データ・AIのスキル

Generates NeMo Guardrails Colang (.co) files and YAML config blocks from a plain-language description of a chatbot's purpose, allowed behaviors, and constraints. Use this skill whenever a user wants to build guardrails for a chatbot, define allowed intents for an LLM, create an AI firewall with NeMo Guardrails, generate Colang flow definitions, or configure a semantic allow-list for a bot. Trigger this skill even when the user just describes what their bot should and shouldn't do — generating the Colang and YAML is almost always what they need next.

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。

Bypass AI safety filters by encoding malicious prompts using ciphers and obfuscation techniques (e.g., Base64, ROT13, Leetspeak, Morse code). This skill exploits the gap where the LLM can decode the request, but intermediate keyword-based safety classifiers cannot.

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。

Identify and simulate Data Poisoning attacks aimed at degrading or skewing an AI model's accuracy. This skill focuses on Adversarial Machine Learning concepts where attackers inject malicious or mislabelled data points into training or fine-tuning datasets (e.g., feedback loops) to bias the AI.

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。

Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.

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。

Execute sophisticated Prompt Injection and Jailbreak techniques against Large Language Models (LLMs) to bypass safety filters, extract system prompts, and manipulate the AI's output to perform malicious or disallowed actions.

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。

Execute advanced SQL Injection attacks to bypass WAFs and extract data from complex architectures. Use this skill for Boolean-Based Blind, Time-Based Blind, Second-Order SQLi, and Out-of-Band (OOB) SQLi across MySQL, PostgreSQL, MSSQL, and Oracle.

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。

Advanced techniques for bypassing LLM safety filters, instruction tuning, and system prompt restrictions using specialized linguistic constructs, hypothetical scenarios, and persona adoption.

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。

Systematically extract hidden system prompts, core directives, and invisible context intentionally concealed within Large Language Model (LLM) applications. This skill utilizes targeted linguistic engineering and boundary manipulation to bypass prompt opacity.

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。

Bypass authentication via forced browsing to protected URLs, parameter tampering (authenticated=yes, debug=true, fromtrustIP=true), session ID prediction from linear/incremental cookies, SQL injection on login forms, PHP unserialize() boolean type juggling (b:1 payload), and credential transport over HTTP. Detectable with Burp Suite, OWASP ZAP, WebGoat.

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。

Exploit AI assistants equipped with web-browsing capabilities or internal API plugins to perform Server-Side Request Forgery (SSRF). This skill details injecting prompts that force the LLM to request sensitive internal endpoints, such as underlying cloud metadata services or internal networks.

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。

Use when Agentforce run costs are climbing, you need to forecast scale, or you want to reduce tokens per conversation without hurting quality. Covers topic (now subagent) design impact on cost, prompt/template reuse, grounding size discipline, caching, and model-tier selection. Triggers: 'agentforce cost', 'tokens per conversation too high', 'reduce agentforce runs spend', 'forecast agentforce scale cost', 'einstein trust layer tokens'. NOT for capping spend per user with a budget gate and fallback — use agentforce/agent-rate-limit-strategy. NOT for org-wide model-tier and BYOLLM platform strategy — use architect/ai-platform-architecture.

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。

Designing or reviewing Agentforce actions: Flow actions, Apex invocable actions, prompt-template actions, action naming, input and output contracts, confirmation requirements, and safe error behavior. Triggers: 'agent actions', 'build an agent that can look up an order', 'make the agent able to check order status', 'give the agent a capability', 'agent that can retrieve a record', 'flow action for agent', 'agent invocable action', 'action schema design'. NOT for writing the Apex class itself — use agentforce/custom-agent-actions-apex. NOT for the reason_code error envelope that stops an agent retry loop — use agentforce/agent-action-error-handling.

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。

Use this skill when writing, debugging, or optimizing SAQL queries in CRM Analytics — covering pipeline syntax, aggregation, windowing functions (rank, dense_rank, moving_average), cogroup joins, rollup subtotals, piggyback queries, and REST API execution. NOT for SOQL GROUP BY aggregates in Apex — use apex/apex-aggregate-queries. NOT for dashboard JSON steps and bindings — use admin/analytics-dashboard-json.

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。

Use when designing how an Agentforce agent extracts structured input parameters (slots) from a user's natural-language utterance to invoke an action. Triggers: 'agent extract date from user', 'agent action argument extraction', 'agentforce slot filling', 'agent invocable input mapping', 'agent fails to fill required parameter'. NOT for action authoring (use agentforce/agent-actions) or for prompt-template variable binding (use agentforce/prompt-builder-templates).

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。

Use when learning, designing, or explaining Salesforce Reports and Dashboards from first principles — report types, custom report types, groupings, bucket fields, summary formulas, charts, dashboard components, dynamic dashboards, report subscriptions, and folder permissions. Triggers: 'how do I build a report', 'what report type should I use', 'set up a dashboard', 'joined report limits', 'bucket field vs formula', 'dynamic dashboard running user'. NOT for CRM Analytics (use crm-analytics-* skills). NOT for Einstein Discovery predictive analytics. NOT for troubleshooting missing report data caused by sharing model issues (use admin/reports-and-dashboards for that).

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。

Use when setting up, customizing, or troubleshooting the Salesforce Path component on Opportunity, Lead, Case, or custom objects. Triggers: 'add guidance to stages', 'key fields on path', 'celebrate closed won', 'path not showing', 'configure path steps', 'confetti on stage change'. NOT for creating the stage picklist — use admin/opportunity-management. NOT for in-app prompts — use admin/in-app-guidance-and-walkthroughs. Metadata: PathAssistant, PathAssistantStep, PathAssistantSettings, pathAssistantEnabled, canOverrideAutoPathCollapseWithUserPref, runtime_sales_pathassistant:pathAssistant, picklistValueName, recordTypeName, BusinessProcess.

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。

Picklist governance for Salesforce admins — Restricted vs Unrestricted, Global Value Sets vs local picklists, value deactivation that breaks reports, dependent picklists with deactivated controllers, and the 'value not in picklist' phantom-data problem. Covers the per-record-type value selection model, the API-vs-label mismatch trap, and the mass-replace-values runbook. NOT for auditing an org where invalid values already exist or record-type mappings have drifted — use admin/picklist-field-integrity-issues. NOT for creating a picklist field or wiring up a dependent picklist — use admin/picklist-and-value-sets.

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。

Revenue Intelligence setup: activating the RI app and its CRM Analytics assets, Einstein deal insights, the opportunity-change waterfall, and forecast-accuracy analytics for sales leaders. NOT for configuring the Pipeline Inspection view, its metrics and review cadence - use admin/pipeline-review-design. NOT for forecast types, categories, rollups and quotas - use admin/collaborative-forecasts.

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。

Configure and troubleshoot Salesforce Billing revenue recognition rules, schedules, and GL transaction generation under ASC 606. Triggers: 'revenue schedule not generated after order activation', 'blng__RevenueSchedule__c missing', 'blng__RevenueRecognitionRule__c on a product', 'Finance Periods not set up', 'performance obligation allocation for bundled products', 'distribution method', 'ASC 606 in Salesforce Billing'. NOT for billing schedules, invoice plans and invoice runs - use admin/billing-schedule-setup. NOT for invoice-to-payment mismatches at month-end close - use data/billing-data-reconciliation.

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。

Use when creating or managing picklist fields: choosing between Global Value Sets and object-local picklists, configuring controlling and dependent field relationships, managing picklist values, and replacing values in existing data records. NOT for why the API or an integration ignores a dependency matrix - use admin/field-dependency-and-controlling. NOT for cleaning up degraded, unrestricted or orphaned picklist values - use admin/picklist-field-integrity-issues. NOT for record type picklist filtering - use admin/record-types-and-page-layouts. Keywords: GlobalValueSet, StandardValueSet, __gvs suffix, customValue, valueSetName, valueSetDefinition, restricted picklist, GlobalValueSetTranslation, OpportunityStage, CaseStatus.

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。

Use when picklist data quality has degraded: unrestricted picklists accepting garbage API values, dependent picklist relationships bypassed by integrations, record type picklist value mappings drifting out of sync, or orphaned values appearing in reports. NOT for the value-deactivation runbook or the API-name-vs-label trap — use admin/picklist-data-integrity. NOT for initial picklist creation or Global Value Set design — use admin/picklist-and-value-sets. NOT for record type configuration itself — use admin/record-types-and-page-layouts.

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。

Use when configuring the Salesforce product catalog and pricing structure: creating Product2 records, setting up Standard and custom Pricebooks, managing PricebookEntry junction records, enabling multi-currency pricing, configuring Product Schedules (Revenue and Quantity), or troubleshooting incorrect prices on Opportunity line items and Quotes. Triggers: 'add product to pricebook', 'pricebook entry', 'standard pricebook', 'product catalog', 'multi-currency product pricing', 'product schedule', 'revenue schedule', 'quantity schedule', 'deactivate product'. NOT for bulk catalog loads — use data/product-catalog-data-model. NOT for CPQ bundles and product rules — use admin/cpq-product-catalog-setup.

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。

Configure and manage NPSP Enhanced Recurring Donations (ERD): enable ERD mode, define schedule objects, configure installment behavior, set status automation thresholds, and interpret the Upcoming Installments UI. NOT for NPSP object and field reference — use data/npsp-data-model. NOT for payment gateways — use architect/fundraising-integration-patterns.

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。

Use when a report or dashboard is slow, timing out, hitting row limits, or consuming excessive system resources on large-volume objects — covers selective filter strategy, custom report type optimization, async report execution via Analytics API, dashboard refresh scheduling, and grouping/aggregation tuning. Triggers: 'report times out', 'report is slow', 'dashboard not refreshing', 'report row limit hit', 'too many report results'. NOT for CRM Analytics / Tableau CRM performance (separate skill). NOT for sharing-model or visibility issues causing missing rows (use admin/sharing-and-visibility). NOT for building or designing reports from scratch (use admin/reports-and-dashboards-fundamentals).

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。