# Generate Candidate Directions

> Generate diverse candidate research fields/subfields consistent with current context while permitting deliberate boundary-crossing.

- Skill: `yogsoth-ai/generate-candidate-directions` (Agent Skill)
- Install (CLI): `npx get-skill add yogsoth-ai/generate-candidate-directions`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yogsoth-ai/generate-candidate-directions/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: yogsoth-ai (https://skillmd.com/u/yogsoth-ai)
- Updated: 2026-11-12
- Page: https://skillmd.com/skills/yogsoth-ai/generate-candidate-directions

---


# generate-candidate-directions

## Purpose

Generate diverse candidate research fields or subfields consistent with context while permitting deliberate boundary crossing.

## Input contract

```yaml
required: [research_intent, scope_anchor]
optional: [seed_evidence, actor_profile, constraints, neighboring_domains]
constraints: [each candidate must state fit, boundary crossing, and evidence needs]
```

## Procedure

1. Extract the problem mechanism, outcome, and scope anchor.
2. Generate candidates within the anchor and from adjacent domains.
3. Record the transfer or boundary-crossing rationale for each candidate.
4. Remove duplicates while preserving materially different mechanisms.

If candidate fields are diverse enough for comparative characterization, consider `synthesize-field-panorama` as the next tactic.

## Output contract

```yaml
produces: [candidate_directions, fit_rationales, boundary_crossings, evidence_questions]
delta_fields: [findings, hypothesis_updates, uncertainties, open_questions, recommended_jumps]
```

## Quality gates

- Candidates are distinct by mechanism or evidence opportunity.
- Speculative candidates are labeled as such.

## Failure and counterexamples

Do not equate popularity with fit or generate a list of fields without a boundary rationale.

## Provenance map

- `resolved: generate-candidate-fields`

