ralph-specum-research

Ralph Specum Research

You are a coordinator, not a researcher -- delegate ALL work to a research-analyst 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
• Respect .claude/ralph-specum.local.md when present
• Default specs root is ./specs
• Keep the canonical Ralph file names
• Merge state fields only

Action

1. Resolve the active spec. If none exists, stop and tell the user to start a spec first.
2. Read the goal, .progress.md, current state, indexed codebase context, related specs, and epic context when present.
3. Run phase_gate.py mode through "$RALPH_CODEX_PLUGIN_ROOT/scripts/phase_gate.py" with STATE and exact --quick, exact --interactive, or no flag. Reject both, -q, variants, and natural-language substitutes.
4. Run skill discovery pass 1 when the state lacks an applicable revision. Select explicitly named skills and record harness-shadowed duplicates.
5. Load "$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 evidence scope, decision thresholds, and material unknowns. Inspect source availability, code facts, and existing patterns instead of asking.
6. 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 research writer dispatch. A failed check-delegation in either mode stops this invocation before phase transition, child dispatch, or target-artifact write; after a normal-mode failure, only the next explicit invocation creates a fresh manifest/interview identity. 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. Exact --quick retains its existing question-and-approval bypass and discovery, manifest, delegation, and writer checks.
7. Delegate research generation to a research-analyst sub-agent. Keep the existing child packet, identity tuple, and receipt behavior unchanged: pass the absolute gate helper path, state path, full identity tuple, unique teammate dispatch identity, verbatim skill manifest, goal, context, and interview results. The sub-agent reloads and records the manifest, passes check-agent-write with that unique identity, and writes research.md. Do NOT write research.md yourself.
8. Read the sub-agent's output and validate it exists.
9. Merge state with phase: "research" and awaitingApproval: true (or false when exact --quick is active).
10. Update .progress.md with the research summary, blockers, learnings, next step, skill discovery, and verification tooling notes when relevant.
11. If spec commits are enabled, commit only the spec artifacts.
12. In normal mode, when the user selects continue to prototype, treat research.md as approved and route to $ralph-specum-prototype --suggested --return-phase requirements with the same resolved base path. Let that skill own prototype behavior and its return handoff.