本文へ移動
cccskills
無料GitHub で公開

ralph-specum-requirements

This skill should be used only when the user explicitly asks to use `$ralph-specum-requirements`, or explicitly asks Ralph Specum in Codex to run the requirements phase.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md6.5 KB
  • agents/openai.yaml1.1 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。

Ralph Specum Requirements

You are a coordinator, not a product manager -- delegate ALL work to a product-manager sub-agent.

Derive RALPH_CODEX_PLUGIN_ROOT from this loaded skill by resolving two parent directories from the SKILL.md directory. Never derive it from the project working directory.

Contract

  • Resolve the active spec by explicit path, exact name, or .current-spec
  • Require the spec directory to exist
  • Merge state fields only
  • Keep the Ralph disk contract unchanged

Action

  1. Resolve the active spec. If none exists, stop.
  2. Read research.md when present, .progress.md, and the current state.
  3. Run phase_gate.py mode through "$RALPH_CODEX_PLUGIN_ROOT/scripts/phase_gate.py" with STATE and exact --quick, exact --interactive, or no flag. Reject both, -q, variants, and natural-language substitutes.
  4. When research.md exists, require its artifact approval in interactive mode; exact quick mode continues with the validated file. When it is absent, record that there is no upstream research artifact and require no prior-artifact approval.
  5. When research.md exists, require skill discovery pass 2 against the goal plus final research. When it is absent, require pass 1 against the goal alone. Run the applicable pass when the state lacks its revision. Select explicitly named skills and record harness-shadowed duplicates.
  6. Load "$RALPH_CODEX_PLUGIN_ROOT/skills/interview-framework-codex/SKILL.md", its required algorithm and domain-modeling references, and all selected domain contracts in both interactive and quick mode. In interactive mode, use its focused brainstorming method for critical user outcomes, scope exclusions, acceptance thresholds, and material non-functional requirements. Inspect existing behavior and terminology instead of asking.
  7. Clear any prior approval gate by merging awaitingApproval: false before generation.
  8. In interactive mode, require explicit approve and delegate; in exact quick mode, record bypassed_quick. In both modes, run phase_gate.py check-delegation with the current loaded-manifest identity before creating the child. Apply the shared hard-transition invariant before requirements writer dispatch. A failed check-delegation in either mode ends this invocation before phase transition, child dispatch, or target-artifact write; after a normal-mode failure, the next explicit invocation creates a fresh manifest/interview identity and does not create an alternate quick bypass. After an exact --quick delegation failure, the next explicit invocation reruns discovery, records a fresh phaseSkillLoad and interview identity, and does not reuse a terminal bypassed_quick interview or its discovery revision. Only a matching in-progress collecting or awaiting_confirmation interview is resumable.
  9. Delegate requirements generation to a product-manager sub-agent. Pass the absolute helper path, state path, identity tuple, unique teammate dispatch identity, verbatim manifest, research context, goal, and interview results. The child reloads and records the manifest, passes check-agent-write with that unique identity, and writes requirements.md. Do NOT write requirements.md yourself.
  10. Read the sub-agent's output and validate it exists.
  11. Merge state with phase: "requirements" and awaitingApproval: true (or false when exact --quick is active).
  12. Update .progress.md with approved research context, user decisions, blockers, next step, skill discovery, and any epic constraints that must carry forward.
  13. If spec commits are enabled, commit only the spec artifacts.
  14. In normal mode only, when the user selects continue to prototype, treat requirements.md as approved and route to $ralph-specum-prototype --suggested --return-phase design with the same resolved base path. Let that skill own prototype behavior and its return handoff.

Quick Prototype Gate

After requirements validation and review in quick mode:

  1. Select the oldest prototype that blocks design. If none blocks design, select the highest-risk grounded, falsifiable question from research.md and requirements.md; let the prototype coordinator record a skipped result when no suitable question exists.
  2. Make exactly one request: $ralph-specum-prototype --quick --return-phase design.
  3. Treat the request as requestAttempt: 1. Keep it separate from builderExecutionAttempt; duplicate reuse, supersession, conflict resolution, skip, and lock failure consume the request without adding a builder execution.
  4. Own every capture, conflict, verdict, retry, cleanup, and handoff decision. Ask no user questions and preserve unrelated active prototypes.
  5. Continue to design after every result. Treat a completed request as the one request on resume and never invoke the prototype skill a second time.

Stop Behavior

  • Without --quick: STOP HERE. Display the walkthrough summary and approval prompt. Do NOT continue to design. Wait for the user to explicitly approve and request the next phase.
  • With exact --quick: Run the Quick Prototype Gate once, then continue directly into design for every outcome.

Output Shape

The result should include user stories, acceptance criteria, functional requirements, non-functional requirements, dependencies, exclusions, and success criteria.

Response Handoff

  • After writing requirements.md, name requirements.md and summarize the requirements briefly.
  • When normalized quickMode is false, end with exactly one explicit choice prompt:
    • approve current artifact
    • request changes
    • continue to design
    • continue to prototype
  • Treat continue to design as approval of requirements.md.
  • Treat continue to prototype as approval of requirements.md and route through $ralph-specum-prototype with returnPhase: design.
  • With exact --quick, do not show this prompt; continue directly to design after the phase gates and single Quick Prototype Gate request complete.
  • During artifact review, apply the changes immediately delegates already-recorded feedback through a new unique dispatch, redisplays the artifact, and stays at this approval gate. Ask one focused change question only when no feedback is pending. Control-only continue, proceed, and go ahead approve nothing.

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。

同じリポジトリのスキル

概要と使いどころ

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

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。

tzachbon/smart-ralph5592026年9月16日 更新

Output rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.

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。

tzachbon/smart-ralph5592026年9月16日 更新

This skill should be used when generating spec artifacts (research.md, requirements.md, design.md, tasks.md), formatting agent output, structuring phase results, or when any Ralph agent needs guidance on concise, scannable output formatting. Applies to all Ralph spec phase 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。

tzachbon/smart-ralph5592026年9月16日 更新

Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.

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。

tzachbon/smart-ralph5592026年9月16日 更新

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

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。

tzachbon/smart-ralph5592026年9月16日 更新

This skill should be used when a Ralph phase must identify critical user decisions, run a layered grill, persist partial answers, obtain explicit approval, or resume an interrupted phase interview before delegating artifact work.

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。

tzachbon/smart-ralph5592026年9月16日 更新

tzachbon のスキルをすべて見る

このスキルの問題を報告する