AI Agent Workflow Collection

Create or update App-in-Skill patterns: Codex skills that bundle a local provider-backed web app for review, approval, dashboards, or lightweight workflows. Use when the user wants a skill with an embedded local UI, provider handoff, local files, Busabase, locks, app launcher, schemas, or a reusable App-in-Skill scaffold.

Personal App-in-Skill ad-campaign command desk (投放指挥台) 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).

Public 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. Local mock config/governance UI only — it never provisions or calls any real agent.

Local App-in-Skill review board 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.

Agent Fleet Observability Desk App-in-Skill — local mock dashboard visualizing a fleet of LLM agents running behind a shared AI gateway for your organization. Use when the user invokes $kelly-agent-observability or /kelly-agent-observability, wants to review agent health, call volume, latency, error rates, cost, or trace-level chain breaks across an agent fleet. This is a demo/reference dashboard over generated mock telemetry, not a live monitoring integration.

Kelly AI Newsroom: App-in-Skill daily industry intelligence cockpit for AI/news-source intelligence. Use when the user asks for AI trend sourcing, news-source monitoring, buyer-intent analysis, or a reusable industry-intelligence cockpit. Prepares news/source signals, buyer-intent interpretation, approved sales actions, and channel drafts for review before any external handoff.

Design human-and-Agent operating apps on Busabase using Research, Plan, Action, and Retrospective workflows. Use when a user wants an approval queue, research desk, planner, action console, operating dashboard, control panel, or collaboration workspace. This skill is Busabase-only and must use both $busabase and $busabase-app-creator; it does not define a local provider, runtime, data layer, or deployment path of its own.

Build, maintain, and run conformance tests for canonical App-in-Skill projects created by kelly-app-skill-creator. Use when a Kelly app skill needs contract checks, local server smoke tests, responsive browser acceptance, temporary open-source Busabase integration, environment-gated Busabase Cloud OAuth verification, lazy provisioning checks, persistence tests, AirApp parity tests, or CI coverage. Keep app creation in kelly-app-skill-creator and own only the reusable test harness, per-skill fixtures, execution gates, diagnostics, and truthful pass/fail/skip reporting.

Personal App-in-Skill finance anomaly review desk that imports the three business tables — orders, invoices, payments/receipts (回款) — from CSV/JSON exports, flags anomalies with deterministic rules, and runs a human review queue with auditable decisions. Use when the user invokes $kelly-audit or /kelly-audit, mentions finance audit, order invoice payment reconciliation, 对账, 应收, 回款, 发票异常, receivables aging, overdue receivables, duplicate payments, missing invoices, amount mismatches, or anomaly review.

Kelly Beauty Intel: App-in-Skill daily industry intelligence cockpit for beauty, wellness, and medical aesthetics. Use when the user asks about beauty, medical aesthetics, wellness, treatments, competitor offers, IG/Xiaohongshu content,美容,医美, or health-service sales scenes. Prepares news/source signals, buyer-intent interpretation, approved sales actions, and channel drafts for review before any external handoff.

Local dashboard App-in-Skill over mock user-behavior funnel data (browse → search → compare → booking attempt/abandon → complete) for a generic consumer booking product. Use when the user invokes $kelly-behavior-predict or /kelly-behavior-predict, wants to review funnel drop-off, per-segment predicted next actions, or backtest a rule-based "predicted next action" heuristic against a mock historical sample. Fully offline mock data and a deterministic, hand-recomputable rule — never a real ML/LLM model, never a live system.

Brand-narrative single source of truth (TALE: Trace/Architect/Land/Evaluate) with a local App-in-Skill workbench. The agent drafts positioning, the message house of value pillars, the story bank, evidence-backed proof points, and vocabulary/tone guardrails; the human curates which drafts become the CANONICAL narrative; a drift monitor flags off-brand usage across channels. Use when the user invokes $kelly-brand or /kelly-brand, mentions brand narrative, brand messaging, positioning, message house, value pillars, story bank, proof points, tone/vocabulary guardrails, narrative quality (NQS), brand drift, or wants a single source of truth for what the brand says.

Outbound email-marketing desk (App-in-Skill) for building segments, drafting campaigns, newsletters, and sequences, running pre-send deliverability and subject-line QA, and approving every send before it is scheduled. Structured around the SEND discipline — Setup, Engage, Nurture, Deliver — with an email-quality-auditor gate (EQS score + SHIP/FIX/BLOCK verdict). Use when the user invokes $kelly-campaigns or /kelly-campaigns, or mentions email marketing, campaigns, newsletters, drip/welcome/win-back sequences, broadcasts, segments, subject-line A/B tests, deliverability (SPF/DKIM/DMARC/spam score/inbox placement), or wants to review and approve marketing email before it is sent. This is OUTBOUND marketing to a subscriber list, distinct from kelly-email inbox triage (incoming mail).

Lightweight contract lifecycle management App-in-Skill for contract inventory, lifecycle status, owners, obligations, renewal notices, and simple approval reminders. Use when the user invokes $kelly-clm or /kelly-clm, mentions CLM, contract lifecycle management, 合同管理, 合同台账, contract repository, obligation tracking, renewal reminders, notice deadlines, contract owners, signature readiness, or wants a simple local UI to review contract status without doing detailed legal redlines.

Repurpose source content into channel-ready drafts with a local review UI and approval/export workflow.

Personal App-in-Skill command desk for influencer/creator marketing — the agent sweeps and fit-scores creator candidates, drafts outreach and briefs, and gates content before it ships; the human reviews creator cards, approves outreach/briefs/contracts, and tracks campaign ROI in a local review dashboard. Use when the user invokes $kelly-creators or /kelly-creators, mentions influencer or creator marketing, creator discovery, fit scoring, outreach DMs, campaign briefs, UGC, sponsorship or partnership deals, content review / FTC disclosure gating, or campaign ROI, or wants to review/approve agent-drafted creator outreach before it is sent through other channels.

Personal App-in-Skill CRM operator for contacts, companies, deals, and agent-drafted follow-ups in a local review dashboard. Use when the user invokes $kelly-crm or /kelly-crm, mentions CRM, pipeline, contacts, companies, deals, follow-ups, relationship management, meeting-note capture, outreach drafts, next steps, or wants to review/approve agent-drafted follow-up messages before they are sent through other channels.

Review-queue App-in-Skill that scores candidate SME financing deals (revenue-based/RBF-style credit) with a deterministic, fully auditable rule-based rubric — never an LLM or API call. Use when the user invokes $kelly-deal-scorer or /kelly-deal-scorer, wants to review a deal-underwriting queue, score financing candidates, compute a composite score breakdown, see a suggested revenue-share rate range, or record approve/send-back/reject decisions for a private-credit or RBF-style lending pipeline.

Plan, verify, and track demo/marketing video production in Busabase — idea to hook/pain-point/storyboard, codebase claim verification, recording progress, post-production handoff, and HyperFrame (Remotion) linkage. Use when the user invokes $kelly-demo-video-factory or /kelly-demo-video-factory, wants to plan a product demo video, write a storyboard, verify a video script's product claims against the codebase, track which shots are recorded, or hand a finished storyboard off to editing/Remotion.

Personal App-in-Skill ops desk for Kelly's multi-product SaaS fleet. Use when the user invokes $kelly-devops or /kelly-devops, or asks about uptime, service health checks, SSL certificate expiry, domain renewal, domain expiry, API key rotation, token rotation reminders, cloud spend anomaly, billing spikes, ops desk, incident review, or reviewing agent-proposed action cards (renew domain, rotate key, investigate spend, restart service, acknowledge incident).

Digital-human implementation and demo skill for choosing, prototyping, and QA-ing low-cost 2D photoreal digital humans and high-control 3D custom digital humans. Use when the user wants a digital-human avatar, AI host, customer-service presenter, multimodal voice-to-lip-sync video stream, vendor comparison for services such as Silicon Intelligence / Tencent Zhiying / ZEGO-like real-time providers, or a UE/Unity 3D digital-human architecture and launch-ready demo.

Cross-Entity Disclosure Tracker App-in-Skill — a local review workspace that helps a compliance/IR team assemble and track a standardized disclosure package per financing vehicle (fund/SPV), across a generic onshore origination entity, an offshore fund-manager entity, and a listing/exchange venue. Use when the user invokes $kelly-disclosure-tracker or /kelly-disclosure-tracker, wants to review disclosure checklists, vehicle readiness, cross-entity reconciliation flags, or reviewer notes across multiple financing vehicles. Local review workspace only — it never files anything or calls any external system.

Short-drama and product-video development skill for planning drama projects through a bundled local App-in-Skill UI, with each project linked to a specified HyperFrame project and each episode linked to a HyperFrame composition for final motion/video tuning. Use when the user asks to create, edit, organize, or review short-drama scripts, product explainer episodes, character consistency cards, series bibles, episode beat sheets, storyboard shots, HyperFrame project/composition links, production checklists, or a drama planning workbench.

Kelly Ecommerce Intel: App-in-Skill daily industry intelligence cockpit for e-commerce and cross-border sellers. Use when the user asks about e-commerce, cross-border selling, product trends, competitor prices, listing optimization, ads,电商, or跨境 scenes. Prepares news/source signals, buyer-intent interpretation, approved sales actions, and channel drafts for review before any external handoff.