菜单
This skill should be used only when the user explicitly asks to use `$ralph-specum-start`, or explicitly asks Ralph Specum in Codex to start or resume a spec.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/tzachbon/smart-ralph --skill ralph-specum-start命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | ralph-specum-start |
| description | This skill should be used only when the user explicitly asks to use `$ralph-specum-start`, or explicitly asks Ralph Specum in Codex to start or resume a spec. |
| metadata | {"surface":"helper","action":"start"} |
Use this for the start and new entrypoints.
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.
.claude/ralph-specum.local.md when present./specs.current-spec in the default specs root.ralph-state.json. Do not replace the full object--quick or exact --interactive, --resume <prototype-id>, commit flags, optional specs root, and optional --tasks-size fine|coarse. Reject both mode flags together, -q, variants, and natural-language substitutes..current-spec. A new-spec request does not inherit or recover the existing current spec.specs/.current-epicnew is an alias here. Create the spec directory if needed.source: "spec"namegoal text used by the context gatebasePathphase: "research"taskIndex: 0totalTasks: 0taskIteration: 1maxTaskIterations: settings default or 5globalIteration: 1maxGlobalIterations: 100commitSpec: settings auto_commit_spec or truerelatedSpecs: []awaitingApproval: false while the goal interview is activequickModegranularity when --tasks-size was suppliedepicName when starting from an epic suggestion.current-spec..progress.md with goal, current phase, next step, blockers, learnings, and skill discovery results.tasks.md and present files over stale state when they disagree.phase_gate.py mode through "$RALPH_CODEX_PLUGIN_ROOT/scripts/phase_gate.py" with STATE and the exact supplied mode flag. No flag normalizes invalid legacy quick state to interactive..agents/skills, project .claude/skills, and the current Codex harness catalog. Always select explicitly named skills and record shadowed duplicates."$RALPH_CODEX_PLUGIN_ROOT/skills/interview-framework-codex/SKILL.md", its required algorithm and domain-modeling references, and every selected domain contract in both interactive and quick mode. In interactive mode, follow that algorithm for the start goal territory: outcome and observable success, material scope boundaries, critical constraints, and viable high-level approach. Ask no spec-path, branch, task-size, or discoverable question.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 a research-analyst child.phaseSkillLoad manifest. The child must record its loads and pass check-agent-write with that unique identity before writing research.md.research.md, merge phase: "research" and awaitingApproval: true in interactive mode or false in exact quick mode, update progress, and present artifact approval when interactive.After resolving the classified target and before normal resume or quick routing. Skip existing-current-spec recovery for new-spec intent:
"$RALPH_CODEX_PLUGIN_ROOT/scripts/resolve_spec_paths.py" and only its resolved basePath. When both basePath and <basePath>/.ralph-state.json exist, run "$RALPH_CODEX_PLUGIN_ROOT/scripts/prototype_records.py" reconcile --base-path "$BASE_PATH" --state "$BASE_PATH/.ralph-state.json", then re-read state.activePrototypes field as an empty map. Sort entries by created, then ID.$ralph-specum-prototype --resume <id> and stop this skill. In normal mode, resume the sole active entry automatically. When several remain, list deterministic IDs with question, status, blocker, returnPhase, and returnTaskIndex, then stop for an explicit ID.created, then ID. At the post-requirements boundary, route through $ralph-specum-prototype --quick; the prototype skill takes over the oldest design blocker and owns every decision. Preserve earlier quick flow and unrelated entries.resume_review candidate as recovery work, not terminal evidence. Parse the exact candidate, verify its ID and hash, and reconstruct a minimal recovery entry from the record and source pointers. Before reviewer dispatch, reserve its ID through create-only locked_state.py upsert-prototype with status: reviewing, the exact candidateHash, null owner and lease fields, a null or absent harnessRun.id, blocker and return fields, source pointers, and recovery timestamps. This is a recovery-only entry: cancellation verifies that owner, leaseToken, and harnessRun.id are all null or absent and that no builder is associated, then skips interrupt and release; inconsistent builder ownership fails closed. On a concurrent reservation, re-read and continue only if its candidateHash matches; never overwrite it. Route the restored entry through deterministic exact-candidate review and publish recovery. If reconstruction or reservation cannot proceed, stop and report the candidate ID and candidate hash. Exclude quarantined or malformed records. If no overlay exists, continue the existing start behavior without extra output.approve and delegate, dispatch research in the same turn.research.md in interactive mode, name the file, summarize it, and end with exactly one artifact approval prompt:
approve current artifactrequest changescontinue to requirements--quick, do not show this prompt; continue directly through the remaining phases after the gates succeed.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.