Skip to content

PranavNagrecha/AwesomeSalesforceSkills / .claude/skills/salesforce-agentforce

salesforce-agentforce

Verified

Router for the 53 SfSkills `agentforce` skill packages. Agentforce and Einstein: agents, topics, actions, prompt templates, grounding, guardrails, evaluation and production readiness. Use when the request mentions Agentforce, agent topic, agent action, prompt builder, Einstein, Trust Layer, grounding, RAG, guardrails, agent evaluation, prompt injection. Finds and opens the exact skill package to read; it does not contain the guidance itself.

FileKindSize
SKILL.mdskill md5.1 KB
references/skill-index.mdmarkdown15.4 KB

references/skill-index.md

View on GitHub
# SfSkills — `agentforce` skill roster (53 packages)

The zero-setup lookup path: this file ships with the plugin and needs
no search index. Scan it, pick a package by name, then read that
package from the repository root under `${CLAUDE_PLUGIN_ROOT}`.

Generated from `registry/skills.json` by `scripts/build_plugin.py`.
Do not hand-edit.

**How to read a gloss.** The package id is on the line already, so the
gloss does not repeat it. It carries what the id cannot, in this order:
the package's own **trigger vocabulary** (the phrasings that should
land here), then its **`NOT for …` redirect** (which names the package
to use instead), then a short scope phrase if there is room. A
`…` marks a truncation, always at a word, keyword or
whole-clause boundary. Budget: 220 characters.

**A `NOT for X - use Y` clause is the most useful thing on the line.**
If your question is X, stop and open Y instead of this package.

- `skills/agentforce/agent-action-error-handling/SKILL.md` — Design Invocable Apex actions that return deterministic, agent-friendly errors …. NOT for authoring the action itself — @InvocableMethod schema, labels, security context — use agentforce/custom-agent-actions-apex.
- `skills/agentforce/agent-action-input-slot-extraction/SKILL.md` — Triggers: 'agent extract date from user', 'agent action argument extraction', 'agentforce slot filling', 'agent invocable input mapping', …. NOT for action authoring (use … use agentforce/prompt-builder-templates
- `skills/agentforce/agent-action-unit-tests/SKILL.md` — Apex test patterns for @InvocableMethod agent actions: per-reason-code branch coverage, bulk …. NOT for testing whether the agent routes to the right topic or answers well — use agentforce/agent-testing-and-evaluation.
- `skills/agentforce/agent-actions/SKILL.md` — 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', …. NOT for writing the Apex … use agentforce/custom-agent-actions-apex
- `skills/agentforce/agent-channel-deployment/SKILL.md` — Triggers: 'deploy agent to website', 'add Agentforce to Slack', 'enable agent for mobile app', 'configure embedded service for agent', …. NOT for agent logic design — use … use agentforce/agent-topic-design
- `skills/agentforce/agent-deployment-checklist/SKILL.md` — Canonical go-live checklist for Agentforce deployments with rehearsed rollback …. NOT for the technical pre-prod verification behind those sign-off rows — cost … use agentforce/agentforce-production-readiness-checklist
- `skills/agentforce/agent-metric-dashboards/SKILL.md` — Build the executive KPI dashboard for Agentforce: adoption, deflection, latency, cost …. NOT for the platform's own session tracing, Agent Analytics and health monitoring — use agentforce/agentforce-observability.
- `skills/agentforce/agent-rate-limit-strategy/SKILL.md` — Control LLM spend and Apex governor exposure for high-traffic Agentforce agents via per-user token budgets …. NOT for reducing tokens per conversation in the first place — use agentforce/agentforce-cost-optimization.
- `skills/agentforce/agent-script-dsl/SKILL.md` — Triggers: 'write or debug Agent Script', 'how do I deploy an Agentforce agent using source control', 'convert an agent topic to a subagent', …. NOT for Apex-based agent actions — use agentforce/custom-agent-actions-apex.
- `skills/agentforce/agent-security-review/SKILL.md` — Pre-production security checklist for Agentforce deployments: agent run-as …. NOT for the full go-live readiness gate covering cost telemetry, rate limits … use agentforce/agentforce-production-readiness-checklist
- `skills/agentforce/agent-testing-and-evaluation/SKILL.md` — Triggers: 'how do I test my Agentforce agent', 'agent routes to wrong subagent', 'write utterance tests', 'regression test after topic change', …. NOT for agent creation … use agentforce/agentforce-agent-creation
- `skills/agentforce/agent-topic-design/SKILL.md` — Triggers: 'agentforce subagents (formerly topics)', 'topic design', 'topic selector', 'agent scope boundary', 'handoff conditions'. NOT for restricting what the agent may do or … use agentforce/agentforce-guardrails
- `skills/agentforce/agentexchange-publishing/SKILL.md` — an ISV or consulting partner is creating, pricing, publishing, or maintaining an AgentExchange listing …. NOT for building the agent or managed package itself (use … use devops/isv-license-management-and-trialforce
- `skills/agentforce/agentforce-agent-creation/SKILL.md` — Triggers: 'create agentforce agent', 'agent not appearing to users', 'how to activate agent', 'agent channel setup', 'agent lifecycle', …. NOT for designing what the agent can DO — an … use agentforce/agent-actions
- `skills/agentforce/agentforce-agent-handoff-patterns/SKILL.md` — Triggers: 'agent to human handoff', 'agentforce escalate to omni channel', 'agent to agent handoff', 'transfer conversation with context', …. NOT for topic scope and selector design — use agentforce/agent-topic-design.
- `skills/agentforce/agentforce-cost-optimization/SKILL.md` — Triggers: 'agentforce cost', 'tokens per conversation too high', 'reduce agentforce runs spend', 'forecast agentforce scale cost', 'einstein trust layer tokens'. NOT for … use agentforce/agent-rate-limit-strategy
- `skills/agentforce/agentforce-custom-channel-dev/SKILL.md` — building custom channel integrations with the Agentforce Agent API or BYOC …. NOT for standing up a standard channel (Embedded Service, Slack, Experience Cloud, Messaging) — use agentforce/agent-channel-deployment.
- `skills/agentforce/agentforce-custom-lightning-types/SKILL.md` — overriding the default UI of an Agentforce agent action's Apex input or output …. NOT for standard agent actions with primitive inputs/outputs (only Apex-class input/output can be … use flow/flow-custom-property-editors
- `skills/agentforce/agentforce-eval-harness/SKILL.md` — Triggers: agent eval, hallucination, doesn't hallucinate, agentforce offline evals, rubric for agent response. NOT for deciding which layers of testing the agent needs — use agentforce/agentforce-testing-strategy.
- `skills/agentforce/agentforce-grid/SKILL.md` — Triggers: Agentforce Grid, workbook, worksheet, grid column, data column, AI column, action column, bulk AI update, Flex Credits per row, metered compute. NOT for … use admin/ai-ethics-and-governance-requirements
- `skills/agentforce/agentforce-guardrails/SKILL.md` — Triggers: agent guardrails, agent out of scope, restrict agent behavior, topic scope, subagent scope, agent fallback, Escalation topic, abuse prevention, …. NOT for Trust … use agentforce/prompt-builder-templates
- `skills/agentforce/agentforce-in-slack/SKILL.md` — Triggers: 'add General Slack Actions topic to agent', 'configure canvas creation for Agentforce in Slack', …. NOT for the initial Slack OAuth install, DM vs channel-mention … use agentforce/agent-channel-deployment
- `skills/agentforce/agentforce-multi-turn-patterns/SKILL.md` — Design Agentforce conversations that span multiple turns without losing context: session variable …. NOT for deciding the topic boundaries themselves or out-of-scope behavior — use agentforce/agent-topic-design.
- `skills/agentforce/agentforce-observability/SKILL.md` — Triggers: 'agentforce session analytics', 'how to query agent conversation data', 'monitor agentforce agent effectiveness', 'agent deflection rate', …. NOT for Trust Layer audit … use agentforce/einstein-trust-layer
- `skills/agentforce/agentforce-persona-design/SKILL.md` — defining or refining the tone, voice, and behavioral personality of an …. NOT for writing the actual conversational copy — utterances, fallback messages, escalation phrasing — use admin/agent-conversation-design.
- `skills/agentforce/agentforce-pii-redaction/SKILL.md` — Triggers: agentforce pii, pii redaction, data masking llm, prompt pii filter, audit pii leakage. NOT for turning on the platform's own masking, zero-retention and audit-trail … use agentforce/einstein-trust-layer
- `skills/agentforce/agentforce-production-readiness-checklist/SKILL.md` — Triggers: 'we want to ship our Agentforce agent next week', 'pre-prod readiness review for our Service Agent', …. NOT for the lighter five-block activation sign-off artifact — use agentforce/agent-deployment-checklist.
- `skills/agentforce/agentforce-prompt-versioning/SKILL.md` — Triggers: prompt template versioning, prompt changelog, prompt rollback, A/B prompt test, agentforce prompt release. NOT for the CMDT-backed binding that swaps the live … use agentforce/prompt-template-versioning
- `skills/agentforce/agentforce-sales-ai-setup/SKILL.md` — Setup and configuration of Einstein for Sales AI features: Opportunity …. NOT for configuring or troubleshooting Einstein Activity Capture and Relationship Insights in … use agentforce/einstein-copilot-for-sales
- `skills/agentforce/agentforce-service-ai-setup/SKILL.md` — Triggers: Einstein for Service setup, enable Case Classification, enable Article Recommendations, enable Reply Recommendations, enable Work Summaries, …. NOT for tuning or … use agentforce/einstein-copilot-for-service
- `skills/agentforce/agentforce-testing-strategy/SKILL.md` — Triggers: agentforce testing, agent regression suite, prompt golden set, action unit test agentforce. NOT for hallucination evals, fixture format, or scoring rubrics — use agentforce/agentforce-eval-harness.
- `skills/agentforce/agentforce-tool-use-patterns/SKILL.md` — Pick the right tool shape for each agent action: Apex invocable vs Flow action vs …. NOT for designing or reviewing an action whose shape is already settled — naming, confirmation, error … use agentforce/agent-actions
- `skills/agentforce/custom-agent-actions-apex/SKILL.md` — Building custom Apex-based actions for Agentforce agents: designing …. NOT for choosing between Apex, Flow, External Service and prompt-template tool shapes — use agentforce/agentforce-tool-use-patterns.
- `skills/agentforce/data-cloud-grounding-for-agentforce/SKILL.md` — Triggers: agent grounding, retriever, DMO, data graph, RAG, vector index, citations. NOT for building or tuning the vector index itself — chunk size, embedding model … use agentforce/data-cloud-vector-search-dev
- `skills/agentforce/data-cloud-vector-search-dev/SKILL.md` — Developing Data Cloud vector search: configuring search indexes, selecting chunking …. NOT for admin-side index upkeep in Setup — refresh mode, PII field exclusion, rebuilds — use data/vector-database-management.
- `skills/agentforce/einstein-bots-to-agentforce-migration/SKILL.md` — Triggers: 'migrate einstein bot to agentforce', 'convert legacy bot to agentforce', 'einstein bot retiring deadline', 'hybrid bot agentforce pattern', …. NOT for new … use agentforce/agentforce-agent-creation
- `skills/agentforce/einstein-copilot-for-sales/SKILL.md` — Sales-specific AI features in Sales Cloud: Einstein Opportunity Scoring setup and …. NOT for the license check and enablement sequence before any of these are turned on — use agentforce/agentforce-sales-ai-setup.
- `skills/agentforce/einstein-copilot-for-service/SKILL.md` — Service-specific AI features in Service Cloud: Case Classification setup and …. NOT for the license, entitlement and data-threshold check before first enablement — use agentforce/agentforce-service-ai-setup.
- `skills/agentforce/einstein-discovery-development/SKILL.md` — Triggers: Einstein Discovery, smartdatadiscovery, predict endpoint, bulk scoring job, model refresh job, prediction definition, story deployment, …. NOT for authoring the story in … use admin/einstein-discovery-setup
- `skills/agentforce/einstein-next-best-action/SKILL.md` — Guide practitioners through building …. Triggers: next best action, NBA strategy, surface recommendations. NOT for training a custom prediction model on your own records — use agentforce/einstein-prediction-builder.
- `skills/agentforce/einstein-prediction-builder/SKILL.md` — Einstein Prediction Builder for creating custom binary classification predictions on Salesforce objects …. NOT for authoring an Einstein Discovery story in CRM Analytics Studio — use admin/einstein-discovery-setup.
- `skills/agentforce/einstein-search-personalization/SKILL.md` — Einstein Search personalization: configure search result ranking, promoted results, searchable objects …. NOT for search on an Experience Cloud site or community portal — use lwc/experience-cloud-search-customization.
- `skills/agentforce/einstein-trust-layer/SKILL.md` — Triggers: trust layer, data masking, zero data retention, ZDR, toxicity detection, AI audit trail, grounding controls, PII masking LLM, …. NOT for redaction you build yourself … use agentforce/agentforce-pii-redaction
- `skills/agentforce/employee-hr-service-agent-rollout/SKILL.md` — Triggers: 'we want an HR self-service agent for leave and benefits', 'employees keep emailing HR for time-off balance — can Agentforce answer that?', …. NOT for general … use agentforce/agentforce-guardrails
- `skills/agentforce/mcp-tool-definition-apex/SKILL.md` — Triggers: McpToolDefinition, extend McpToolDefinition, Apex MCP tool, mcp-tool Apex, JSON-RPC tool, salesforce-mcp-lib tool class. NOT for a native Agentforce agent action — use agentforce/custom-agent-actions-apex.
- `skills/agentforce/model-builder-and-byollm/SKILL.md` — configuring Model Builder in Salesforce to register external LLMs or select …. NOT for deciding the model-tier or multi-agent platform strategy before you register anything — use architect/ai-platform-architecture.
- `skills/agentforce/prompt-builder-templates/SKILL.md` — Triggers: prompt template, Prompt Builder, field generation, record summary, sales email template, flex template, grounding, merge fields, LLM template, …. NOT for … use agentforce/prompt-template-versioning
- `skills/agentforce/prompt-injection-defense/SKILL.md` — Red-team an Agentforce agent against prompt-injection and jailbreak attacks; codify …. NOT for the overall agent test plan (topic coverage, golden sets, regression harness) — use agentforce/agentforce-testing-strategy.
- `skills/agentforce/prompt-template-versioning/SKILL.md` — Lifecycle management for Prompt Builder templates: version, test, promote, roll …. NOT for source-control layout, model-version pinning, or versioning agent topic prompts — use agentforce/agentforce-prompt-versioning.
- `skills/agentforce/rag-patterns-in-salesforce/SKILL.md` — Grounding Agentforce agents with retrieved knowledge using Data Cloud vector search …. NOT for the Query API, Data Cloud access tokens, or Easy vs Advanced index mechanics — use agentforce/data-cloud-vector-search-dev.
- `skills/agentforce/sales-coach-agent-rollout/SKILL.md` — Triggers: 'roll out sales coach agent', 'set up Agentforce sales coach for our reps', 'sales coach not engaging reps on early-stage opps', …. NOT for rolling out an … use agentforce/employee-hr-service-agent-rollout
- `skills/agentforce/salesforce-mcp-server-setup/SKILL.md` — Triggers: MCP server, salesforce-mcp-lib, Claude Desktop Salesforce, MCP proxy setup, Apex JSON-RPC, MCP Connected App. NOT for writing the Apex tool classes the server exposes — use agentforce/mcp-tool-definition-apex.
- `skills/agentforce/sf-to-llm-data-pipelines/SKILL.md` — Triggers: export Salesforce data to external LLM, Bulk API extract for embeddings, send Salesforce records to OpenAI, pipe Salesforce data to Pinecone, …. NOT for vector … use agentforce/rag-patterns-in-salesforce

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall