Skip to content

forcedotcom/sf-skills / plugins/builder/agentforce-adlc/skills/agentforce-generate

agentforce-generate

Flagged

Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates, reviews, or changes .agent files or aiAuthoringBundle metadata; asks to fix AgentScript, audit an existing agent, run an AgentScript health check, common-pitfall review, or baseline-versus-candidate repair loop; changes a response, action, subagent, route, state flow, or Agent Spec; migrates or upgrades a legacy GenAiPlannerBundle Agentforce agent (NOT an Einstein Bot) to an aiAuthoringBundle (Agent Script) agent; previews, debugs, deploys, publishes, or tests agents; uses sf agent generate/preview/publish/test; or manages Agentforce MCP servers, tools, assets, or authentication. DO NOT TRIGGER when: Apex, Flow, Prompt Template, Experience Cloud, or general Salesforce CLI work is unrelated to Agent Script; the source is an Einstein Bot (BotDefinition/BotVersion) — use agentforce-bot-upgrade; or the primary input is a production session or trace ID rather than an agent artifact.

FileKindSize
README.mdmarkdown5.4 KB
SKILL.mdskill md31.7 KB
assets/agent-spec-template.mdmarkdown6.4 KB
assets/agents/README.mdmarkdown2.6 KB
assets/agents/hello-world.agentother1.9 KB
assets/agents/knowledge-grounded.agentother5.6 KB
assets/agents/local-info-agent-annotated.agentother17.0 KB
assets/agents/order-service.agentother11.7 KB
assets/agents/production-faq.agentother3.9 KB
assets/agents/production-faq.bundle-meta.xmlconfig161 B
assets/agents/router-first.agentother5.6 KB
assets/agents/simple-qa.agentother1.9 KB
assets/agents/template-multi-subagent.agentother5.4 KB
assets/agents/template-single-subagent.agentother2.6 KB
assets/agents/verification-gate.agentother10.7 KB
assets/agents/voice-knowledge-grounded.agentother8.2 KB
assets/agents/voice-service-agent.agentother4.6 KB
assets/bundle-meta.xmlconfig808 B
assets/invocable-apex-template.clsother6.9 KB
assets/patterns/README.mdmarkdown10.8 KB
assets/patterns/action-callbacks.agentother4.7 KB
assets/patterns/advanced-input-bindings.agentother6.9 KB
assets/patterns/bidirectional-routing.agentother5.6 KB
assets/patterns/critical-input-collection.agentother12.2 KB
assets/patterns/delegation-routing.agentother6.4 KB
assets/patterns/lifecycle-events.agentother4.7 KB
assets/patterns/llm-controlled-actions.agentother5.1 KB
assets/patterns/multi-step-workflow.agentother10.1 KB
assets/patterns/open-gate-routing.agentother11.6 KB
assets/patterns/procedural-instructions.agentother4.8 KB
assets/patterns/prompt-template-action.agentother6.6 KB
assets/patterns/system-instruction-overrides.agentother10.6 KB
references/action-prompt-templates.mdmarkdown5.7 KB
references/actions-reference.mdmarkdown30.2 KB
references/agent-access-guide.mdmarkdown2.9 KB
references/agent-audit-and-repair.mdmarkdown7.9 KB
references/agent-audit-candidate-verification.mdmarkdown5.2 KB
references/agent-audit-diagnostic-catalog.mdmarkdown7.6 KB
references/agent-audit-diagnostics-actions-state.mdmarkdown6.9 KB
references/agent-audit-diagnostics-architecture-evaluation.mdmarkdown2.5 KB
references/agent-audit-diagnostics-instructions-routing.mdmarkdown11.8 KB
references/agent-audit-evaluation-loop.mdmarkdown6.0 KB
references/agent-audit-repair-report.mdmarkdown6.9 KB
references/agent-audit-scope-path-review.mdmarkdown8.5 KB
references/agent-design-and-spec-creation.mdmarkdown54.5 KB
references/agent-metadata-and-lifecycle.mdmarkdown30.2 KB
references/agent-script-core-language.mdmarkdown49.3 KB
references/agent-subagent-map-diagrams.mdmarkdown10.8 KB
references/agent-user-setup.mdmarkdown27.8 KB
references/agent-validation-and-debugging.mdmarkdown44.6 KB
references/agentscript-toolchain.mdmarkdown4.6 KB
references/architecture-patterns.mdmarkdown13.5 KB
references/common-control-flow-pitfalls.mdmarkdown9.4 KB
references/complex-data-types.mdmarkdown3.9 KB
references/control-flow-actions-sequencing.mdmarkdown6.9 KB
references/control-flow-lifecycle-side-effects.mdmarkdown3.3 KB
references/data-library-reference.mdmarkdown40.8 KB
references/deploy-reference.mdmarkdown6.7 KB
references/discover-reference.mdmarkdown4.3 KB
references/examples.mdmarkdown12.6 KB
references/feature-validity.mdmarkdown2.1 KB
references/instruction-resolution.mdmarkdown23.4 KB
references/known-issues.mdmarkdown27.6 KB
references/legacy-nga-regression-eval.mdmarkdown30.2 KB
references/mcp-management-reference.mdmarkdown37.6 KB
references/optimization-pattern-1-data-flow.mdmarkdown4.6 KB
references/optimization-pattern-2-deterministic-logic.mdmarkdown5.4 KB
references/optimization-pattern-3-reference-syntax.mdmarkdown4.1 KB
references/optimization-pattern-4-escalation.mdmarkdown2.2 KB
references/org-setup-for-adl.mdmarkdown23.7 KB
references/patterns-by-requirement.mdmarkdown5.4 KB
references/posture-and-determinism.mdmarkdown9.3 KB
references/production-gotchas.mdmarkdown12.6 KB
references/reference-map.mdmarkdown5.3 KB
references/safety-review-reference.mdmarkdown6.3 KB
references/salesforce-cli-for-agents.mdmarkdown16.7 KB
references/scaffold-reference.mdmarkdown6.7 KB
references/scoring-rubric.mdmarkdown3.3 KB
references/upgrade-legacy-agent-to-agentscript.mdmarkdown26.2 KB
references/version-history.mdmarkdown4.4 KB
references/voice-latency-heuristics.mdmarkdown9.7 KB
references/voice-modality-reference.mdmarkdown19.0 KB
references/voice-telephony-cli.mdmarkdown10.3 KB
references/zen-of-agentscript.mdmarkdown13.1 KB
scripts/__init__.pyscript0 B
scripts/agentscript-sdk-loader.mjsscript4.0 KB
scripts/discover.pyexecutablescript20.2 KB
scripts/generators/__init__.pyscript0 B
scripts/generators/apex_stub.pyscript13.4 KB
scripts/generators/apex_test_stub.pyscript3.8 KB
scripts/generators/flow_xml.pyscript7.6 KB
scripts/generators/permission_set_xml.pyscript1014 B
scripts/generators/remote_site_xml.pyscript1.4 KB
scripts/index-agent.mjsexecutablescript3.8 KB
scripts/org_describe.pyexecutablescript5.8 KB
scripts/scaffold.pyexecutablescript15.1 KB
scripts/setup-agentscript-sdk.mjsexecutablescript9.7 KB
scripts/upgrade-legacy-nga-analyze.pyexecutablescript20.0 KB
scripts/upgrade-legacy-nga-run-trials.shexecutablescript3.4 KB

references/patterns-by-requirement.md

View on GitHub
# Patterns by Requirement

Use this guide to choose patterns based on product requirements, not topology labels.

Default shape:

- One `start_agent <domain>:` execution block and zero `subagent` blocks unless
  a boundary changes objective, instructions, actions, authority, or escalation
  behavior and cannot remain coherent in the current scope
- Router-first architecture only when multiple genuine domains require
  current-intent classification
- Subagent-specific posture (scripted, mixed, agentic)
- Deterministic controls only where justified

Read this file first when deciding architecture and flow patterns. Then use:

- `references/architecture-patterns.md` for architecture mechanics and migration guidance
- `assets/patterns/` for concrete pattern snippets

## Quick Selection Table

| Requirement / Scenario | Recommended Pattern | Why | Reference Assets |
|---|---|---|---|
| Multiple genuine domains need different instructions, actions, authority, or escalation | Router-first architecture; consider HyperClassifier for a transition-only router when latency matters | Separates incompatible domain scopes and classifies current intent without turning a conversational node into a router | `references/architecture-patterns.md`, `assets/agents/router-first.agent`, `assets/agents/template-multi-subagent.agent` |
| Identity/trust gate before protected operations | Verification gate | Enforces trusted action output before sensitive actions; does not require a generic focus lock | `references/architecture-patterns.md` |
| Need deterministic follow-up after action | Action callbacks (`run`) | Guarantees ordered post-action execution | `assets/patterns/action-callbacks.agent` |
| Need deterministic setup/cleanup around a turn | Lifecycle events | Runs once before and once after the turn's reasoning loop | `assets/patterns/lifecycle-events.agent` |
| Need specialist consultation and return | Bidirectional routing/delegation | Keeps workflow continuity across subagents | `assets/patterns/bidirectional-routing.agent`, `assets/patterns/delegation-routing.agent` |
| Complex action input strategy required | Advanced input bindings | Mixes slot filling, variable binding, output chaining | `assets/patterns/advanced-input-bindings.agent`, `assets/patterns/critical-input-collection.agent` |
| Controlled output changes the prompt | Context-aware instruction layering | Resolves a branch from trusted action output or a named invariant | `assets/patterns/system-instruction-overrides.agent`, `assets/patterns/procedural-instructions.agent` |
| External process requires ordered successful actions | Outcome-driven gates | Makes the next action available only after the prior external action succeeds | `references/architecture-patterns.md`, `assets/patterns/multi-step-workflow.agent` |
| Prefer LLM-led flexibility with minimal pinning | LLM-controlled actions | Keeps implementation agentic by default | `assets/patterns/llm-controlled-actions.agent` |
| Prompt-template-backed action usage | Prompt template action pattern | Standardized prompt action wiring | `assets/patterns/prompt-template-action.agent` |

## Decision Rules

1. **Choose posture first (per subagent).**
   - Start agentic.
   - Move scripted only when required by regulation, authorization, confirmed
     consequence, external ordering, or observed failure.
   - See `references/posture-and-determinism.md`.

2. **Choose architecture second.**
   - Start with one domain `start_agent` and zero `subagent` blocks.
   - Never add a router that only transitions to that one domain.
   - Add a router only for multiple genuine domains.
   - Use HyperClassifier only when that router can remain transition-only; keep
     an ordinary model when the entry node must converse or run other actions.
   - Add verification gates for protected operations.
   - Add workflow-local sequencing only for externally ordered outcomes.

3. **Choose implementation patterns third.**
   - Add lifecycle/callback/input-binding patterns to solve concrete behavior gaps.
   - Prefer the smallest pattern that satisfies the requirement.

## Common Compositions

### Multi-Domain Protected Service

- Router-first architecture
- Verification gate for protected actions
- Input pinning only for trusted values consumed by protected actions

### Regulated Flow

- One subagent unless the regulated work contains genuine additional domains
- Verification gate
- Scripted controls only for regulated decisions
- Action callbacks for deterministic post-action chain

### Open-Ended Assistant

- One agentic subagent unless genuine domain boundaries require more
- Minimal deterministic controls
- LLM-controlled actions and selective input pinning

## Anti-Patterns

- Modeling the entire agent as linear when only one workflow needs sequencing
- Creating a separate router subagent instead of using `start_agent agent_router`
- Creating greeting, cancellation, completion, off-topic, or ambiguity
  subagents when one existing scope can handle those branches coherently
- Routing every turn back to router by default instead of using direct subagent transitions when workflow intent is clear
- Overusing deterministic controls without requirement or observed failure
- Pinning all action inputs by default instead of using `...` where safe
- Persisting names, preferences, questions asked, or dialogue stages that
  surviving conversation history already contains
- Adding a variable without a trusted writer, named consumer, and lifecycle
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall