aiskillstore/marketplace / skills/2389-research/scenario-testing
scenario-testing
VerifiedThis skill should be used when writing tests, validating features, or needing to verify code works. Triggers on "write tests", "add test coverage", "validate feature", "integration test", "end-to-end", "e2e test", "mock", "unit test". Enforces scenario-driven testing with real dependencies in .scratch/ directory.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.2 KB |
| skill-report.json | config | 19.0 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-04T17:19:29.428Z",
"slug": "2389-research-scenario-testing",
"source_url": "https://github.com/2389-research/claude-plugins/tree/main/scenario-testing/skills",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "34e5e44b31de86d7f4a4e7d1f305fb78ba9850d8317016cc2f2aacfdf499cd4a",
"tree_hash": "ae95732f8266a3fd3d5d071f3756c4dbbbd2f697a3261198671513df6c708aa5",
"provenance": {
"model_requested": "gpt-5.5:high",
"model_effective": "codex:gpt-5.5:high",
"fallback_chain": [
{
"agent": "codex",
"model": "gpt-5.5",
"effort": "high",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "scenario-testing",
"description": "Guides AI coding agents to validate features with scenario-driven tests that exercise real dependencies and document repeatable coverage.",
"summary": "Validate code changes with scenario tests, real dependencies, and repeatable scenario records.",
"icon": "π¦",
"version": "1.0.0",
"author": "2389-research",
"license": "MIT",
"tags": [
"scenario-testing",
"integration-tests",
"e2e-testing",
"test-validation",
"real-dependencies"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands"
],
"category": "coding"
},
"security_audit": {
"risk_level": "medium",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "All static analyzer matches for Ruby or shell backtick execution are false positives caused by Markdown inline-code formatting. The system reconnaissance matches are also false positives, but the skill does have a medium contextual risk because it encourages real credential requests and real service execution without clear safeguards.",
"remediation": [
{
"issue": "Credential handling guidance",
"suggestion": "Tell users to use sandbox credentials, avoid sharing secrets in chat, and rely on approved secret managers or local environment variables.",
"severity": "medium"
},
{
"issue": "Real service execution",
"suggestion": "Require explicit user approval before hitting external services, databases, or APIs, and mention cost and data exposure risks.",
"severity": "medium"
},
{
"issue": "Absolute mock prohibition",
"suggestion": "Allow safe fakes when real dependencies are unavailable or risky, then require real scenario validation before release.",
"severity": "low"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 32,
"line_end": 32
},
{
"file": "SKILL.md",
"line_start": 37,
"line_end": 37
},
{
"file": "SKILL.md",
"line_start": 39,
"line_end": 39
},
{
"file": "SKILL.md",
"line_start": 78,
"line_end": 78
},
{
"file": "SKILL.md",
"line_start": 80,
"line_end": 80
},
{
"file": "SKILL.md",
"line_start": 81,
"line_end": 81
},
{
"file": "SKILL.md",
"line_start": 85,
"line_end": 85
},
{
"file": "SKILL.md",
"line_start": 88,
"line_end": 88
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 32,
"line_end": 32,
"snippet": "### 1. Write Scenarios in `.scratch/`"
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 37,
"line_end": 37,
"snippet": "- Must be in `.gitignore` (never commit)"
},
{
"id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 39,
"line_end": 39,
"snippet": "### 2. Promote Patterns to `scenarios.jsonl`"
},
{
"id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 78,
"line_end": 78,
"snippet": "1. β
A scenario in `.scratch/` passes with zero mocks"
},
{
"id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 80,
"line_end": 80,
"snippet": "3. β
`.scratch/` remains in `.gitignore`"
},
{
"id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 81,
"line_end": 81,
"snippet": "4. β
Robust patterns extracted to `scenarios.jsonl`"
},
{
"id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 85,
"line_end": 85,
"snippet": "1. **Write scenario** - Create `.scratch/test-user-registration.py`"
},
{
"id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 88,
"line_end": 88,
"snippet": "4. **Extract pattern** - Document in `scenarios.jsonl`"
},
{
"id": "blocker:SKILL.md:57:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 57,
"line_end": 59,
"snippet": "## What Makes a Scenario Invalid"
},
{
"id": "blocker:SKILL.md:59:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 59,
"line_end": 59,
"snippet": "A scenario is invalid if it:"
},
{
"id": "blocker:SKILL.md:65:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 65,
"line_end": 67,
"snippet": "## Common Violations to Avoid"
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The detected backticks are Markdown inline code around .scratch/, not Ruby or shell execution. No command invocation or interpolated input appears on this line."
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format .gitignore as inline Markdown code. The line describes repository hygiene and does not execute commands."
},
{
"id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format scenarios.jsonl as inline Markdown code. This is documentation text and has no shell or Ruby execution semantics."
},
{
"id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks mark .scratch/ as inline Markdown code inside a checklist. The line does not run a command or evaluate dynamic input."
},
{
"id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The line uses Markdown backticks to reference .scratch/ and .gitignore. It is a documentation checklist item, not executable code."
},
{
"id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks only format scenarios.jsonl as a filename. There is no command execution pattern or user-controlled command string."
},
{
"id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format an example file path in prose. Creating a test file is described conceptually and no shell execution is present."
},
{
"id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format scenarios.jsonl as a documentation target. The line does not contain executable syntax."
},
{
"id": "blocker:SKILL.md:57:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The heading introduces invalid test-scenario criteria. It does not instruct the agent to inspect system state or enumerate host information."
},
{
"id": "blocker:SKILL.md:59:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The line starts a list of testing anti-patterns. It contains no reconnaissance behavior, command, or request for system details."
},
{
"id": "blocker:SKILL.md:65:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The heading introduces common testing violations to avoid. It is not asking the model to probe the environment or collect system information."
}
],
"semantic_findings": [
{
"title": "Encourages Real Credential Requests",
"description": "The skill requires external APIs to hit actual services and says to ask a human partner for real API credentials. This guidance can pressure users to disclose credentials and run costly or sensitive external operations without explicit safeguards.",
"severity": "medium",
"locations": [
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 48
},
{
"file": "SKILL.md",
"line_start": 72,
"line_end": 72
}
],
"confidence": 0.82,
"confidence_reasoning": "The cited lines explicitly require real services and direct users to request real credentials. The risk is contextual because sandbox mode is mentioned, but clear secret handling and approval guardrails are missing."
}
],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Encourages Real Credential Requests",
"description": "The skill requires external APIs to hit actual services and says to ask a human partner for real API credentials. This guidance can pressure users to disclose credentials and run costly or sensitive external operations without explicit safeguards.",
"locations": [
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 48
},
{
"file": "SKILL.md",
"line_start": 72,
"line_end": 72
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.82,
"confidence_reasoning": "The cited lines explicitly require real services and direct users to request real credentials. The risk is contextual because sandbox mode is mentioned, but clear secret handling and approval guardrails are missing."
}
],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 1,
"total_lines": 98,
"audit_model": "codex",
"audited_at": "2026-07-04T17:19:29.428Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Validate Features with Scenario Tests",
"value_statement": "Feature work can pass shallow tests while failing against real systems. This skill guides Claude, Codex, and Claude Code to prove behavior with scenario tests and documented real-dependency checks.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"scenario testing",
"integration testing",
"end-to-end testing",
"test coverage",
"real dependencies",
"scenarios.jsonl",
"AI coding tests"
],
"actual_capabilities": [
"Directs agents to create scenario tests in a .scratch/ workspace.",
"Requires tests to exercise real systems and real dependencies.",
"Defines when a scenario is invalid because it uses mocks or fake data.",
"Promotes repeatable scenario patterns into a committed scenarios.jsonl file.",
"Sets a definition of done for scenario validation before completion."
],
"limitations": [
"Does not provide executable test runner code or framework adapters.",
"May require sandbox services, test databases, or approved credentials.",
"Real dependency testing can increase runtime, cost, and setup effort.",
"The .scratch/ scenarios are intended to stay uncommitted."
],
"use_cases": [
{
"title": "Validate Backend Feature Behavior",
"description": "Create a real dependency scenario before marking a new API, workflow, or database-backed change as complete.",
"target_user": "Backend engineer"
},
{
"title": "Turn Bug Fixes into Repeatable Coverage",
"description": "Reproduce a reported failure, verify the fix with a scenario, and document the pattern for future regression checks.",
"target_user": "QA engineer"
},
{
"title": "Guide AI Agents During Delivery",
"description": "Keep Claude, Codex, or Claude Code focused on proving working behavior instead of stopping at isolated unit tests.",
"target_user": "AI coding assistant operator"
}
],
"prompt_templates": [
{
"title": "Create a First Scenario",
"scenario": "Beginner validation for a new feature",
"prompt": "Use scenario-testing to design a .scratch/ scenario for this feature. Include the real dependencies it must exercise and the pass condition."
},
{
"title": "Validate a Bug Fix",
"scenario": "Intermediate regression coverage",
"prompt": "Use scenario-testing to reproduce this bug with real dependencies, verify the fix, and list what makes the scenario independent."
},
{
"title": "Promote a Scenario Pattern",
"scenario": "Document repeatable testing knowledge",
"prompt": "Use scenario-testing to extract the validated scenario into a scenarios.jsonl entry with name, given, when, then, and validates fields."
},
{
"title": "Audit Release Readiness",
"scenario": "Advanced delivery review",
"prompt": "Use scenario-testing to review this change set for missing real-dependency scenarios, invalid mock usage, and unresolved validation gaps."
}
],
"output_examples": [
{
"input": "Validate a user registration workflow before release.",
"output": "A .scratch/ scenario plan that uses the real database, real auth service in test mode, expected success criteria, and cleanup notes."
},
{
"input": "Convert a recurring checkout validation into shared coverage.",
"output": "A documented scenario pattern with a clear given, when, then flow and a list of business behavior it validates."
},
{
"input": "Review a completed bug fix for missing validation.",
"output": "A gap report that names missing real-dependency checks, invalid mocks, and the scenario needed before declaring the fix complete."
}
],
"best_practices": [
"Use sandbox or test-mode services when real external systems are required.",
"Keep each scenario independent so it can run alone and in parallel.",
"Move stable lessons from scratch scenarios into committed scenario documentation."
],
"anti_patterns": [
"Treating mocked unit tests as proof that a feature works end to end.",
"Running scenarios that depend on hidden state from earlier test executions.",
"Requesting or exposing production secrets instead of approved test credentials."
],
"faq": [
{
"question": "Does this skill write test code for me?",
"answer": "It gives process guidance and scenario structure. The agent still adapts implementation details to your project and test framework."
},
{
"question": "Can I use mocks with this skill?",
"answer": "The skill rejects mocks as final validation. Use real dependencies or approved sandbox equivalents for completion evidence."
},
{
"question": "What is .scratch/ used for?",
"answer": ".scratch/ is a temporary workspace for scenario experiments. The skill expects it to remain ignored by version control."
},
{
"question": "What should go into scenarios.jsonl?",
"answer": "Put repeatable scenario patterns there after they prove useful. Include the behavior, setup, action, expected result, and validation purpose."
},
{
"question": "Does this require production services?",
"answer": "No. Use sandbox, test-mode, or staging services when possible, and get explicit approval before touching real external systems."
},
{
"question": "Which tools can use this skill?",
"answer": "The report lists compatibility with Claude, Codex, and Claude Code."
}
]
},
"file_structure": [
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 98
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |