forcedotcom/sf-skills / plugins/builder/agentforce-adlc/skills/agentforce-generate
agentforce-generate
FlaggedBuild, 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.
README.md
View on GitHub# Agentforce Development Skill
A skill for developing Agentforce agents with Agent Script.
## What This Skill Covers
The skill routes agent work across the full lifecycle:
| Domain | What It Handles |
|--------|----------------|
| Create an Agent | Agent Spec design, environment checks, bundle generation, draft authoring |
| Modify an Agent | Subagent/action changes, instruction refinement, flow updates |
| Audit and Repair | Health checks, common-pitfall review, minimal evidence-backed repairs |
| Diagnose Compilation Errors | Error capture, classification, targeted fixes |
| Diagnose Behavioral Issues | Trace-based debugging, routing/action analysis |
| Deploy / Release | Draft iteration, deploy, explicit publish + activate |
| Test an Agent | Coverage design, spec creation, run analysis |
| Migrate a Legacy Agent | `GenAiPlannerBundle` → `AiAuthoringBundle` (Agent Script) conversion, then optimize |
## Skill Structure
```text
agentforce-generate/
├── SKILL.md # Execution router and hard rules
├── references/ # Domain guidance and adjacent operational docs
│ ├── patterns-by-requirement.md
│ ├── posture-and-determinism.md
│ ├── agent-design-and-spec-creation.md
│ ├── architecture-patterns.md
│ ├── agent-script-core-language.md
│ ├── agent-audit-and-repair.md
│ ├── salesforce-cli-for-agents.md
│ ├── agent-validation-and-debugging.md
│ ├── deploy-reference.md
│ ├── agent-metadata-and-lifecycle.md
│ ├── data-library-reference.md
│ ├── ... (additional references)
├── assets/ # Templates, examples, and reusable snippets
│ ├── agent-spec-template.md
│ ├── bundle-meta.xml
│ ├── invocable-apex-template.cls
│ ├── agents/ # Complete agent templates (including router-first)
│ └── patterns/ # Reusable implementation patterns
```
## How It Works
`SKILL.md` acts as the router. It maps user intent to task domains and required references, then enforces hard rules for safe execution.
Core rules include:
1. **Always `--json`** on every `sf` CLI command
2. **Use proportionate evidence** — compile local syntax changes; use preview and traces for behavior; use live actions only with approval in a safe org
3. **Use a proportionate spec gate** — require approval for greenfield and material design changes, not every one-line repair
4. **Draft-first lifecycle** — iterate in draft by default; publish/activate only with explicit user confirmation
## Prerequisites
- Salesforce org with Agentforce license
- API version 66.0+ (Spring '26)
- Einstein Agent User (for service agents)
- Salesforce CLI v2.x (`sf` command)
- Claude Code (or compatible AI coding agent)
## Installation
Copy the `agentforce-generate` folder into your project's `.claude/skills/` directory:
```text
your-project/
└── .claude/
└── skills/
└── agentforce-generate/
├── SKILL.md
├── references/
└── assets/
```
Restart Claude Code after installation.
The skill can install its local AgentScript compiler on first use. It uses a
skill-owned user cache and does not add dependencies to the customer's project:
```bash
node .claude/skills/agentforce-generate/scripts/setup-agentscript-sdk.mjs \
--npm --json
```
Claude should run this automatically for every existing `.agent` file before
org-side validation. If npm setup fails, the skill can build the public
`salesforce/agentscript` source checkout. If neither provider works, the skill
continues with target-org validation or a clearly labeled static review and
states that the compiler was not used.
## Key References
- Pattern selection: [references/patterns-by-requirement.md](references/patterns-by-requirement.md)
- Posture guidance: [references/posture-and-determinism.md](references/posture-and-determinism.md)
- Design/spec workflow: [references/agent-design-and-spec-creation.md](references/agent-design-and-spec-creation.md)
- Architecture mechanics: [references/architecture-patterns.md](references/architecture-patterns.md)
- Core language: [references/agent-script-core-language.md](references/agent-script-core-language.md)
- Audit and repair: [references/agent-audit-and-repair.md](references/agent-audit-and-repair.md)
- Validation/debugging: [references/agent-validation-and-debugging.md](references/agent-validation-and-debugging.md)
- Reference index and consolidation notes: [references/reference-map.md](references/reference-map.md)
## Version
Current version: **0.11**. See [references/version-history.md](references/version-history.md) for the full changelog.
## Credits
This skill integrates knowledge from the following sources:
**Jag Valaiyapathy** ([sf-skills](https://github.com/Jaganpro/sf-skills), MIT License)
— Known issues catalog, production gotchas, agent access and permissions guide, and deployment patterns. Integrated starting in v0.4.2.
**Hua Xu** (Salesforce APAC FDE team)
— Open-gate routing pattern from Kogan agent deployment.
**Salesforce DevRel** ([agent-script-recipes](https://github.com/trailheadapps/agent-script-recipes))
— Canonical Agent Script examples used as grounding material.
**Dylan Zeigler, AI Platform** (llm-utils)
— Agent Script playground used as reference source.
## License
Apache-2.0
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |