本文へ移動
cccskills
無料GitHub で公開

test-scenario

Generate test outlines (living documentation) and test code from natural language feature descriptions. Supports .NET (xUnit/NUnit/MSTest), Python (pytest), TypeScript (Vitest/Jest). Strict mode: no internal module mocking, real DB, AAA pattern, Design by Contract (DbC). Use when the user asks to generate tests from a feature description, create test cases from requirements, write test outlines, scaffold test files, generate test code from spec, convert TODO tests to real tests, or create tests for a function. Trigger phrases include "test scenario", "テストシナリオ", "generate tests", "テスト生成", "テストケース作成", "write tests for", "scaffold tests", "tests from requirements", "テストアウトライン", "convert todo tests", "implement test outline", "test outline", "test cases from spec".

日本語の概要は準備中です。原文の説明を表示しています。

hideki5123/agent-skill-set

実行スコア 未検証

インストール方法を見る

含まれるファイル（4）

  • SKILL.md7.4 KB
  • references/framework-profiles.md4.9 KB
  • references/implementation-rules.md10.6 KB
  • references/outline-rules.md7.1 KB

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Test Scenario Generator

Generate exhaustive test outlines and executable test code from natural language feature descriptions. The outline serves as "living documentation" — a specification expressed as test case names.

Arguments

ArgumentDefaultDescription
--frameworkauto-detectTest framework override (skips auto-detection)
--langenLanguage for test case names: ja, en
--outline-onlyfalseStop after Phase 2 (produce outline only, skip implementation)
--test-fileautoTarget test file path
--run-cmdauto-detectOverride test runner command

Constraints

  • NEVER write implementation or production code — create and modify test files only
  • Never skip the outline — Phase 2 outline is the "contract" that Phase 3 implements
  • Always ask when specs, data flows, or edge cases are unclear
  • Strict mode only — no internal module mocking, real database, AAA pattern, Design by Contract

Workflow

Phase 1: Understand & Clarify

  1. Parse the user's feature description. Extract:

    • Functional requirements (what the feature does)
    • Constraints (limits, ranges, defaults, permissions)
    • Data flows (input sources, processing, output destinations)
    • UI/API surface (where the feature is exposed)

  2. Detect the project's test framework. Read references/framework-profiles.md for detection logic and syntax mappings.

    • Scan project files to identify the test framework
    • Use --framework override if provided
    • Present detection result to user and confirm

  3. Determine test file location:

    • If --test-file provided, use it
    • Otherwise, infer from the feature description and project conventions
    • If file exists, read it to understand current test coverage

  4. Determine test name language:

    • If --lang provided, use it
    • Otherwise, use en

  5. If anything is unclear, present a numbered question list covering:

    • Input/output contracts
    • Data sources involved (DB tables, APIs, caches)
    • Boundary values and limits
    • Error states to handle
    • Authentication/authorization requirements

    Wait for answers before proceeding. If the user says "use your best judgment", proceed with reasonable assumptions and note them.

Phase 2: Generate Test Outline

Read references/outline-rules.md for the full outline generation rules and per-framework syntax.

  1. Generate a test file with only structure and TODO-marked test cases:

    • Use the detected framework's TODO marker syntax
    • Organize tests hierarchically by context/precondition
    • Each test case name must be self-documenting "living documentation"

  2. Cover all 5 categories:

    • Happy Path — normal expected behavior with valid inputs
    • Edge Cases — boundary conditions, empty/null/zero values, at-limit values
    • Error Handling — invalid inputs, auth failures, service unavailability
    • Constraints — business rules, limits, defaults from the spec
    • Data Integrity — state before/after operations, rollback on failure

  3. Do NOT create test cases that assume mocking of internal modules.

  4. Present the outline to the user in chat. Ask:

    "Does this outline cover all the behaviors you expect? Should I add, remove, or modify any test cases?"

  5. Iterate until the user approves, then write the file.

  6. If --outline-only is set, stop here and report the file path.

Phase 3: Implement Test Code

Read references/implementation-rules.md for the 6 absolute rules with per-framework code examples.

Convert each TODO-marked test case into an executable test following these rules:

  1. Test Data Lifecycle — create data in setup, clean up in teardown, using framework-appropriate hooks
  2. AAA Pattern — visually separate Arrange, Act, Assert with blank lines
  3. No Internal Module Mocking — use real database, Docker-based mock servers for HTTP
  4. Design by Contract — assert return value AND database state; in error cases, assert error AND unchanged state
  5. Readability — each test must be self-explanatory in isolation
  6. Test Utilities — discover and use existing helpers; create new ones if needed

After implementing all tests, run them:

  • Detect or use --run-cmd for the runner command
  • For each failure, classify:
    • Test code bug (wrong assertion, incomplete setup): fix the test and re-run
    • Spec/implementation mismatch (real defect or ambiguous spec): skip the test with a comment explaining the issue, and ask the user

Report results:

"X tests passing, Y tests skipped (awaiting clarification on: [list specific questions])"

Present skipped tests with the specific questions that need answering.

Behavior Scenarios

Scenario: Generate test outline from natural language description
  Given the user provides a feature description in natural language
  When /test-scenario is invoked
  Then detect framework, ask clarifying questions if needed, generate test outline
       covering all 5 categories, present for user approval, and write the file

Scenario: Implement test code from approved outline
  Given an approved test outline exists
  When Phase 3 proceeds
  Then convert all TODO markers to executable tests following the 6 absolute rules,
       run tests, fix test bugs, skip ambiguous cases for user clarification,
       and report results

Scenario: Outline-only mode
  Given the --outline-only flag is set
  When /test-scenario --outline-only is invoked
  Then produce only the test outline and stop after writing the file

Scenario: Ambiguous feature description
  Given a vague or incomplete feature description
  When Phase 1 parses the input
  Then present a numbered list of specific questions and wait for answers
       before generating the outline

Scenario: Update existing test file
  Given a test file already exists at the target path
  When /test-scenario is invoked for the same feature
  Then read existing tests, identify gaps in coverage, and add only missing
       test cases without duplicating existing ones

Integration with Other Skills

SkillHow to use together
tddUse test-scenario to generate the outline (RED state), then the tdd skill's red-green-refactor loop to implement production code (GREEN)
orch-qaUse orch-qa to identify missing test coverage, then feed gap descriptions to test-scenario as input
scenario-genDifferent triggers: scenario-gen works from git diffs (change-driven), test-scenario works from natural language (spec-driven)

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

adversarial-panel

無料

Run a multi-model adversarial mutual review with facilitator synthesis: 2+ panelists (different model families where possible — use codex-server / codex-cli for the external-family seat) independently answer, adversarially critique each other across rounds, and the main session acts as facilitator, synthesizing agreements, live disagreements, and calibrated confidence into one answer. Use ONLY on high-stakes, hard-to-reverse claims, designs or decisions, and only when the user EXPLICITLY asks to debate or adversarially review with multiple models — "discuss with Opus and Codex", "red-team this", "devil's advocate", 敵対的レビュー, 相互レビュー, 多モデル討論, 議論させて. A full run costs ~6 subagent/CLI dispatches: state the panel size and round count and get a go-ahead before launching. Where the Workflow tool is available, run the panel as a Workflow (judge-panel / adversarial-verify) instead of ad-hoc fan-out. Do NOT self-trigger on a bare "are you sure?" — that is a cue to OFFER the panel, not to run it.

日本語の概要は準備中です。原文の説明を表示しています。

hideki5123/agent-skill-set22026年10月21日 更新

agent-swarm

無料

Orchestrate multiple coding-agent sessions (Claude Code, Codex, Gemini) over the mcp_agent_mail MCP server, observe their progress on a recurring auto-loop, and prevent inconsistencies (file/edit conflicts and contradictory decisions) between concurrent tasks. Auto-manages the agent-mail server, derives the shared room key from the git repo, and runs either as the orchestrator/observer or as a participating worker. Handles the operational details (server startup, room key, reservation conventions) so the user does not have to remember them. Use when coordinating several agent sessions on different tasks at once, watching a swarm of sessions for conflicts, or wiring already-running sessions into a shared coordination room. Trigger phrases: "agent-swarm", "/agent-swarm", "orchestrate agents", "orchestrate multiple claude sessions", "coordinate sessions", "watch for conflicts between agents", "observe the swarm", "prevent inconsistency between sessions", "multi-agent observe", "複数セッションを協調", "エージェント協調", "セッション間の不整合監視", "スウォーム監視", "複数のClaudeを束ねて".

日本語の概要は準備中です。原文の説明を表示しています。

hideki5123/agent-skill-set22026年10月21日 更新

agents-init

無料

Generate AGENTS.md (cross-tool agent context — Codex CLI, Aider, Cursor, etc.) and wire CLAUDE.md as a symlink so Claude Code reads the same file. Delegates content generation to Claude's built-in /init when needed, then renames + symlinks. Idempotent. Triggers — /agents-init, "generate agents.md", "create agents.md", "share claude and codex context", "set up agents file", "init agents", "agents-init", "cross-tool agent context", "wire claude and agents".

日本語の概要は準備中です。原文の説明を表示しています。

hideki5123/agent-skill-set22026年10月21日 更新

chrome-use

無料

Drive an already-running, LOGGED-IN Chromium browser on macOS via AppleScript — navigate, click, fill forms, scroll, and extract page content from the user's REAL session, with the browser left open and NO profile copy and NO restart. Use when the task needs the existing logged-in session (cookies, auth, current tabs) reused as-is. Trigger phrases: "chrome-use", "ブラウザから取得", "ログイン済みの Chromeで", "ブラウザを操作して", "このページ読んで", "Xのスレッド読んで", "ログインしたまま取得", "自分のセッションでスクレイプ", "read this page in my browser", "scrape with my session", "drive my chrome", "execute JS in my (logged-in) browser", "automate my logged-in browser". Chromium family (Chrome default; Brave/Edge/Arc/Vivaldi via --app). NOT for isolated/throwaway automation where login reuse is unneeded — use playwright-cli for that. macOS only.

日本語の概要は準備中です。原文の説明を表示しています。

hideki5123/agent-skill-set22026年10月21日 更新

codex-cli

無料

Run OpenAI Codex CLI from the terminal for batch / one-shot `codex exec` invocations with output captured to an `-o` file. Use for fire-and-forget runs, scripted CI, code review batches (`codex review`), and resuming a specific session by id (`codex exec resume`). Always use this skill instead of `mcp__codex__codex` and `mcp__codex__codex-reply` MCP tools — CLI is faster and more capable. For streaming UX, multi-turn dialogues that need live state, structured (JSON schema) output, attaching images, or programmatic event handling → **use codex-server instead**. codex-server uses the user's ChatGPT subscription via Codex App Server and decoupled async invocation that bypasses the Bash 2-minute timeout entirely. Trigger patterns (batch-only — chat/streaming triggers belong to codex-server): codex-cli / codex CLI / codex exec / codex review / codex resume / codex fork / batch + {codex, gpt} / one-shot + {codex, gpt} / non-interactive + codex / codex {to a file, -o, output file, captured output} / CI + {codex, gpt} / scripted + {codex, gpt} / fork codex session / resume codex session by id

日本語の概要は準備中です。原文の説明を表示しています。

hideki5123/agent-skill-set22026年10月21日 更新

codex-server

無料

Run OpenAI Codex via the Codex App Server (JSON-RPC-over-stdio) for streaming multi-turn chat sessions with persistent threads, structured output, image input, and rich event streams. Default entry point for ChatGPT/GPT/Codex-like conversations from the terminal. Uses the user's ChatGPT subscription (Plus / Pro / Team) exclusively via `codex login` — never consumes OPENAI_API_KEY billing, by design. Implementation: TypeScript on deno with npm:@openai/codex-sdk; spawns the existing system codex binary. Decoupled async invocation: every turn returns turn-id in <1 s; the actual SDK work runs in a detached worker that streams to per-turn files under ~/.codex-server/turns/<turn-id>/ — Bash's 2-min timeout never applies. Prefer this over codex-cli for streaming UX, multi-turn dialogues that need live state, structured (JSON schema) output, attaching images, or programmatic event handling. Use codex-cli only for one-shot batch invocations that pre-capture to an -o file. For OpenAI Platform API calls specifically (embeddings, image generation, audio, moderation, batches, files) — not open-ended chat — use openai-cli instead; that path bills OPENAI_API_KEY, this one uses the ChatGPT subscription. Trigger patterns (match any variation): codex / codex-server / codex app server / codex app-server / openai / open ai / OpenAI / chatgpt / chat gpt / ChatGPT / GPT / ask gpt / chat with gpt / gpt session / codex session / streaming chat / multi-turn chat / multi turn chat / second opinion / cross-check / cross check / ai pair programming / another AI / external AI / ask another model / get GPT's take / what does openai think / show me what gpt thinks / structured output from gpt / json schema gpt / resume codex thread / continue codex conversation / continue codex session / /codex-server

日本語の概要は準備中です。原文の説明を表示しています。

hideki5123/agent-skill-set22026年10月21日 更新

hideki5123 のスキルをすべて見る

このスキルの問題を報告する