Skip to content

aiskillstore/marketplace / skills/a-genno/test-ops

test-ops

Verified

テスト計画・実行・報告を標準化する運用スキル。

FileKindSize
SKILL.mdskill md1.7 KB
skill-report.jsonconfig8.2 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-07T19:20:08.804Z",
    "slug": "a-genno-test-ops",
    "source_url": "https://github.com/A-Genno/Polaris/tree/master/documents/skills/test-ops",
    "source_ref": "master",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "62fe09192fea817fa321b245ed9cac148e97af2a42e907f66c4f7e8789d57e7b",
    "tree_hash": "2b64a6d611924192d797f4cecec97620021cf1e5d1ce7c9658d66f317c1ba265",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "test-ops",
    "description": "Standardizes test planning, implementation, execution, and reporting for software quality work.",
    "summary": "Guides structured test operations from design through coverage review.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "A-Genno",
    "license": "MIT",
    "category": "devops",
    "tags": [
      "testing",
      "quality-assurance",
      "test-planning",
      "test-automation"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": []
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "The only static finding is a high-entropy heuristic on SKILL.md. Manual review shows readable Japanese Markdown with testing guidance, so the finding is a false positive.",
    "remediation": [],
    "risk_factor_evidence": [],
    "static_findings": [
      {
        "id": "obfuscation:SKILL.md:1:heuristic-high-file-entropy-6-69-bits-possible-b",
        "category": "obfuscation",
        "severity": "high",
        "pattern": "[HEURISTIC] High file entropy (6.69 bits) - possible binary/encrypted content",
        "file": "SKILL.md",
        "line_start": 1,
        "line_end": 1,
        "snippet": "File: SKILL.md"
      }
    ],
    "finding_verdicts": [
      {
        "id": "obfuscation:SKILL.md:1:heuristic-high-file-entropy-6-69-bits-possible-b",
        "verdict": "false_positive",
        "confidence": 0.9,
        "reason": "SKILL.md is plain Japanese Markdown with front matter and test process guidance. No binary, encrypted, or obfuscated content was found."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 32,
    "audit_model": "codex",
    "audited_at": "2026-07-07T19:20:08.804Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Standardize Test Operations",
    "value_statement": "Testing work often becomes inconsistent across planning, execution, and reporting. This skill helps Claude, Codex, and Claude Code guide structured test operations.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "test operations",
      "test planning",
      "quality assurance",
      "test automation",
      "mocking strategy",
      "coverage review",
      "software testing"
    ],
    "actual_capabilities": [
      "Outlines test design for normal, error, boundary, and edge cases.",
      "Recommends independent tests that can run without cross-test dependencies.",
      "Defines mocking guidance for databases, APIs, time-dependent code, and file I/O.",
      "Provides implementation steps from feature analysis through coverage review.",
      "Specifies test quality standards for structure, names, assertions, and error messages."
    ],
    "limitations": [
      "Does not include runnable test scripts or framework-specific commands.",
      "Does not inspect project code without user-provided context.",
      "Coverage goals still require engineering judgment.",
      "Provides general testing guidance, not a complete QA governance process."
    ],
    "use_cases": [
      {
        "title": "Plan Feature Test Coverage",
        "description": "Create a clear test plan that covers normal, error, boundary, and edge cases.",
        "target_user": "Application developers"
      },
      {
        "title": "Review Mocking Strategy",
        "description": "Decide how to isolate databases, APIs, clocks, timers, and file access during tests.",
        "target_user": "QA engineers"
      },
      {
        "title": "Standardize Test Reports",
        "description": "Align test implementation and results reporting around consistent quality criteria.",
        "target_user": "Engineering leads"
      }
    ],
    "prompt_templates": [
      {
        "title": "Create a Basic Test Plan",
        "scenario": "Beginner planning for a new feature",
        "prompt": "Use the test-ops skill to create a test plan for this feature. Include normal, error, boundary, and edge cases."
      },
      {
        "title": "Design Isolated Tests",
        "scenario": "Intermediate test implementation",
        "prompt": "Use the test-ops skill to design independent tests for this component. Identify needed mocks and fixtures."
      },
      {
        "title": "Audit Test Quality",
        "scenario": "Reviewing an existing test suite",
        "prompt": "Use the test-ops skill to review these tests for independence, readability, assertions, and failure messages."
      },
      {
        "title": "Build a Coverage Improvement Plan",
        "scenario": "Advanced quality improvement",
        "prompt": "Use the test-ops skill to find coverage gaps and propose a prioritized plan to improve test completeness."
      }
    ],
    "output_examples": [
      {
        "input": "Plan tests for a payment retry feature.",
        "output": "A structured plan covering successful retries, declined payments, timeout handling, retry limits, duplicate prevention, and reporting expectations."
      },
      {
        "input": "Review how to mock external services in tests.",
        "output": "Guidance to mock HTTP clients, use stable response patterns, isolate database access, and fix time-dependent behavior."
      },
      {
        "input": "Improve the quality of an existing test suite.",
        "output": "A review checklist for AAA structure, readable names, clear assertions, independent execution, and useful failure messages."
      }
    ],
    "best_practices": [
      "Provide the feature behavior, expected risks, and current test framework before asking for a plan.",
      "Ask for separate normal, error, boundary, and edge cases to avoid missing important scenarios.",
      "Review proposed mocks against real system boundaries before implementing tests."
    ],
    "anti_patterns": [
      "Do not ask for full coverage without explaining the feature or business risk.",
      "Do not treat generated test plans as a substitute for running the actual test suite.",
      "Do not mock behavior that should be verified through integration tests."
    ],
    "faq": [
      {
        "question": "What does this skill help with?",
        "answer": "It helps structure test planning, implementation, execution checks, and reporting standards."
      },
      {
        "question": "Does it generate runnable test code?",
        "answer": "It provides testing strategy and implementation guidance. Runnable code depends on the project and framework context."
      },
      {
        "question": "Can it help with mocks?",
        "answer": "Yes. It gives guidance for databases, external APIs, clocks, timers, and file system access."
      },
      {
        "question": "Which tools can use this skill?",
        "answer": "The report lists support for Claude, Codex, and Claude Code."
      },
      {
        "question": "Is this skill specific to one programming language?",
        "answer": "No. The guidance is general and can be adapted to different test frameworks."
      },
      {
        "question": "What should I provide for best results?",
        "answer": "Provide feature requirements, known risks, existing tests, target framework, and coverage goals."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 32
    }
  ]
}
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall