thinkingaiagenticengine

@thinkingaiagenticengine source repo

71 skills
0 followers
17 hours ago last updated

▌
MCP Trino · thinkingaiagenticengine bundle
Inspect Trino metadata, table schemas, query plans, EXPLAIN ANALYZE output, and existing query records through the mcp-trino MCP tools. Use when Codex needs to navigate Trino catalogs or schemas, inspect a table before writing or reviewing SQL, analyze a query plan, diagnose a Trino query ID from query-info, or explain the inspection-only limits and query visibility behavior of mcp-trino.

0
installs
▌
Churn Define · thinkingaiagenticengine bundle
Establishes churned user filtering conditions and segmentation assets. Use when users explicitly ask to define churned users, identify churned user characteristics, create churned user profiles, analyze churned users, or perform churn segmentation. Does NOT include diagnosing churn reasons or executing recall operations.

0
installs
▌
Ltv Analysis · thinkingaiagenticengine bundle
Analyzes LTV and provides optimization strategies covering LTV calculation methodology, monitoring dashboard setup, channel/server/user tier/payment point dimension analysis, and industry benchmark comparison. Use when users need to diagnose LTV decline, align LTV calculation definitions, interpret LTV trends and decay curves, or optimize LTV across dimensions.

0
installs
▌
Ltv Prediction · thinkingaiagenticengine bundle
Predict internet product user lifetime value (LTV) and lifecycle (LT) from retention and revenue data. Use when the user asks about LTV, user lifetime value, LT, user lifecycle, lifecycle forecast, payback period, retention fitting, retention decay, retention curve, channel quality assessment, per-user or per-cohort value estimation, cohort revenue projection, active days forecast, LTV segmentation — for games, tools, social, e-commerce, or any internet product. Supports both directly provided data and automated ae-cli data retrieval from a TE project, including RFM / pay-tier / VIP stratified LTV. For macro calendar-time total-revenue forecasting and acquisition-budget / DNU-ARPU target-solving, use revenue-forecast-model-cli.

0
installs
▌
Generate SQL · thinkingaiagenticengine bundle
Write Trino SQL statements based on requirements and system data specifications. Triggered only under the following conditions >> 1. When users need SQL code, such as "help me write a SQL", "generate SQL statement", "how to write this SQL", "give me a query statement". 2. When users need to query a list of players meeting certain conditions or query a player's behavior list, used to generate SQL and then initiate query requests through `ae-cli analysis adhoc run` with `--model-type sql`. 3. If the data users need can be obtained through ae-analysis (such as dashboards, reports), prioritize using the ae-analysis skill to complete the full query execution process, do not use this skill

0
installs
▌
Te Model Selector · thinkingaiagenticengine bundle
Recommend the most suitable AE (AgenticEngine) analysis model from 12 models and generate its configuration. Use when users are unsure which analysis model to choose, ask "which model to use / which one should I choose", ask whether a model fits a scenario (e.g. "can retention analysis do this"), ask which model to use for LTV / ROI / revenue, or want configuration guidance for a chosen model — with precise field mapping when a project is available, or a generic-example configuration for consultation when no project is provided. Do not use for simple data queries, executing a specific investigation, writing SQL/code, or configuring a model whose name is already known (route those to ae-analysis).

0
installs
▌
Rfm Segmentation · thinkingaiagenticengine bundle
Build end-to-end RFM user segmentation on real AE/TE transaction data: resolve the person-level analysis entity, define universe/window/transaction caliber, compute and score R/F/M, validate segment quality, create AE tags only after confirmation, create per-segment user clusters for activation only after confirmation, and recommend segment-specific operations. Use for RFM analysis, user value tiering, high-value/lapsed payer identification, R/F/M scoring, or RFM-based LTV/retention/campaign analysis. Not for direct LTV forecasting or non-RFM segmentation.

0
installs
▌
Pricing Evaluation · thinkingaiagenticengine bundle
Evaluates product pricing rationality through conversion rate analysis, competitive price comparison, user willingness-to-pay analysis, and scenario-based pricing strategies with actionable price optimization recommendations. Use when users need to evaluate product pricing rationality, analyze price elasticity, design price tiers, or optimize pricing strategies.

0
installs
▌
Ad Delivery Analysis · thinkingaiagenticengine bundle
Comprehensive ad campaign performance analysis covering channel efficiency, conversion funnels, attribution analysis, retention quality, and ROI calculation on the ThinkingEngine (TE) platform. Use when users need to evaluate ad campaign performance, analyze channel efficiency, diagnose funnel drop-offs, attribute conversions to touchpoints, or calculate ROI across channels.

0
installs
▌
Journey Intent Parser · thinkingaiagenticengine bundle
Parses natural language descriptions of ThinkingData journey canvas into structured intent JSON for downstream node orchestration. Triggered when users mention "generate journey", "create journey", "build a campaign", "new user onboarding", "churn recall", "time-based split", "scheduled push", etc. Output serves as input for `references/journey-node-builder`.

0
installs
▌
New Hero Insight · thinkingaiagenticengine bundle
Analyzes new hero/card launch impact including acquisition rate, gacha cost, payment impact, progression depth, battle performance, clear efficiency, and ecosystem health, providing strength ratings (T0-T4), balance recommendations, and operational strategies. Use when users need to analyze the impact of a new hero or card launch — such as acquisition rate, gacha cost, payment impact, or balance issues.

0
installs
▌
Retention Verification · thinkingaiagenticengine bundle
Verifies retention data, diagnoses discrepancies between retention and event analysis, and explains retention statistical logic. Use when users report retention data discrepancies, need to verify retention calculations, or want to understand why retention numbers don't match event analysis.

0
installs
▌
Community Ops Report · thinkingaiagenticengine bundle
Generates community operations sentiment reports in two modes — a concise daily flash report (day-over-day, T-1 vs T-2) and a structured weekly summary (week-over-week, past 7 days with cross-day sentiment arcs) — using ae-cli community commands to consolidate overview metrics, sentiment, key events, representative quotes, and security/compliance risk signals. Use when users request a community daily report, yesterday's battle report, daily sentiment summary, community weekly report, weekly operations summary, or a weekly recap for community projects.

0
installs
▌
Ae Risk Monitoring · thinkingaiagenticengine bundle
Trigger when game operations, risk, or data teams need external monitoring over AE/TE event data for account bursts, traffic drops, withdrawals, payment failures, or custom formulas. Accept a verified project plus event/property mappings and a rule configuration; return a read-only query plan, backtest evidence, external schedule, deduplicated masked alerts, and an audit trail. Do not use for AE native alerts, automatic user enforcement, or monitoring without data-freshness validation.

0
installs
▌
Gift Push Strategy · thinkingaiagenticengine bundle
Helps create behavior-triggered and scenario-based gift pack push strategies for numeric progression games, providing lifecycle-based, user tier-based, and trigger scenario-based strategy matrices. Supports SLG, MMORPG, Card, Casual, Racing, Shooter and other game genres. Use when users need to design or optimize gift pack push strategies for games.

0
installs
▌
Drama Retention Analyzer · thinkingaiagenticengine bundle
Decomposes short drama retention through a 5-layer funnel (traffic acquisition, opening hook, plot viewing, payment conversion, long-term return) and outputs layered actionable optimization strategies with per-episode churn inflection point diagnosis. Accepts ThinkingData project ID, drama name, and drama type as input via ae-cli. Supports 5 optional drill-down dimensions (segment, time, social, genre comparison, ROI). Use when users need to analyze short drama retention, churn, or per-episode completion rates. Not applicable to long-form dramas, games, e-commerce, or any non-short-drama content.

0
installs
▌
Single User Inspector · thinkingaiagenticengine bundle
Queries individual user profiles, tracks behavior events, analyzes payment history, monitors game progress, and diagnoses churn reasons, applicable to game operations, planning, and customer service teams. Use when users need to check a specific user/player, view user details, payment records, game progress, or ask why a user churned.

0
installs
▌
Channel Quality Analysis · thinkingaiagenticengine bundle
Analyzes game channel effectiveness through multi-dimensional metrics including CPI, retention, payment, LTV, and ROI, providing channel scoring, problem diagnosis, and budget optimization recommendations. Use when users need to evaluate or compare game channel quality, diagnose channel performance issues, optimize acquisition budgets, or set up channel monitoring.

0
installs
▌
Game Economy Balance · thinkingaiagenticengine bundle
Diagnose confirmed or suspected game economy imbalance from macro production-consumption ratio to micro source-point and user breakdown, localize inflation or deflation root causes, output quantified intervention strategies, and build anomaly alert mechanisms. Use when: a game operations team has observed resource over-production or depletion, currency devaluation, abnormal hoarding, suspicious studio/cheat farming, or needs source attribution, remediation parameters, rollback design, or a general economy monitoring system. Do NOT use for proactive cross-domain early-warning inspection while macro economy totals still appear normal, including combat-meta concentration, nurturing breadth, backpack accumulation, equipment recycle-before-use trends, and monetization-linked slow variables; route those to game-economy-inspection. Do NOT use for single-metric dashboard configuration, general DAU/retention analysis without economy context, payment funnel setup, or ad attribution tracking.

0
installs
▌
Level Churn Analyzer · thinkingaiagenticengine bundle
Diagnose game level churn by identifying chokepoint levels, analyzing root causes, and providing actionable optimization recommendations. **Standard Analysis**: Triggered by "level churn analysis", "users stuck at level X", "chokepoint diagnosis". **Comparison Mode**: Triggered by "compare before and after update", "did the patch improve retention", "analyze event impact". **Applicable Games**: All games with level-based progression (Card, RPG, SLG, Casual, Match-3, Runner, etc.).

0
installs
▌
Puzzle Iaa Analytics · thinkingaiagenticengine bundle
Analyze puzzle IAA game post-launch version data covering retention, levels, monetization, segmentation, and churn. Trigger when reviewing casual/puzzle game retention, level experience, ad placements, user segmentation, or churn attribution. Not for ad-hoc single-metric queries or non-game analytics.

0
installs
▌
Pvp Winrate Analyzer · thinkingaiagenticengine bundle
Analyze how PVP win rate relates to retention, payment, and player progression in games. Use for win-rate distribution, matchmaking-health, inverted-U checks, tier comparisons, and PVP balance recommendations backed by TE project data.

0
installs
▌
First Purchase Analysis · thinkingaiagenticengine bundle
Analyzes first purchase conversion rate through funnel analysis, channel segmentation, user tier analysis, and activity effect evaluation with actionable optimization recommendations. Use when users need to improve first purchase conversion rate, diagnose first purchase rate decline, or optimize first purchase activity design.

0
installs
▌
Payment Funnel Analysis · thinkingaiagenticengine bundle
Analyzes payment conversion funnels covering funnel setup, event tracking configuration, conversion data analysis, and A/B test-driven optimization, applicable to general payment funnels, first purchase funnels, and gacha funnels. Use when users need to build or analyze payment conversion funnels, diagnose payment conversion rate decline, locate churn nodes, or optimize payment paths.

0
installs
▌
Funnel Misconceptions · thinkingaiagenticengine bundle
Diagnoses funnel counting rules, explains common pitfalls, and helps troubleshoot funnel or conversion rate anomalies. Use when users report that funnel conversion counts look wrong, users are missing from funnel results, or conversion rates seem inconsistent with event data.

0
installs
▌
Te User Id Debug · thinkingaiagenticengine bundle
Diagnoses user fragmentation caused by multi-platform reporting (client-side + server-side), detects Account ID/Distinct ID missing ratios, analyzes user behavior sequences, and provides code-level solutions. Use when users report duplicate user records, fragmented user profiles across platforms, or missing Account ID/Distinct ID issues in TE.

0
installs
▌
Repeat Purchase Analysis · thinkingaiagenticengine bundle
Analyzes repeat purchase behavior applicable to game subscriptions, short drama memberships, tool app subscriptions, and e-commerce repurchase scenarios. Use when users need to diagnose repeat purchase rate decline, assess purchase health, compare repurchase behavior across segments, or analyze repurchase trends.

0
installs
▌
SQL Performance Optimizer · thinkingaiagenticengine bundle
Identifies slow SQL queries, unreasonable indexes, and inefficient writing patterns, providing actionable rewrite solutions and tuning suggestions based on execution plans and database optimization rules. Special support for Trino SQL optimization, including partition field usage and field naming conventions. Use when users need to optimize slow SQL queries, identify inefficient writing patterns, or get tuning suggestions based on execution plans.

0
installs
▌
User Tag System Designer · thinkingaiagenticengine bundle
Designs hierarchical user tag systems based on actual tracking data, automatically identifying industry categories and providing tag business definitions, calculation logic, value tiering rules, and business application scenario guidance. Use when users need to design or build a user tag system, define tag business rules, or establish tag calculation logic.

0
installs
▌
System Field Reference · thinkingaiagenticengine bundle
Help users reference system preset fields in the frontend analysis models of the AE. System fields are visible in SQL queries by default but cannot be used directly in frontend analysis models. Must use this skill when the user wants to use system fields (system properties) in frontend analysis models, mentions "system fields", "default fields", or "hidden fields", wants to reference hidden fields that are visible in SQL but not in frontend analysis models, or asks how to expose system fields to frontend models such as Event Analysis, Funnel Analysis, or Retention Analysis. This skill guides users through the complete workflow of "Create and Connect" and "Create Virtual Property".

0
installs
▌
Revenue Forecast Model CLI · thinkingaiagenticengine bundle
Forecasts game revenue using real DAU/DNU/ARPU/retention data queried via ae-cli, with a Python engine supporting forward prediction, reverse target-solving, and DNU-ARPU dual-drive optimization. Use when game operations need to plan future revenue, set acquisition budgets, or figure out how many new users are required to hit a revenue target.

0
installs
▌
Propensity Score Matching · thinkingaiagenticengine bundle
Trigger when game operations, marketing, product, or data teams need to estimate the incremental effect of a non-random campaign, offer, message, feature, channel, or intervention from user-level CSV, spreadsheet, database or warehouse, or AE/TE data. Validate pre-treatment covariates, estimate propensity scores, match comparable controls, diagnose overlap and balance, and return ATT, confidence bounds, matched users, and quality evidence. Do not use when a credible randomized experiment exists, treatment timing is unknown, or observed covariates cannot support a defensible comparison.

0
installs
▌
Game Economy Inspection · thinkingaiagenticengine bundle
Proactive game economy ecology health inspection using the 'slow variable + cross-domain correlation' methodology. Inspects combat, economy, equipment, backpack, and monetization domains together to detect gradual structural degradation while macro economy totals may still appear normal. Covers nurturing currency devaluation, equipment recycle anomalies, content pacing imbalance, and related ecosystem issues. Trigger for routine or event-driven early-warning inspection, hero/meta diversity analysis, or monitoring of this Skill's defined slow-variable signals. Use ae-cli, read the matching references/ command manual, and never guess project_id, event names, or parameter formats. Do NOT use when a production-consumption imbalance is already confirmed or when source-point breakdown, suspicious-user investigation, quantified intervention design, or a general economy dashboard is needed; route those to game-economy-balance. Do NOT use for single-metric ad-hoc queries or non-game analysis; route those to ae-analysi

0
installs
▌
Device Performance Analysis · thinkingaiagenticengine bundle
Diagnoses APP performance issues by automatically matching core performance analysis fields from TE system tables, covering device compatibility, frame rate & lag, page loading, and crash & exceptions analysis, with field matching confirmation, professional report output, and compliant SQL generation. Use when users need to diagnose APP performance issues such as device compatibility problems, frame rate drops or lag, slow page loading, or crash and exception analysis.

0
installs
▌
Community Hottopic Insight · thinkingaiagenticengine bundle
Generates a structured topic analysis report including executive summary, public-sentiment overview and timeline, key discussion hotspots, sentiment slices, cross-channel social insights, and actionable operational recommendations by automatically invoking ae-cli community commands to collect corpus data and adapting to industry context. Use when users ask to analyze a topic, generate a topic analysis report, or perform topic analysis for a community project.

0
installs
▌
Analysis Scope Alignment · thinkingaiagenticengine bundle
Aligns and explains analytical scope for dashboards, reports, queries, SQL, tags, cohorts, virtual attributes, dimension-table attributes, and related analysis objects. Use when users ask about the scope, definition, or coverage of any of these analysis objects.

0
installs
▌
Drama Quality Assessment · thinkingaiagenticengine bundle
Quantitatively scores a single short drama across nine quality dimensions (first-episode appeal, completion quality, in-episode pacing, cliffhanger effect, inter-episode retention, binge depth, payment conversion, heat trend, and user engagement) and provides AI-powered diagnosis and optimization suggestions based on ThinkingEngine tracking data. Use when the user asks to evaluate a short drama's episode quality, diagnose episode-level quality issues, or assess drama performance. Requires a TE project ID. Not for long-form dramas, games, or general retention-only analysis; use drama-retention-analyzer for funnel-based retention drill-downs.

0
installs
▌
Rate Change Significance · thinkingaiagenticengine bundle
Analyze whether a binary rate differs significantly and meaningfully between two periods, versions, cohorts, groups, or the same users before and after. Use for retention, conversion, repurchase, churn, renewal, payment and other 0/1-rate comparisons when the user asks whether an uplift/drop is real, whether a campaign or version improved the rate, whether the sample supports a conclusion, whether overlapping users require paired analysis, or whether Z-test, Fisher exact, or McNemar is appropriate. Includes cohort selection, sample-quality checks, overlap-aware test routing, reproducible statistics and business interpretation. Not for continuous metrics, multi-period forecasting, or auditing how the source metric was calculated.

0
installs
▌
Ae Freeze Inactive Dashboards · thinkingaiagenticengine bundle
Automatically identifies and freezes inactive dashboards with no visits in the past 30/60/90 days (configurable) using dashboard_search event data from an Audit Project, executed via ae-cli. Use when users need to identify and freeze inactive dashboards to reduce clutter and resource usage.

0
installs
▌
Game Activity Evaluation · thinkingaiagenticengine bundle
Analyzes game activity effectiveness through user growth, retention, payment behavior, and ROI metrics with actionable optimization recommendations. Supports new server launches, seasonal limited-time events, recharge/gacha activities, veteran player recall campaigns, and collaboration partnerships. Use when users need to evaluate game activity effectiveness, measure activity ROI, or diagnose activity performance issues.

0
installs
▌
Ae Feishu Data Permission Sync · thinkingaiagenticengine bundle
Trigger when a Feishu spreadsheet defines account-to-platform data permissions that must be compared with, added to, or synchronized into one explicitly selected AE/TE project. Resolve accounts and existing access, build a deterministic change plan, preserve project roles, require approval before permission mutations, and verify every result. Do not use for organization-wide access, unspecified projects, arbitrary role changes, or sheets without an unambiguous account and permission mapping.

0
installs
▌
Payment Attribution Analysis · thinkingaiagenticengine bundle
Diagnoses payment rate anomalies and attributes payment changes to root causes by breaking down payment drivers (Revenue = Active × Rate × ARPPU), identifying key conversion nodes, and supporting multi-dimension analysis across channel, server, user segmentation, product node, activity/version, and time dimensions. Use when users need to diagnose payment rate anomalies, investigate revenue decline, or attribute payment changes to root causes.

0
installs
▌
Audit Project Usage Analysis · thinkingaiagenticengine bundle
Analyze system usage of an AE project explicitly named, translated, or confirmed as "Audit Project". Aggregate per-user tracking-event counts for analysis, engage, and agent modules over a recent time window, assign usage tags (deep usage, viewer, engage task, data export), and assess module value and project activity. Trigger when the target project has already been identified as Audit Project and the user asks who uses which features, for per-user usage statistics, for analysis/engage/agent module usage, or for a system value assessment. Do not use for an unidentified project's generic usage question, dashboard freeze/cleanup actions, unrelated ad-hoc queries, or non-AE platform data.

0
installs
▌
Gift Pack Penetration Analysis · thinkingaiagenticengine bundle
Analyzes gift pack penetration rate through funnel analysis, user tier segmentation, and scenario-based timing strategies with actionable optimization recommendations including content, pricing, and exposure optimization. Use when users need to improve gift pack penetration rate, diagnose gift pack sales anomalies, or optimize gift pack design.

0
installs
▌
Data Inconsistency Debug · thinkingaiagenticengine bundle
Performs step-by-step comparison across analysis models, definitions, time dimensions, filter conditions, and system configurations to locate root causes of data discrepancies between reports and provide alignment solutions. Use when users report data discrepancies between TE reports — such as different metrics for the same event, mismatched totals across dashboards, or inconsistent results after changing filters.

0
installs
▌
Game Testing First Day Report · thinkingaiagenticengine bundle
Generate a first-day game testing report from TE data, covering acquisition, monetization, progression, and data quality. Trigger when the user wants to review or analyze first-day game test/launch performance data, including first-day metrics, ROI, or post-launch day-one results. For game projects only; confirm data model compatibility for non-game projects.

0
installs
▌
Community Analyzing Theme Comment · thinkingaiagenticengine bundle
Perform deep analysis of a topic’s comment section and generate a structured analytical report. Use this skill when users need an in-depth comment analysis for a specific topic (post or video).

0
installs
▌
Data Integration Assistant · thinkingaiagenticengine bundle
Helps troubleshoot ThinkingData SDK setup, event reporting, data pipeline configuration, and data quality problems during integration. Use when users encounter issues with SDK integration, data ingestion, or data integration tool configuration.

0
installs
▌
Dashboard No Data Troubleshooting · thinkingaiagenticengine bundle
Performs minimal investigation of dashboards showing no data, all zeros, or abnormal drops — checking dashboard config, spot-checking one report, then verifying the event source to quickly determine whether the issue is time range, filter/metric config, or tracking/data ingestion. Use when a dashboard shows no data, all zeros, or an abnormal drop.

0
installs
▌
Filter Result Deviation Troubleshooting · thinkingaiagenticengine bundle
Investigates filter result deviations layer by layer based on report definition, time, dedup, properties, and detail evidence to locate root causes. Use when TE/TA analysis shows filter results inconsistent with expectations, cross-report results don't match, filter results are abnormally high or low, results are empty, or show abnormal fluctuations.

0
installs
▌
Ae Data Integration Helper · thinkingaiagenticengine bundle
Answers questions about ThinkingData SDK integration and usage, including the LogBus2 data import tool. Trigger words: 怎么接入 / 如何集成 / SDK / 埋点 / 报错 / 使用方式 / API / LogBus / tracking / integration / how to integrate / data import / データ連携 / インテグレーション / 트래킹 / 연동.

0
installs
▌
Ae Experiment Insight · thinkingaiagenticengine bundle
Diagnose and interpret AE/TE A/B experiments from configuration and report evidence through a defensible decision. Use when the user asks what an experiment means, whether it can roll out, why a result is not significant, why group sizes or exposure are wrong, why treatment results conflict, whether the report is trustworthy, or what to do next. Covers SRM, duration sufficiency, novelty effects, metric conflicts, missing or anomalous data, design reasonableness, data reliability, metric interpretation, trend and segment analysis, root-cause hypotheses, and rollout recommendations. All platform discovery and reads must use ae-cli.

0
installs
▌
Ae Generate Tracking Code · thinkingaiagenticengine bundle
Interactive generation of AE tracking code, LogBus2 configuration, and debug scripts from a tracking plan. Trigger words: 代码埋点、埋点代码、tracking code、埋点落地、logbus 配置、AE 上报代码、generate tracking code、insert tracking、トラッキングコード、트래킹 코드. Supports independent output mode selection per platform (insert/snippet). Server-side defaults to LoggerConsumer + LogBus2 architecture.

0
installs
▌
Ae Generate Tracking Plan · thinkingaiagenticengine bundle
Interactive generation of an AE tracking plan and upload. Trigger words: 埋点方案、埋点模板、tracking plan、AE 方案生成、create tracking plan、トラッキングプラン、트래킹 플랜. Follows anchor → draft → refine → token → upload five-phase workflow. Deliverable is a real tracking plan created in the AE platform.

0
installs
▌
Ae Analysis Global · thinkingaiagenticengine
Use when AE/TE analysis requests mention query/current/service/deployment clusters, current cluster (当前集群), cluster info (集群信息/有哪些集群), global or multi-cluster data, all clusters/all servers, GLOBAL/SLAVE, query-cluster, cluster_query_scope, slave_cluster_id, country/region/server/shard/site/market routing, or when cluster may mean query cluster rather than audience/user segment.

0
installs
▌
Ae Data Integration · thinkingaiagenticengine bundle
Bring local CSV, TSV, TXT, JSON, JSONL (NDJSON), XLS, and XLSX files into AE end-to-end: identify the source's business meaning, generate and confirm a tracking plan, transform rows into UE records, and upload. Also supports privacy-preserving local analysis and handing a small file to AE Agent. Use whenever a user wants to import offline/local data into AE or analyze a file without uploading it. Trigger words: 本地数据导入 / 离线数据 / 数据文件 / 文件导入 / 文件上报 / CSV 导入 / Excel 导入 / TSV 导入 / JSON 导入 / 导入到 AE / 导入到 ThinkingData / local data import / import local file.

0
installs
▌
Ae Project Semantic · thinkingaiagenticengine bundle
Use when generating, testing, submitting, reviewing, or publishing governed project semantic candidates from AE/TE project asset packages. This skill owns progressive asset-scope consent, recommendation quality gates, evidence authority, topic-domain grouping, candidate JSON generation, CLI closed-loop validation, and frontend review acceptance. Do not use it for ordinary analysis questions that only consume already published semantics.

0
installs
▌
Ae Experiment Design · thinkingaiagenticengine bundle
Design AE/TE A/B experiments from a business goal through a reviewable draft. Use when the user asks to form an experiment hypothesis, assess metric readiness, choose or create metrics and Features, design groups or traffic, estimate sample size or duration, create an experiment draft, or run readiness and conflict checks. SDK guidance is a conditional branch: enter it only when the user explicitly asks about an A/B experiment SDK, client SDK integration, experiment SDK code generation, or SDK troubleshooting; do not include SDK work in an ordinary experiment-design or draft-creation request.

0
installs
▌
Ae Experiment · thinkingaiagenticengine bundle
Use when managing Atlas AB experiments, traffic layers, Features, metrics, buckets, and experiment reports through ae-cli

0
installs
▌
Ae Kb Discovery · thinkingaiagenticengine
Discover which AE/TE/ThinkingEngine knowledge bases accessible to the current user are worth searching, and decide whether to search at all, through read-only operations. Use when the user explicitly asks to search knowledge bases, internal documentation, or company materials. Also use when a task requires internal facts or business context, including product design and rules, events, campaign or operations calendars, release and iteration records, workflows, policies, and terminology; use it as well when this context is needed to explain data analysis results, anomalies, or trends and form evidence-backed conclusions. Do not use if the user explicitly asks not to access knowledge bases. This skill covers discovery and candidate selection; run the actual `+index` / `+grep` / `+read` / `+ask` retrieval with the `ae-kb` skill.

0
installs
▌
Ae Community · thinkingaiagenticengine bundle
AE community analysis and data reporting for posts, comments, topics, livestreams, customer-service chats, WeCom after-sales groups, and in-game chat. Use for community content insight, sentiment, intent, evidence drill-down, community data ingestion/import/submission, and WeCom chat data integration (社区数据上报、导入、提交社区数据、企微聊天数据接入).

0
installs
▌
Ae Capability · thinkingaiagenticengine
AE/TE capability gateway discovery and generic invocation with ae-cli. Use when the user needs to list or search available capabilities, inspect an unknown capability schema/risk/auth contract, optionally validate complex input or dry-run before execute, or invoke a long-tail capability that has no curated ae-cli command. Always discover and inspect before composing input; never guess capability IDs or input fields. Prefer on-demand validate OR dry-run — do not stack both by default.

0
installs
▌
Ae Metadata · thinkingaiagenticengine bundle
AE/TE metadata capability-gateway CLI: metadata data-table management and property dimension-table binding. Metadata CLI routes through the analysis gateway. Input-file upload and event/property detail belong to ae-analysis.

0
installs
▌
Ae Analysis · thinkingaiagenticengine bundle
Use ae-cli for AE/TE analysis-side data questions, asset operations, and asset governance: reports, analysis boards, BI dashboards, ad-hoc models, drilldown, detail data, alerts, clusters, tags, metrics, metadata, project configuration, tracking plans, governance asset lists/rules/lineage/impact/dependency, batch asset operations, projects, and resource links. Use when the user asks to query data, explain a change, export evidence, or inspect/create/update/govern analysis assets.

0
installs
▌
Ae System · thinkingaiagenticengine bundle
AE Agent system administration CLI for root and agent administrators. Use when the user asks to manage Agent members, sandboxes and shared tools, company model visibility/defaults/pricing, usage statistics and exports, cost quotas, balance alerts, IM channels, channel routing, WhatsApp Web linking, or Feishu user bindings. Must use ae-cli system commands, discover real IDs before writes, and never attempt to bypass a permission denial.

0
installs
▌
Ae Dataops · thinkingaiagenticengine bundle
AE Data Development and Operations: Data warehouse management, flow orchestration, IDE queries, and data integration

0
installs
▌
Ae Engage · thinkingaiagenticengine bundle
AE Engage capability gateway: config center, flows, push/config channels, strategies, templates, task management, operation activities, and query lifecycle. Trigger words: config center, scene config, push channel, config channel, operation strategy, operation task, operation activity, query lifecycle, template, config item, Engage, Hermes, engage-scene, engage-setting, engage-flow, engage-task, engage-activity, engage-query.

0
installs
▌
Ae Kb · thinkingaiagenticengine bundle
AE/TE knowledge base CLI manual for creating, importing read-only compiled snapshots, querying, LLM-powered ask, listing accessible knowledge bases and their sources, deterministic index/grep/read retrieval, checking status, uploading, compiling, schema generation, URL sources, source deletion, and knowledge base deletion. Use when the user asks to manage TE/AE/ThinkingEngine knowledge bases, import a compiled Markdown ZIP snapshot, upload documents or URLs to a knowledge base, query knowledge, ask knowledge bases with an LLM, list accessible knowledge bases or source metadata, inspect knowledge base indexes, search knowledge base pages, read a specific knowledge base page, check knowledge base status, generate schemas, compile knowledge, remove sources, or delete a knowledge base. To choose which knowledge base is worth searching, use the ae-kb-discovery skill first; this skill runs the retrieval once a target is chosen. Must use ae-cli kb commands and must not guess knowledge base names, scopes, page paths,

0
installs
▌
Ae Team · thinkingaiagenticengine bundle
AE/TE/ThinkingEngine/ThinkingAI ae-cli manual for AI Agent Team tasks: managing teams (list, create, update, delete, AI-generate, templates) and executing TeamRuns (start, chat, cancel, reply, result, artifacts). Use when the user asks to find a team, run a team task, check run status, retrieve results or artifacts, or set up multi-agent workflows. Must use ae-cli, read the matching references/<command>.md before composing commands, and never guess team IDs, run IDs, config structures, or parameter formats.

0
installs
▌
Ae Agent · thinkingaiagenticengine bundle
AE Agent platform CLI for Agent, approval, archived conversation, automation, model, MCP, Skill, attachment, and user-memory work. Use when managing these resources, browsing Agent markets, handling approval requests and tasks, restoring archived conversations, creating scheduled automations, persisting user memory, or answering from user preferences, background, stable workflows, or historical conventions.

0
installs
▌
CLI Self Check · thinkingaiagenticengine bundle
检测新合并到 te-cli 的 CLI 功能是否合理。从命令注册、业务域↔skill 配对、skill 文档覆盖、skill 内部一致性、用户文档同步、工程健壮性六个维度扫描，定位会导致命令加载失败、AI agent 读空文档瞎猜参数、用户文档滞后等问题。当合并了新命令域/命令、新增或修改 skill、做发版前自检、或需要评估 CLI 功能完整性时使用。

0
installs

71 published skills