AI & ML

banibratachatterjee Bundle

Model and verify unlocked package dependencies, version pinning, and promotion. NOT for 1GP managed packages.

banibratachatterjee Bundle

Use this skill when gathering or evaluating requirements for a Salesforce Enterprise Territory Management (ETM) territory design: alignment criteria, coverage model selection, assignment rule logic, geographic considerations, hierarchy depth and breadth, and user-to-territory ratios. Trigger keywords: territory design, territory alignment, territory model requirements, sales coverage model, territory criteria, geographic territory, named account territory, overlay territory. NOT for ETM configuration or setup steps — use enterprise-territory-management for that. NOT for role hierarchy design — use sharing-and-visibility.

banibratachatterjee Bundle

Use this skill to implement custom Apex MCP tool classes by extending McpToolDefinition from the salesforce-mcp-lib package. Covers inputSchema(), validate(), and execute() override patterns, JSON schema construction, SOQL and DML inside tools, error handling, and tool registration in the Apex REST endpoint. Trigger keywords: McpToolDefinition, extend McpToolDefinition, Apex MCP tool, mcp-tool Apex, JSON-RPC tool, salesforce-mcp-lib tool class. NOT for the initial server installation and proxy setup (see salesforce-mcp-server-setup), NOT for MCP Resources or Prompts, NOT for OmniStudio or Flow-based tool definitions.

banibratachatterjee Bundle

Use when configuring Model Builder in Salesforce to register external LLMs or select standard models for Agentforce and Einstein features. Covers model registration, API key configuration, model aliases, and cost/performance tradeoffs. NOT for Trust Layer configuration (use agentforce-trust-layer).

banibratachatterjee Bundle

Use this skill when configuring or troubleshooting Salesforce Enterprise Territory Management (ETM): territory models, territory types, territory hierarchies, account assignment rules, opportunity territory assignment, and forecast by territory. Trigger keywords: territory model, territory hierarchy, ETM, assign accounts to territories, territory forecast, territory activation. NOT for role hierarchy (use sharing-and-visibility). NOT for Legacy/Original Territory Management (pre-ETM).

banibratachatterjee Bundle

Designing Omni-Channel capacity models for service orgs: agent capacity allocation, channel weighting (cases, chats, calls), skills matrix design, overflow strategy, presence configuration, and interruptible work patterns. Use when planning capacity units, defining Service Channel weights, or designing agent skills-based routing capacity. NOT for Omni-Channel routing configuration or queue assignment rules (use multi-channel-service-architecture). NOT for Einstein Bot design (use einstein-bot-architecture).

banibratachatterjee Bundle

Use this skill when designing API-led connectivity architecture for Salesforce integrations — covering System/Process/Experience layer separation, governance policy (catalog, versioning, deprecation, rate limits), multi-consumer strategy, and Agentforce Agent Fabric integration. Trigger keywords: API-led connectivity, MuleSoft three-tier, System API, Process API, Experience API, integration layer governance, API versioning policy, Agent Fabric. NOT for individual Apex callout implementation (use integration-pattern-selection), HTTP error response contracts (use api-error-handling-design), or retry backoff mechanics (use retry-and-backoff-patterns).

banibratachatterjee Bundle

Use this skill to design, configure, and troubleshoot the Field Service Lightning (FSL) Optimizer — including selecting optimization type (Global, In-Day, Resource Schedule), understanding the priority-score model, configuring travel mode (Aerial vs Street-Level Routing), and tuning optimizer behavior for specific scheduling objectives. NOT for configuring scheduling policies, work rules, service objectives weights, or the Dispatcher Console dispatch settings.

banibratachatterjee Bundle

Use when embedding OmniScripts in Lightning Web Components, registering custom LWC elements inside OmniScript screens, or calling OmniScript/Integration Procedures from LWC. Triggers: embed omniscript in LWC, custom LWC element in OmniScript, call OmniScript from Lightning page, omnistudio-omni-script tag, seed data JSON, OmniScript launch from LWC. NOT for standalone LWC development, standard Flow embedding, or OmniScript-to-OmniScript embedding.

banibratachatterjee Bundle

Use this skill when building custom channel integrations with the Agentforce Agent API or BYOC (Bring Your Own Channel) for CCaaS — covering session lifecycle management, webhook handling, externalSessionKey design, sequenceId sequencing, BYOC Interaction API integration, and conversation state management. NOT for standard channels (Embedded Service, Slack, SMS/MMS via standard Messaging). NOT for agent-channel-deployment (which handles standard channel setup and activation). NOT for custom agent actions or Apex topics.

banibratachatterjee Bundle

Use when designing or evaluating a Salesforce conversational AI deployment that involves Agentforce agents, Einstein Bots, or a combination of both. Triggers: Agentforce topic design, Einstein Bot handoff to Agentforce, multi-agent orchestration, conversational channel routing, Atlas Reasoning Engine behavior. Does NOT cover Einstein Bot standalone implementation (see einstein-bot-architecture), Omni-Channel routing for human agents, or Flow-only automation without a conversational surface.

banibratachatterjee Bundle

Design Invocable Apex actions that return deterministic, agent-friendly errors instead of surfacing raw exceptions to the LLM. NOT for generic Apex exception handling or Flow fault paths.

banibratachatterjee Bundle

Use this skill to install and configure the salesforce-mcp-lib Apex package and npm stdio proxy so that an MCP client (Claude Desktop, Cursor, ChatGPT) can call Salesforce org data and logic via the Model Context Protocol. Trigger keywords: MCP server, salesforce-mcp-lib, Claude Desktop Salesforce, MCP proxy setup, Apex JSON-RPC, MCP Connected App. NOT for Salesforce Hosted MCP Servers (Agentforce-native hosted endpoints), NOT for Flow-based tool definitions, NOT for OmniStudio integrations.

banibratachatterjee Bundle

Design Agentforce conversations that span multiple turns without losing context: session variable scoping, conversation memory, clarifying-question patterns, topic-to-topic handoff, and the right abstractions for accumulating state across turns. NOT for single-turn agent actions (use agent-actions). NOT for channel-specific conversation UX (use agent-channel-deployment).

banibratachatterjee Bundle

Plan, batch, and monitor Salesforce sharing recalculation jobs — including OWD changes, sharing rule add/remove, role hierarchy restructuring, and Apex managed share rebuild — to avoid multi-hour background jobs and data-access blackouts. NOT for diagnosing data-skew root causes (use admin/data-skew-and-sharing-performance), NOT for designing the sharing model itself (use admin/sharing-and-visibility), and NOT for Apex managed sharing row-cause creation (use apex/apex-managed-sharing).

banibratachatterjee Bundle

Use when migrating an existing Einstein Bot (legacy or Enhanced) to Agentforce: feature mapping, conversation design translation, cutover planning, hybrid bot/agent architecture, and context handoff. Triggers: 'migrate einstein bot to agentforce', 'convert legacy bot to agentforce', 'einstein bot retiring deadline', 'hybrid bot agentforce pattern', 'bot dialog to topic migration'. NOT for new Agentforce setup with no existing bot — use agentforce/agentforce-agent-creation instead.

dsmmartin Bundle

The database schema changed and the agent is returning wrong answers. Fix it.

dsmmartin Bundle

Fix an agentic NL2SQL system after a database schema change. Inspect the schema contract, agent prompts, and vector database chunks for stale field references and update them.

dsmmartin Bundle

Complete schema drift repair for the Ghost Contributors NL2SQL system. Patches all four layers (YAML contract, ChromaDB RAG chunks, NL2SQL prompt, RAG prompt) using validated tooling. Includes dry-run preview, step-by-step fallback, validation, and rollback.

dsmmartin Bundle

Four-layer schema sync procedure for the Ghost Contributors NL2SQL system after a database migration. Covers YAML contract, ChromaDB RAG chunks, NL2SQL prompt, and RAG prompt with a step-by-step repair sequence.

banibratachatterjee Bundle

Diagnose and mitigate Salesforce data skew — ownership skew (single user owns >10,000 records) and parent-child skew (>10,000 children under one parent) — that cause sharing recalculation slowness, group membership lock errors, and record-level locking failures. NOT for sharing model design decisions (use sharing-and-visibility) or query optimization (use soql-query-optimization).

akashrpatil Bundle

Identify and exploit vulnerabilities in Applications integrating Large Language Models (LLMs). Prompt Injection involves crafting inputs that override the original system instructions provided by the developer, allowing an attacker to exfiltrate data, bypass restrictions, or manipulate the AI's output logic.

banibratachatterjee Bundle

Creating and integrating custom Lightning Web Components within OmniScripts: LWC override patterns, pubsub event handling, custom validation, OmniStudio data passing conventions. Use when a standard OmniScript element cannot meet a UX requirement. NOT for standalone LWC development (use lwc/* skills). NOT for Integration Procedures (use integration-procedures). NOT for embedding an OmniScript inside an LWC (use omnistudio-lwc-integration).

lukasreese Skill

Power BI PBIP Dependency Analyzer. Analyzes all Power BI Project (.pbip) files, TMDL exports, and semantic model definitions to map dependencies between measures, columns, tables, M/Power Query, relationships, and report visuals. Use this skill EVERY TIME the user asks to: find unused measures or columns, analyze dependencies, clean up a data model, check what would break if something is deleted, perform impact analysis, identify orphaned objects, audit model quality, or asks 'what can I delete'. Also trigger when the user uploads .pbip files, model.bim files, TMDL exports, or report.json files and wants to understand their structure or dependencies. Trigger phrases include: 'analyze dependencies', 'find unused', 'what can I delete', 'clean up model', 'impact analysis', 'dependency check', 'unused measures', 'unused columns', 'orphaned objects', 'model audit', 'PBIP analysis'.

geegewu Bundle

小红书自动发帖（narrative 链路）。含 MCP 发布、note_id 安全恢复、内容准备、图片生成。用户说"发小红书"、"发帖"、"publish to XHS"时触发。

posthog Bundle

Draw 2D shapes (filled rectangles, outlined frames, ASCII bitmaps) on the 32×32 MCP pixel grid. Use this skill whenever the user asks to draw a square, rectangle, box, frame, outline, border, sprite, or other 2D shape on the pixel grid, or when the task involves placing a block or bitmap at specific grid coordinates. The pixel-grid MCP server only exposes a 1D `write(offset, bits)` primitive; this skill compiles a 2D drawing into the sequence of `write` calls that implements it.

zhekinmaksim Bundle

Encrypt secrets and PII before they reach LLM providers via MEMORY.md. Intercept save-to-memory requests containing credentials, API keys, or personal data; replace sensitive payload with opaque reference; store real value in local age-encrypted vault. Agent resolves references locally at tool-execution time via veil_resolve.

waytoaic Skill

Research Amazon keyword demand, competition, and ASIN keyword signals with SIF MCP. Use when the user asks about 关键词需求, keyword demand, keyword lifecycle, 竞争格局, 是否值得打某个词, 词根趋势, ASIN 靠哪些词带量, or wants data-backed keyword opportunity analysis.

waytoaic Skill

Diagnose Amazon traffic changes with SIF MCP. Use when the user asks why an ASIN or Listing 流量下跌/上涨, wants traffic trend analysis, 流量结构拆解, 自然流和广告流变化, listing traffic overview, or wants to judge whether traffic changes already affected sales.

skytiger6724 Skill

Intelligent model routing for OpenClaw. Automatically selects between Gemini 3, GPT-5.3 Codex, and Claude 4.6 based on task complexity.

skytiger6724 Skill

name: agent-browser

skytiger6724 Bundle

自動化 LLM Wiki 知識編譯技能。當啟動時，它會掃描指定目錄下的新檔案，並依照 Karpathy 的 LLM Wiki 邏輯（Ingest -> Summarize -> Compile -> Log）將其整合進 Obsidian 知識庫。

maorenxin Bundle

Launch a multi-agent harness (Planner + Generator + Evaluator, pass^k reliability) to iteratively build and deliver high-quality software. Accepts either a vague task description OR a detailed pre-written plan — the Planner auto-detects and adapts.

willwebster5 Bundle

> SOC skill v3 loaded — agent-delegated phased architecture. Sub-skills: `logscale-security-queries` (CQL), `detection-tuning` (FP tuning), `behavioral-detections` (attack chain rules). Agents: `alert-formatter` (Haiku), `cql-query` (Sonnet), `mcp-investigator` (Sonnet), `evidence-summarizer` (Sonnet), `syntax-validator` (Haiku).

skytiger6724 Skill

Compresses context to fit within model token limits while preserving the most critical information for the task at hand.

q2wxec Bundle

Generates a delegation rules document for multi-agent workflows, covering what to keep at orchestrator level vs. what to delegate, and how to write self-contained sub-agent prompts. Use this skill when the user asks to "design multi-agent systems", "delegate work to sub-agents", "improve agent prompt quality", "design orchestrator/worker patterns", "write better sub-agent prompts", or "avoid duplicating work in agents". Also activate when someone is building an orchestrator that spawns workers and wants to avoid re-doing work the sub-agents already handle.