salesforce-agentforce
Use for Salesforce Agentforce work — Agents (Topics, Actions), prompt templates, Atlas reasoning engine, Trust Layer integration, agent testing.
What this skill does
# salesforce-agentforce Salesforce Agentforce platform skill. Agents, Topics, Actions, prompt templates, Atlas Reasoning Engine. ## Concepts - **Agent** — autonomous worker with goals + topics - **Topic** — capability cluster (e.g. "Service", "Sales") with actions - **Action** — operation the agent can take (Apex/Flow/Prompt-based) - **Prompt template** — reusable prompt with merge fields - **Atlas** — reasoning engine that picks topics and actions - **Trust Layer** — masking, audit, retention enforcement ## Method (build an action) 1. **Decide action type:** - **Apex action** — programmatic; full control; deploy via metadata - **Flow action** — declarative; click-built; bulkification limits - **Prompt template action** — LLM-powered; needs grounding 2. **Inputs/outputs.** Strict shape. Atlas needs deterministic schema. 3. **Grounding** for prompt actions: which records / files / data feed the prompt? Inline static data is anti-pattern. 4. **Testing.** Unit-test the action. Integration-test via "Try Agent" in Setup. Capture eval cases. 5. **Topic assignment.** Action belongs to a Topic; Topic to an Agent. Wrong topic = action never invoked. ## Output / deliverable shape ``` Agent: <name> Topic: <name> Action: <name> Type: <Apex | Flow | Prompt template> Files: force-app/main/default/genAiPlugins/<Agent>.genAiPlugin-meta.xml force-app/main/default/genAiFunctions/<Action>.genAiFunction-meta.xml force-app/main/default/classes/<ActionName>.cls (if Apex) force-app/main/default/genAiPromptTemplates/<Template>.genAiPromptTemplate-meta.xml (if prompt) Test plan: Unit: <test class> Integration: <Setup → Agent → "Try"; eval cases> Eval: <prompt eval rubric> Trust Layer: PII masking: <enabled | reason if not> Audit logging: <captured destination> Retention: <policy> ``` ## Rules - **Action signatures are strict.** Atlas can only call deterministic shapes. No `any`-typed inputs. - **Prompt actions need grounding** from records/files, not invented data. - **Trust Layer settings** are per-org policy. Don't override without security review. - **Test eval cases captured to memory** so future agent changes can re-run. - **`with sharing` on Apex actions** unless explicitly auditable reason for `without sharing`. ## Anti-patterns - Prompt template with hardcoded data (defeats grounding) - Apex action that returns `String` for everything (Atlas can't reason about untyped output) - Topic assignment by guess (read existing topics first) - Disabling Trust Layer in non-test orgs - Action that performs DML without audit trail ## When NOT to use - Non-Agentforce projects — irrelevant - Static automation (Flow with no AI) — `/siftcoder:salesforce-flow` ## Subagent dispatch - `salesforce-architect` for org-level Agentforce review (topic coverage, security, capacity) - `apex-bulkifier` for Apex actions - `general-purpose` for the metadata generation ## Key references - Salesforce Agentforce docs: developer.salesforce.com/docs/einstein/genai/guide/ - Trust Layer docs: help.salesforce.com (Einstein Trust Layer) ## Value over native CC CC will write Salesforce code if asked. CC won't naturally know Agentforce-specific shapes (genAiPlugin metadata, genAiFunction structure, Atlas reasoning constraints, Trust Layer policy axes). The platform-specific knowledge IS the value.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.