本文へ移動
cccskills
無料GitHub で公開

kelly-insurance-intel

Kelly Insurance Intel: App-in-Skill daily industry intelligence cockpit for insurance and wealth advisory (Busabase App-in-Skill). Use when the user asks about insurance, wealth advisory, client risk reminders, market news, policyholder follow-up,保险, or financial-advisor sales scenes. Prepares news/source signals, buyer-intent interpretation, approved sales actions, and channel drafts for review before any external handoff.

インストール方法を見る

含まれるファイル(64)

  • SKILL.md11.3 KB
  • agents/openai.yaml270 B
  • assets/screenshots/actions-zh-CN.webp130 B
  • assets/screenshots/actions.webp130 B
  • assets/screenshots/drafts-zh-CN.webp130 B
  • assets/screenshots/drafts.webp130 B
  • assets/screenshots/overview-zh-CN.webp130 B
  • assets/screenshots/overview.webp130 B
  • assets/screenshots/signals-zh-CN.webp130 B
  • assets/screenshots/signals.webp130 B
  • assets/screenshots/thumbs/actions-zh-CN.webp129 B
  • assets/screenshots/thumbs/actions.webp129 B
  • assets/screenshots/thumbs/drafts-zh-CN.webp130 B
  • assets/screenshots/thumbs/drafts.webp130 B
  • assets/screenshots/thumbs/overview-zh-CN.webp130 B
  • assets/screenshots/thumbs/overview.webp130 B
  • assets/screenshots/thumbs/signals-zh-CN.webp129 B
  • assets/screenshots/thumbs/signals.webp130 B
  • busabase.json1.2 KB
  • content/_folder.json479 B
  • content/actions/base.json2.3 KB
  • content/actions/records.ndjson2.5 KB
  • content/drafts/base.json2.1 KB
  • content/kelly-insurance-intel-app/_node.json499 B
  • content/kelly-insurance-intel-app/.busabaseignore194 B
  • content/kelly-insurance-intel-app/app/accent-theme.css8.0 KB
  • content/kelly-insurance-intel-app/app/accent-theme.js7.3 KB
  • content/kelly-insurance-intel-app/app/app.js23.7 KB
  • content/kelly-insurance-intel-app/app/base-ui.css13.0 KB
  • content/kelly-insurance-intel-app/app/i18n/messages.js4.9 KB
  • content/kelly-insurance-intel-app/app/index.html4.5 KB
  • content/kelly-insurance-intel-app/app/js/busabase-client.js226 B
  • content/kelly-insurance-intel-app/app/js/config.js6.9 KB
  • content/kelly-insurance-intel-app/app/js/connect-gate.js1.7 KB
  • content/kelly-insurance-intel-app/app/js/insurance-model.js11.6 KB
  • content/kelly-insurance-intel-app/app/js/providers/busabase-provider.js10.5 KB
  • content/kelly-insurance-intel-app/app/js/providers/demo-provider.js6.5 KB
  • content/kelly-insurance-intel-app/app/js/providers/index.js270 B
  • content/kelly-insurance-intel-app/app/js/runtime.js3.4 KB
  • content/kelly-insurance-intel-app/app/styles.css19.0 KB
  • content/kelly-insurance-intel-app/app/styles/editorial.css30.7 KB
  • content/kelly-insurance-intel-app/app/vendor/busabase-airapp-gate.css6.1 KB
  • content/kelly-insurance-intel-app/app/vendor/busabase-airapp-gate.js11.2 KB
  • content/kelly-insurance-intel-app/app/vendor/busabase-airapp.js556.0 KB
  • content/kelly-insurance-intel-app/app/vendor/busabase-sdk.js849.5 KB
  • content/kelly-insurance-intel-app/package.json1.1 KB
  • content/kelly-insurance-intel-app/pnpm-lock.yaml5.2 KB
  • content/kelly-insurance-intel-app/pnpm-workspace.yaml50 B
  • content/kelly-insurance-intel-app/scripts/check-editorial.mjs6.1 KB
  • content/kelly-insurance-intel-app/scripts/check.mjs4.4 KB
  • content/kelly-insurance-intel-app/server.js3.1 KB
  • content/kelly-insurance-intel-app/test/insurance-model.test.mjs7.8 KB
  • content/settings/base.json822 B
  • content/signals/base.json2.9 KB
  • content/sources/base.json956 B
  • package.json456 B
  • pnpm-lock.yaml4.3 KB
  • pnpm-workspace.yaml50 B
  • README.md3.3 KB
  • references/ui-schema.md6.0 KB
  • scripts/execute_decisions.mjs5.9 KB
  • scripts/publish_airapp.mjs3.1 KB
  • scripts/setup.mjs6.5 KB
  • scripts/sync-content.mjs2.5 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Kelly Insurance Intel

Overview

Use this skill as Kelly's daily industry-intelligence operator for insurance and wealth advisory.

It turns current news sources, trend signals, competitor movement, customer questions, and buyer-intent clues into a small reviewable batch, held in Busabase:

  • source-backed signals;
  • why each signal matters to the buyer;
  • sales or operating actions for today;
  • draft messages/content for client WhatsApp, advisor email, meeting agenda;
  • blocked claims that need human, legal, compliance, or domain review.

Signal/action/draft collection is a genuine external operation a browser cannot perform (web browsing, source reading, buyer-intent judgment). The AirApp itself only reads and writes Busabase — it never browses, posts anywhere, or performs an external handoff; Kelly writes today's batch directly into Busabase through busabase-sdk as part of the normal workflow below, then reviews and decides inside the app.

Default interaction mode: App UI. Unless the user explicitly asks for chat-only handling, check onboarding, collect/refresh today's batch, and give the user the clickable AirApp URL (or the local preview URL when local preview is explicitly requested). Use chat-only mode only when the user says "纯聊天", "chat only", "不要打开 UI", or similar.

Mandatory Dependencies

  1. Read and follow $kelly-app-skill-creator for product behavior, visual quality, responsive layout, and the complete canonical content/kelly-insurance-intel-app/ artifact.
  2. Read and follow $busabase for connection, target Space, node discovery, ChangeRequests, review, and merge behavior.
  3. Read and follow $busabase-app-creator for resource modeling, AirApp runtime limits, security, validation, and deployment.

If a dependency is unavailable, preserve this skill's product contracts, stop before the unavailable Busabase operation, and report the exact missing dependency. Do not invent a second data backend.

Product Package

  • Buyer: insurance advisors, agency managers, and independent financial consultants.
  • Pain: advisors need compliant, timely reasons to contact clients without sounding generic or alarmist.
  • Offer: daily advisor intelligence that becomes client reminders, meeting reasons, and compliant draft messages.
  • Demo source mix: market news, insurer announcements, regulator updates, health/cost-of-living news, and client lifecycle events.

Sales framing:

Every morning, AI watches the sources that affect your business, turns them into today's sales actions, and puts the drafts in a review queue before anything becomes official.

Do not lead with "AI platform", "agent workspace", "database", or model names. Lead with the daily business scene.

Scene Logic

Use this skill to convert insurance-market movement into compliant advisor, agency, or broker actions. A useful signal creates a timely reason to review cover, explain risk, update a client segment, or prepare a renewal conversation.

Prioritize signals in this order:

  1. regulator, insurer, product, premium, claims, or benefit changes that affect a client's review checklist;
  2. health, travel, weather, business, or cost-of-living news that makes a protection gap newly visible;
  3. competitor education content or campaign movement that shifts the client's comparison frame;
  4. lifecycle events and recurring client questions that can become segmented follow-up tasks.

Actions should become compliant meeting agendas, client education notes, renewal scripts, needs-review checklists, or Busabase approval batches. Block personalized financial advice, product suitability conclusions, return promises, policy interpretation beyond sourced text, and outbound claims without approval.

Boundary

  • The skill may browse public/current sources, reason over buyer intent, draft actions/content, and write signal/action/draft/source records to Busabase.
  • The AirApp reads and writes its own Busabase Bases only. It must never post content, send WhatsApp/email, mutate CRMs, scrape private systems, spend money, or perform any other external side effect.
  • Customer-visible drafts, regulated claims, pricing promises, medical/financial/legal advice, and outbound messages are approval-required.
  • Store only the minimal source excerpts needed for review. Never store crawl credentials or API keys in Busabase.
  • Block personalized financial advice, product suitability conclusions, return promises, policy interpretation beyond sourced text, and outbound claims without approval.

Busabase Resources

Five Bases under one application Folder (kelly-insurance-intel), declared in content/kelly-insurance-intel-app/app/js/config.js and the generated template sidecars under content/:

  • signals: source-backed regulator, insurer, product, premium, claims, benefit, health, travel, and lifecycle signals — evidence link, why-it-matters, buyer-intent interpretation, confidence, risk badges, a suggested action, and the human decision verdict.
  • actions: approved/blocked/reviewable compliant meeting agendas, client education notes, renewal scripts, or operating actions linked to signals, with owner, priority, reason, next step, and the human decision verdict.
  • drafts: editable channel drafts (client WhatsApp / advisor email / meeting agenda) tied to an approved action; a human edit is stored as edited-body on the same row, never a separate file.
  • sources: configured news/insurer/regulator/competitor/trend source categories, freshness, and coverage gaps.
  • settings: one row (record-id: "batch") holding the current batch's metadata (batch_id, generated_at, source, vertical, buyer, offer) as a JSON payload.

Resources provision lazily through an idempotent Busabase ChangeRequest the first time the app runs in a Space; see references/ui-schema.md for exact field shapes.

First Run And Onboarding

On invocation, check the signals, actions, and drafts Bases. If all are empty, guide setup before collecting a real batch: ask for company/brand name, geography, language, and customer segment; 3-10 public source URLs or source categories to monitor; competitor names/URLs; approved offer, CTA, and forbidden claims; preferred channels among client WhatsApp, advisor email, meeting agenda. Never ask for API keys or platform tokens in chat — Busabase connection happens through the app's own Connect Busabase gate.

Local App

Default behavior is AirApp-first — give the user the clickable AirApp URL. Start pnpm --dir content/kelly-insurance-intel-app dev only when local preview/debugging is explicitly requested.

Required app views (hash routes):

  • #/overview: human-attention panel — today's needs-review/approved/blocked counts, top signals, and ready (approved) actions.
  • #/signals and #/signals/<id>: source-backed signals with evidence links, buyer-intent interpretation, confidence, risk badges, and a decision panel (Approve / Request changes / Block) with a review note.
  • #/actions and #/actions/<id>: approved/blocked/reviewable operating or sales actions with owner, priority, reason, next step, linked signals, and the same decision panel.
  • #/drafts and #/drafts/<id>: editable client WhatsApp, advisor email, meeting agenda drafts with the decision panel plus a Save revision action that writes an edited body directly onto the draft record.
  • #/sources: configured source categories, freshness, and gaps.
  • #/settings: sanitized batch metadata, data provider, onboarding state.

Demo mode:

  • ?demo=1, ?demo=overview, ?demo=signals, ?demo=actions, ?demo=drafts, and ?demo=detail load deterministic demo data.
  • lang=en or lang=zh forces UI chrome language.
  • Demo mode never reads or writes Busabase; decisions only mutate the in-memory demo batch.

Batch Workflow

  1. Detect mode. Default to App UI.
  2. Browse or otherwise collect current public evidence. For news/trends, use exact dates and source URLs.
  3. Build one narrow buyer scene, not a generic AI report.
  4. Write the batch directly into Busabase through busabase-sdk (bases.createChangeRequest for each new signal/action/draft/source row, matching the field slugs in references/ui-schema.md; refresh the settings "batch" row's JSON payload with batch_id/generated_at/source/vertical/buyer/offer). Keep every item tied to evidence or mark it blocked.
  5. Open the AirApp for review.
  6. Poll for request_changes decisions (decision-verdict = request_changes on a signal/action/draft row) and revise only those items — write the revision back onto the same record.
  7. On "execute/export approved", run node scripts/execute_decisions.mjs first as a dry run. After performing any real handoff, run node scripts/execute_decisions.mjs --apply to mark the approved items done.

Decisions Workflow

  1. Kelly's verdicts write directly onto the item record (status, decision-verdict, decision-comment, decided-at) through busabase-sdk. From a standalone local preview the write merges immediately (trusted operator); from the deployed AirApp it creates a pending ChangeRequest for the trusted process to merge.
  2. Before executing anything, run node scripts/execute_decisions.mjs (dry-run). It prints the concrete operation for every decided signal/action/draft: mark_signal_approved, export_action_plan, or handoff_content_pack for an approve verdict; queue_agent_revision for request_changes; mark_blocked for block; save_human_revision for a draft's revise.
  3. After Kelly confirms the dry-run and performs the handoff somewhere outside this script, run node scripts/execute_decisions.mjs --apply to mark the approved items done. request_changes/block verdicts are left exactly as decided — there is nothing further for the script to do.

Safety Defaults

  • Treat outbound messages, regulated claims, medical/financial/legal advice, pricing promises, and publishing as approval-required.
  • If source evidence is weak, mark the item blocked or lower confidence instead of pretending.
  • Preserve source language unless the workflow asks for translation.
  • Keep every write idempotent by upserting on the item's own id field so re-running a collection pass never duplicates rows.
  • Block personalized financial advice, product suitability conclusions, return promises, policy interpretation beyond sourced text, and outbound claims without approval.

Useful Commands

node skills/kelly-insurance-intel/scripts/execute_decisions.mjs
node skills/kelly-insurance-intel/scripts/execute_decisions.mjs --apply
pnpm --dir skills/kelly-insurance-intel/content/kelly-insurance-intel-app dev

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Align all AI coding agents to a single source of truth. AGENTS.md for rules, .agents/skills/ for skills, symlinks for everything else. Use when setting up a repo for multiple agents, or when links are missing, broken, or out of date.

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月2日 更新

Read, answer and post on the Buda community forum at community.buda.im through its /api/v1/community REST API. Lists categories and posts, reads a thread with its replies, searches, and publishes posts and replies behind an explicit confirmation. Use when the user invokes $buda-community or /buda-community, asks what is happening in the Buda community, wants an unanswered question triaged or answered, or wants something posted or announced there.

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月2日 更新

Read, answer and post on the Busabase community forum at community.busabase.com through its /api/v1/community REST API. Lists categories and posts, reads a thread with its replies, searches, and publishes posts and replies behind an explicit confirmation. Use when the user invokes $busabase-community or /busabase-community, asks what is happening in the Busabase community, wants an unanswered question triaged or answered, or wants something posted or announced there.

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月2日 更新

kelly-ads

無料

Ad-campaign command desk (投放指挥台, Busabase App-in-Skill) for a cross-border e-commerce seller running Amazon Ads, Meta (FB/IG), TikTok Ads, and Google Ads. Use when the user invokes $kelly-ads or /kelly-ads, or asks about 投放, ad campaigns, ad spend, ACOS, ROAS, Amazon Ads, TikTok ads, Meta ads, Google Ads, search terms, negative keywords, bid adjustment, budget pacing, CPC spikes, rejected ads, ad anomaly detection, 广告优化, or reviewing agent-proposed adjustment cards (negative keyword, bid down/up, pause target, budget shift, creative refresh).

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月2日 更新

Busabase-backed App-in-Skill low-code agent configuration and governance console for a platform team. Use when the user invokes $kelly-agent-builder or /kelly-agent-builder, wants to review or edit a catalog of mock LLM agent configs, check quota usage, find configs that need attention, move a draft to live, pause a live agent, or archive an agent. Mock config/governance console only — it never provisions or calls any real agent.

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月2日 更新

Review board (Busabase App-in-Skill) that runs a fixed suite of mock test cases against a baseline vs candidate agent version and surfaces rubric-scored regressions before a release. Use when the user invokes $kelly-agent-eval or /kelly-agent-eval, wants to review agent-version regressions, compare baseline vs candidate quality, triage a release, or record a release approve/block decision. Deterministic mock rubric scores only — not a real LLM-judge call, and it never deploys anything.

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月2日 更新

mr-kelly のスキルをすべて見る

このスキルの問題を報告する