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/optimization-pattern-2-deterministic-logic.md

View on GitHub
# Optimization Pattern 2: Extract Deterministic Logic from Natural Language

## Detection Logic

Scan instruction blocks for logic that may need deterministic enforcement:

1. **Material action ordering**: Instructions saying "first do X" or "do X
   before Y" where regulation, authorization, irreversible consequence, or an
   external protocol requires the order.

2. **Machine-known gates**: Authorization, confirmation, eligibility, and
   trusted action-result conditions that control tool visibility or routing.

3. **Post-action invariants**: Success/failure outcomes that must enable,
   disable, or route later execution.

4. **Exact comparisons in prompt text**: Instructions such as
   `If {!@variables.status} == "blocked"` that expose a runtime value but ask
   the model to perform a machine-known branch.

Do not extract current intent, remembered preferences, question progress, or
other unstructured conversational judgment into mutable state merely because
it can be phrased as “if X.”

## Decision Test

Put on the author's thinking hat; do not rewrite conditions mechanically.

- **Keep model-facing:** “If the user wants to speak with a human…” The model
  must interpret the user's intent from natural language.
- **Make deterministic when material:** “If account status equals blocked…”
  The runtime already knows the exact value and the branch must not drift.
- **Use mixed control when needed:** Let the model identify intent, but gate a
  consequential action with `available when` over trusted state.

Interpolation and determinism are separate decisions. A merge field gives the
model a value; it does not make the model's comparison or sequence reliable.

## How to Fix

Move requirement-backed procedural logic to explicit `if`, `run`, `set`,
`available when`, or `transition` constructs.

Create a mutable variable only when a named later deterministic consumer needs
an action output after `@outputs` leaves scope. Then:
1. Create a new mutable variable with matching type if it doesn't exist
2. Add `set @variables.X = @outputs.Y` to store the output
3. Use `@variables.X` only in that consumer

When the decision is immediate in the producing action's post-action scope, use
`@outputs.X` directly instead of copying it to state.

**Ordering**: Deterministic checks should happen BEFORE natural language instructions, not embedded within them.

### Focused example

```agentscript
# BAD: exact runtime comparison delegated to the model
| If {!@variables.account_status} == "blocked", use account recovery.

# GOOD: runtime owns the exact comparison
if @variables.account_status == "blocked":
    | Help the customer recover access to the blocked account.

# ALSO GOOD: model owns semantic intent
| If the user asks to speak with a human, use
  {!@actions.escalate_to_support}.
```

## Example

**Before:**
```agentscript
subagent hotel_booking:
    reasoning:
        instructions: ->
            | If user is not known, always ask for their username and get their User record before making any booking. Help user check room availability with {!@actions.CheckAvailability}. If room is available, transition to payment.
        actions:
            IdentifyUserByUsername: @actions.identify_user_by_username
                with username = ...
            CheckAvailability: @actions.check_room_availability
                with roomType = ...
                with userRecord = ...
    actions:
        identify_user_by_username:
            description: "Get user tier"
            inputs:
                "username": string
            outputs:
                "userRecord": object
        check_room_availability:
            inputs:
                "roomType": string
                "userRecord": object
            outputs:
                "available": boolean
```

**After:**
```agentscript
variables:
    userRecord: mutable object = None

subagent hotel_booking:
    reasoning:
        instructions: ->
            if @variables.userRecord is None:
                | Ask for the username needed to identify the user, then use
                  {!@actions.IdentifyUserByUsername}.
            else:
                | Help the user check room availability with
                  {!@actions.CheckAvailability}.
        actions:
            IdentifyUserByUsername: @actions.identify_user_by_username
                with username = ...
                set @variables.userRecord = @outputs.userRecord
            CheckAvailability: @actions.check_room_availability
                with roomType = ...
                with userRecord = @variables.userRecord
                available when @variables.userRecord != None
                if @outputs.available == True:
                    transition to @subagent.payment
    actions:
        identify_user_by_username:
            description: "Get user tier"
            inputs:
                "username": string
            outputs:
                "userRecord": object
        check_room_availability:
            inputs:
                "roomType": string
                "userRecord": object
            outputs:
                "available": boolean
```

**Key improvements:**
- Persisted only `userRecord`, because the later availability action requires
  that exact identified record
- Kept username and room type as conversational slot-filled inputs
- Hid availability until identification succeeds
- Used immediate `@outputs.available` instead of duplicating it in a variable
- Kept natural-language instructions focused on the current user-facing task
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