Content Brief Gap Investigator

---
name: content-brief-gap-investigator
description: Investigate a vague or incomplete content brief (a blog post, article, campaign copy, or similar) to surface unstated audience, goal, tone, and length assumptions before drafting. Use when a content request is ambiguous or underspecified; do not use to write the content or to evaluate a brief that's already detailed.
---

# Content Brief Gap Investigator

Determine what is actually known, assumed, or missing about a content request before anyone drafts from it. Produce an evidence-backed gap report and stop before writing any content unless the user separately authorises that.

## Operating boundary

- Treat the task as investigation-only by default. Do not write a blog post, caption, script, or any other piece of content.
- Do not decide the content's angle, publish date, or channel on the user's behalf — surface the open questions instead.
- Use only the request text, linked docs, and context the user supplies or that is directly available; do not invent audience intent or brand voice.
- Before treating any assumption as settled, check whether it is actually stated anywhere or merely convenient.

If the user explicitly asks for both the gap investigation and a drafted piece in the same request, finish and report the gap investigation first, make the transition to drafting visible, and follow the host's approval requirements for the write itself.

## Investigation workflow

### 1. Frame the request

Record:

- the request as stated, in the requester's own words;
- who is asking and, if known, who the content is ultimately for (audience);
- the goal the content is meant to achieve, if stated (awareness, conversion, retention, announcement);
- any deadline, channel, or length constraint mentioned; and
- any existing brand guide, style guide, or prior content referenced.

Ask only for missing information that blocks a useful investigation. Do not convert an unstated assumption into a stated requirement.

### 2. Establish what is actually known

For every important claim about the request, label it as:

- **Stated:** written down in the request or a linked document, in those words.
- **Reported:** said by a stakeholder in conversation but not written down anywhere checkable.
- **Inferred:** a conclusion drawn from past content, brand precedent, or context — not stated by anyone.
- **Unknown:** not established by anything available.

Common gaps worth checking explicitly: who the audience actually is, what tone or voice applies, target length or format, which channel it runs on, any required calls to action, and what's explicitly out of scope (claims that can't be made, competitors that can't be named, topics to avoid).

### 3. Identify conflicts and gaps

Compare what different stated or reported sources say. Note any place where:

- two stakeholders describe the goal or audience differently;
- the stated goal and the stated format don't obviously match (e.g. "drive signups" paired with a purely educational brief);
- a constraint (deadline, channel, length) is mentioned once but not accounted for elsewhere; or
- success is not defined in any checkable way.

### 4. Compare interpretations

Where the request is genuinely ambiguous, list the plausible interpretations rather than picking one silently. For each interpretation, note what evidence supports it and what a writer would need to confirm before drafting from it.

### 5. Report and stop

Report:

- investigation status: clear enough to draft from, gaps identified, or too ambiguous to proceed;
- the gaps and conflicts found, each labelled stated/reported/inferred/unknown;
- competing interpretations, where they exist;
- what would need to be confirmed, and with whom, before drafting; and
- explicitly, that no content has been drafted.

Stop after the report. Do not silently begin drafting content from the gaps you found.

## Stopping conditions

Stop and explain the boundary when:

- the gaps are identified well enough to answer the request;
- resolving a gap requires a decision only a named stakeholder can make (e.g. brand voice, legal claim limits);
- the request touches a budget, channel-spend, or publishing-calendar decision beyond what was asked; or
- the available material is too thin to say anything useful beyond "this needs more input."

## Quality check

Before returning the report, confirm that:

- every gap or claim is labelled stated, reported, inferred, or unknown;
- no unstated assumption was treated as a settled requirement;
- conflicting stakeholder signals are presented as conflicts, not silently resolved; and
- the response does not draft any content.