SalesforceAIResearch

13 mods across 5 repositories, 1.5k stars between them.

MCPEval CLAUDE.md

01

SalesforceAIResearch/MCPEval

Instructions file

Instructions for SalesforceAIResearch/MCPEval, covering mcpeval development guide, llm inference via sfrgateway, starting the gateway, model config files and environment variables for cli.

155 3mo ago A 2,310 tokens original Apache-2.0

SalesforceAIResearch/agentforce-adlc

Instructions file

Claude Code instructions for SalesforceAIResearch/agentforce-adlc, covering agentforce adlc — agent development life cycle, project structure, skills, backward compatibility aliases and important: agent creation routing.

102 1mo ago A 2,892 tokens

PreToolUse

09

SalesforceAIResearch/agentforce-adlc

Hook

Runs before the agent uses a tool for Bash tool calls, executing guardrails.py via python3. From SalesforceAIResearch/agentforce-adlc.

102 1mo ago A tokens not measured

PostToolUse

10

SalesforceAIResearch/agentforce-adlc

Hook

Runs after a tool call finishes for Write and Edit tool calls, executing agent-validator.py via python3. From SalesforceAIResearch/agentforce-adlc.

102 1mo ago A tokens not measured

agentforce-generate

11

SalesforceAIResearch/agentforce-adlc

Skill Claude CodeCodex

Build, modify, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates, modifies, optimizes, or asks about .agent files or aiAuthoringBundle metadata; changes agent behavior, responses, or conversation logic; designs agent actions, tools, subagents, or flow control; writes or…

102 1mo ago A 186 tokens

agentforce-observe

12

SalesforceAIResearch/agentforce-adlc

Skill Claude CodeCodex

Analyze production Agentforce agent behavior using session traces and Data Cloud. TRIGGER when: user queries STDM session data or Data Cloud trace records; investigates production agent failures, regressions, or performance issues; asks about session traces, conversation logs, or agent metrics; wants to reproduce a…

102 1mo ago C 128 tokens

agentforce-test

13

SalesforceAIResearch/agentforce-adlc

Skill Claude CodeCodex

Write, run, and analyze structured test suites for Agentforce agents — functional AND security. TRIGGER when: user writes or modifies test spec YAML (AiEvaluationDefinition); runs sf agent test create, run, run-eval, or results commands; asks about test coverage strategy, metric selection, or custom evaluations…

102 1mo ago B 202 tokens