install agent skills when they ask questions like 'how do I do X', 'find a skill for X', 'is there a skill that can...', or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Fill a scaffolded Zynkr skill stub into a shippable SKILL.md — claim the sheetId, write frontmatter that satisfies SKILL_SPEC.md, replace every <!-- TODO --> marker with real steps, and self-check against the same validate-skill.ts engine /skill-qa will run. The build stage of the skill pipeline, between /skill-triager and /skill-qa. Trigger on 'write this skill', 'fill the stub', 'author the SKILL.md', 'finish skill <slug>', '把這個 skill 寫完', '填 stub', or '/skill-author'.

Land a freshly-built SKILL.md into the Zynkr skills pipeline — the closing step of the canonical chain (/skill-sourcer → /skill-triager → /skill-creator → /skill-qa → /skill-publish). Attaches the artifact to the existing pipeline issue, fires the publish-skill workflow to open a PR, and hands off to /skill-triager confirm-ship for closure. Trigger on phrases like 'publish this skill', 'land this skill', 'I finished building, push it', 'register this skill', 'add this built skill', 'check cat...

Quality-gate a SKILL.md before it ships — runs the shared validate-skill.ts engine (frontmatter + body structure + absolute-path leak scan + synergy + IPO length + downloadability) and renders a per-check ✅/⚠️/❌ report with file:line and fix suggestions, optionally auto-fixing mechanical issues (strip leaked machine paths, repair the install snippet) with confirmation, then emits a PASS/FAIL verdict gated on ERROR-tier checks. The QA tollgate of the skill pipeline, between /skill-creator and ...

Aggregate skill candidates from any source, classify against the Zynkr taxonomy, check for duplicates in the GitHub Project pipeline, and propose new skills as issues for review.

Triage the queue of approved skill proposals in peter-tu-zynkr/zynkr-skill-idea (label: triage-ready), present each as a one-screen review packet, and on assign-build fire a repository_dispatch event to zynkr-skill-builder so the pickup-approved-issue workflow scaffolds the SKILL.md. The DevOps-admin middle layer of the skill pipeline. Trigger on phrases like 'triage skills', 'review skill queue', 'skill triage', or '/skill-triager'.

The front-door router for the Zynkr assistant ecosystem. Takes ANY input from the user — a URL, a file path, a slug, a vague idea, a question about pipeline state — figures out which Zynkr skill it belongs to, reads the relevant state across GitHub Project / issues / on-disk / live marketplace, and either auto-invokes the right sub-skill or asks one targeted clarifying question. Use this skill whenever the user drops something into the conversation without specifying which skill should handle...

Prepare Peter for an inbound PAID career / résumé consultation before it happens. Give it the booking — a Gmail thread, the appointment email, or just the client's name — and it reads the client's pre-consult reply + CV + LinkedIn, then builds a ready-to-use prep Doc in Peter's 職涯諮詢 folder: the GROW-model intake (Goal / Reality / Options / Will / Story / Summary) prefilled from the client's own words, an opener checklist of the make-or-break facts to confirm first (visa/work-rights for overse...

5-phase CV optimization workflow — job analysis, story extraction, fit scoring, career progression analysis, and CV rewrite with Google Doc output.

Anticipates likely interview questions for a specific role by analyzing the job description, the candidate's resume, the interview stage, and company context from an interviewer's perspective. Returns a prioritized question map with rationale and evaluation signals. Use when a candidate is preparing for an upcoming interview and needs to know what's coming — strictly prediction, not coaching or model answers.

End-to-end recruiting pipeline — JD authoring, resume screening, interview design with scorecard, and calibration / final decision — bilingual (Chinese-English) outputs throughout.

The monthly financial close for the Zynkr Finance Ledger — reconciles one month's 台北富邦 bank statement against Gmail receipts, appends the rows that are missing, files the statement, and mails a performance report. Give it the statement PDF and a month; it reads every line on the statement as the spine of the month, sweeps the Finance Gmail label for invoices, receipts and remittance notices, works out which of them are already in the ledger, and proves the month is complete with a balance ide...