Sf Ai Agentforce Testing

Skill Verified Active

Agentforce agent testing with dual-track workflow and 100-point scoring. TRIGGER when: user tests Agentforce agents, runs sf agent test commands, creates test specs, validates topic routing, or analyzes agent test coverage. DO NOT TRIGGER when: Apex unit tests (use sf-testing), building agents (use sf-ai-agentforce), or Agent Script DSL (use sf-ai-agentscript).

Purpose

To enable thorough and automated testing of Agentforce agents, ensuring quality and reliability through detailed coverage analysis and agentic fix loops.

Features

Dual-track testing workflow (CLI & API)
Test execution and coverage analysis
Agentic fix loops for automated issue resolution
Multi-turn conversation testing via Agent Runtime API
Comprehensive test scenario templates

Use Cases

Validating topic routing and action invocation
Analyzing agent test coverage and identifying gaps
Automating agent regression tests
Testing multi-turn conversation flows and context preservation
Implementing agentic fix loops for continuous improvement

Non-Goals

Building or editing Agentforce agents (delegate to sf-ai-agentforce)
Running Apex unit tests (delegate to sf-testing)
Testing Agent Script DSL directly (use sf-ai-agentscript)
Directly managing ECA or org credentials outside the skill's context

Installation

npx skills add jaganpro/sf-skills

Runs the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.

Quality Score

Verified

99 /100

Analyzed 1 day ago

Trust Signals

Last commit17 days ago

GitHub owner jaganpro

Stars409

LicenseMIT

Status

View Source

Similar Extensions

Telegram Crabbox E2e Proof

100

Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.

Skill

steipete

Agent Browser

100

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Skill

shanraisshan

Project Session Manager

100

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions

Skill

Yeachan-Heo

Oh My Claudecode

100

Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly

Skill

Yeachan-Heo

Github

100

Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.

Skill

steipete

Openclaw Testing

100

Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.

Skill

steipete