Agent-Skills.md

Agent Skills: User Flow Validator

Test user journey assertions against real surfaces (Web UI, CLI, API) with evidence collection and isolation boundaries

UncategorizedID: oimiragieo/agent-studio/user-flow-validator

Repository

oimiragieo/agent-studio
oimiragieo
19

Install this agent skill to your local

pnpm dlx add-skill https://github.com/oimiragieo/agent-studio/tree/HEAD/.claude/skills/user-flow-validator

Skill Files

Browse the full folder contents for user-flow-validator.

Download Skill

Loading file tree…

.claude/skills/user-flow-validator/SKILL.md

Skill Metadata

Name
user-flow-validator
Description
Test user journey assertions against real surfaces (Web UI, CLI, API) with evidence collection and isolation boundaries

User Flow Validator

<identity> User Flow Validator Skill - Test user journey assertions against real surfaces (Web UI, CLI, API) with evidence collection and isolation boundaries </identity> <capabilities> - User Flow Validator primary function - Integration with agent ecosystem - Standardized output generation </capabilities> <instructions> <execution_process>

Step 1: Gather Context

Read relevant files and understand requirements

Step 2: Execute

Perform the skill's main function using available tools

Step 3: Output

Return results and save artifacts if applicable

</execution_process>

<best_practices>

  1. Follow existing project patterns: Follow this practice for best results
  2. Document all outputs clearly: Follow this practice for best results
  3. Handle errors gracefully: Follow this practice for best results

</best_practices> </instructions>

<examples> <usage_example> **Example Commands**: 
# Invoke this skill
/user-flow-validator [arguments]

# Or run the script directly
node .claude/skills/user-flow-validator/scripts/main.cjs --help

</usage_example> </examples>

Search Protocol

For code discovery and search tasks, follow this priority order:

  1. `pnpm search:code "<query>"` (Primary intent-based search).
  2. `ripgrep` (for exact keyword/regex matches).
  3. semantic/structural search via code tools if available.

Memory Protocol (MANDATORY)

Before starting: ```bash cat .claude/context/memory/learnings.md cat .claude/context/memory/decisions.md ```

After completing:

  • New pattern -> `.claude/context/memory/learnings.md`
  • Issue found -> `.claude/context/memory/issues.md`
  • Decision made -> `.claude/context/memory/decisions.md`

ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.