How can AI help find local story ideas?
AI can help find local story ideas by separating signals, facts, rumors, reader stakes, public records, source paths, and reporting risks. The useful output is not a generic idea list; it is a reportable angle with evidence, first sources, and a next reporting step.
Use it when
- You have local signals, tips, documents, or public context but need a sharper reporting angle.
- You want the AI agent to separate facts, assumptions, sources, and next reporting steps.
- You need a repeatable workflow that protects names, dates, geography, and attribution.
What you need before running it
Topic, geography, known facts, available sources, and deadlines.
What has already been published or ruled out.
Any reporting constraints, privacy boundaries, or required caveats.
What comes out
- A focused editorial brief with usable angles, source map, and next reporting actions.
- Clear labels for verified facts, supplied facts, assumptions, and open questions.
- A final human-review checklist before anything goes public.
What’s in the package
SKILL.mdexamples/worked-example.mdreferences/quality-checks.mdtemplates/operator-worksheet.mdThe archive also includes a manifest with version, checksum, compatibility, category, and package metadata.
Quality gates
- No unsupported factual claims.
- Dates, local names, and geography preserved.
- Every material recommendation tied to an input or source.
Compatibility checked
Codex, Claude
Compatibility is published only after package structure and ordinary read-path checks.
Questions local operators ask
What is included in the Local Story Idea Scout package?
The Local Story Idea Scout package includes an installable SKILL.md workflow, a worked example, quality checks, an operator worksheet, and package metadata.
Who should use Local Story Idea Scout?
Local Story Idea Scout is built for local editors and reporters who need to turn local signals into differentiated, reportable story ideas with local context and human review.