geo-content-brief-skill

Geo Content Brief Skill

When To Use This Skill

The user provides interview notes, keywords, competitor snippets, product selling points, or channel restrictions, and wants them consolidated into a Chinese content brief.
The team needs to convert scattered inputs into actionable GEO content topics, angles, structure, evidence, and delivery requirements.
It is necessary to first clarify trigger boundaries, input gaps, and output acceptance criteria before entering content production.

Read user input and identify the target audience, content channels, keywords, brand boundaries, prohibited expressions, and information that must be covered.
Against references/brief-structure.md generate the brief skeleton: goals, insights, angles, keywords, structure, evidence, risks, and acceptance criteria.
If core inputs are missing, first ask at most three clarifying questions, and do not use assumptions to fill in facts the user has not provided.
Use evals/trigger_cases.jsonl to check whether the current request belongs to the GEO content brief scenario.
Use evals/output_cases.jsonl to check whether the output includes an input summary, content structure, evidence requirements, prohibited areas, and next actions.
Before delivery, review channel restrictions and brand prohibited areas, and remove vague marketing jargon, unsourced assertions, and non-actionable recommendations.

Interview notes, sales feedback, customer questions, or expert opinions.
Keywords, search intent, competitor page summaries, or ranking leads.
Target channels, target readers, brand tone, prohibited words, and delivery format.

A one-page Chinese content brief, including goals, audience, core insights, recommended angles, article structure, keyword placement, evidence requirements, and risk notes.
A gap list explaining the information that must be completed before continuing production.
Next actions, for writers, editors, or SEO/GEO leads.

Before final output, apply the likely failure modes in reports/output-risk-profile.md when that report is present.
Before rendering reports, tutorials, review pages, dashboards, or visual artifacts, apply the artifact direction and visual quality gates in reports/artifact-design-profile.md when that report is present.
When prompt behavior, role design, dialogue quality, or output contracts matter, apply reports/prompt-quality-profile.md when that report is present.
Before adding more structure, apply the boundary, feedback-loop, drift, and leverage-point checks in reports/system-model.md when that report is present.
Repair generic headings, cluttered notes, fragile visual assumptions, weak tables, and missing verification cues before handing work back.
Map role, task, and format into skill behavior rather than copying a large prompt template into SKILL.md.
Let the artifact's content choose the visual system; do not copy a fixed palette or report style from another skill without a clear reason.
If output-specific evidence is missing, state the gap instead of inventing screenshots, citations, data, or examples.

Do not directly ghostwrite complete long-form articles, do not replace brand strategy judgment, and do not fabricate competitor data, search volume, rankings, or citation sources.
When the user only wants title inspiration, advertising copy, public opinion analysis, or complete article writing, this Skill should not be triggered.
When the target readers, channels, or keywords are missing, first tighten the input, then output the brief.

references/brief-structure.md: Chinese GEO content brief structure, field descriptions, and quality standards.
references/review-checklist.md: Pre-delivery editorial review checklist.
evals/trigger_cases.jsonl: Examples that should and should not trigger.
evals/output_cases.jsonl: Output structure acceptance examples.