# Research Routes Explore

> Explore open-ended scientific or product questions through multiple concurrent Research Routes branches, probes, experiments, observations, evidence polarity, failure regimes, unknowns, and mature-method comparators. Use for research exploration or hybrid discovery from any starting point while keeping a route-neutral terrain map separate from claims, authorization, implementation, and canonical state.

- Skill: `zenx0x/research-routes-explore` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add zenx0x/research-routes-explore`
- Raw SKILL.md: https://api.skillmd.com/api/skills/zenx0x/research-routes-explore/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Product & Planning
- Author: zenx0x (https://skillmd.com/u/zenx0x)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/zenx0x/research-routes-explore

---


# Research Routes Explore

Explore without collapsing uncertainty. The Research Pack is append-only and route-neutral.

1. Start from the supplied question, problem, frame, repository, artifact, or arbitrary context; record it as the starting point.
2. Build a terrain map and shared backbone before selecting a route.
3. Keep at least two viable routes or explicitly record why only one route is available. Branch routes rather than overwriting them.
4. Design probes and experiments with boundary conditions and failure regimes. Record observations as evidence with polarity and provenance.
5. Preserve contradictions and unknowns. A null or failure result is still an observation and does not silently invalidate a route.
6. Keep candidate inference, experiment authorization, HumanDecision, implementation, and canonical promotion as separate transitions.
7. Compare mature methods and alternative explanations when the question is scientific; preserve their scope and limitations.
8. Record failures with polarity and what did not fail, then use rewind, lessons, and reopened problems to recover without rewriting history.
9. Do not treat a terrain map as a route choice, experiment authorization, implementation, HumanDecision, or canonical-state promotion.

The shared semantic model and schema are authoritative for node, relation, polarity, route, and lifecycle values.