全部 Agent Skills
41,263 个结果
- Humanizer Zh Twkevintsai1202潤飾中文文章、評論和文件，刪去空話、重複與公式化表達（俗稱去 AI 味、AI 寫作痕跡）， 讓文字更自然，同時保留事實、確定程度和作者聲音。適用於編輯或審閱已有文字；不用於 判斷作者身分，也不保證通過 AI 偵測器。若使用者要求清理不可見 Unicode、文字型 AI 浮水印或檔案 provenance，改用 $text-watermark-cleaner-zh-tw，不要在本 skill 中把 語氣改寫冒充成浮水印已移除。
- Home Assistant Best Practiceshomeassistant-aiHome Assistant (HA) best practices. Load first, before answering or exploring, on any HA request. TRIGGER THIS SKILL WHEN: - Creating or editing automations, scripts, scenes, dashboards, blueprints - Choosing template sensors, helpers, or Jinja macros - Restructuring triggers, conditions, or modes; button, remote, or event-entity automations - Renaming entities or migrating device_id to…
- Ab Test PlanIndranil BanerjeePlan an A/B test by script: sample size per variant, days to run, stopping rules. "how many visitors per variant"
- Aeo GeoIndranil BanerjeePlan AEO/GEO strategy to get cited by AI: content, entities, schema, 90-day plan. "how do we get cited by AI"
- Agency DashboardIndranil BanerjeeBuild the agency dashboard across all client brands: health, pacing, risk. "how are all our clients doing"
- Agent Readiness AuditIndranil BanerjeeAudit agent readiness by script: AI-crawler rules, product schema, no-JS HTML, feeds. "can AI agents use our site"
- Analytics InsightsIndranil BanerjeeDesign the analytics layer with script-backed benchmarks: KPI trees, report templates, MMM, cookieless. "define our KPIs"
- Anomaly ScanIndranil BanerjeeScan connected platforms for anomalies against stored baselines, with likely causes. "why did our CPA spike"
- Audience IntelligenceIndranil BanerjeeResearch audiences: personas, JTBD maps, RFM segments. One persona doc → audience-profile. "run a JTBD analysis"
- Autopilot StatusIndranil BanerjeeShow autopilot status: health, auto-corrections, guardrails, escalations. "what did the autopilot change"
- Backlink GapIndranil BanerjeeFind backlink gap domains linking to competitors, not you, scored by script. "who links to our competitors but not us"
- Brand SetupIndranil BanerjeeSet up or update the brand profile every skill reads: voice, audience, compliance. "set up a new brand"
- Budget OptimizerIndranil BanerjeeOptimize channel budget with diminishing-returns models. Pacing → budget-tracker. "is our channel split right"
- Budget TrackerIndranil BanerjeeProject ad budget pacing by script from live accounts or given numbers: month-end overspend. "are we overspending this month"
- Campaign AuditIndranil BanerjeeAudit all campaigns running for a brand across channels, with 4-tier triage. "we just inherited this account"
- Campaign OrchestratorIndranil BanerjeeOrchestrate a campaign lifecycle: briefs, budget models, UTMs, post-mortems. "set up UTM naming conventions"
- Campaign StatusIndranil BanerjeeShow status of every tracked campaign: health, spend, executions, pending approvals. "what campaigns are running right now"
- CheckIndranil BanerjeeRun the scored pre-publish gate via eval-runner.py: claims, brand voice, compliance, AI tells. "check this before we publish"
- Churn RiskIndranil BanerjeeScore churn risk per segment by script, with tiered retention playbooks. "which customers are about to churn"
- Client ReportIndranil BanerjeeWrite a white-labeled report for one client from tracked data. All clients → agency-dashboard. "prepare the monthly client report"
- Client Validation DocumentIndranil BanerjeeProduce the Part 5 client validation document: evidence-cited findings for client decisions. "prepare v1 findings for client review"
- Cohort AnalysisIndranil BanerjeeRun cohort analysis: retention matrix and LTV by cohort. Churn scoring → churn-risk. "build a retention matrix"
- Competitor MonitorIndranil BanerjeeMonitor competitors over time: baseline sites, pricing and ads by script, flag changes. "track our competitors over time"
- ConnectIndranil BanerjeeConnect a known MCP integration: check the registry and status, return exact setup steps. "connect Google Ads"