agentleFS
jqaisystemsjqaisystems/jqai-ai-skills/skills/discovery-brief/SKILL.md

discovery-brief

Skill3 starsChanged 6 months agoMITView on GitHub

Run a structured discovery interview for a new client project and turn the answers into a completed brief plus a strategy starter document. Conversational, skips what is already known, and never fabricates unanswered questions. Use when the user says "run discovery", "brief for this client", "discovery questionnaire", or "help me figure out what this client needs".

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before asking anything, read whatever the user points at: an existing brief, intake form answers, emails, meeting notes, the client's …

    line 14
  2. Distinctive:

    Ask in small batches, not twenty questions at once.

    line 18
  3. Distinctive:

    Never fabricate answers. Unanswered questions go under Open questions.

    line 60
  4. Distinctive:

    No em dashes in any output.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Discovery Brief

A project priced before discovery is a project scoped by hope. This skill runs the discovery conversation and turns the answers into two working documents: the brief (the project's source of truth) and a strategy starter (the first thinking pass).

This is the interview counterpart to a client-facing intake form: the client-intake-builder skill generates an HTML questionnaire the CLIENT fills in alone; this skill interviews YOU (or processes the client's answers) and writes the documents.

Step 1: Read what already exists

Before asking anything, read whatever the user points at: an existing brief, intake form answers, emails, meeting notes, the client's website. Never ask a question the material already answers.

Step 2: Interview across seven areas

Ask in small batches, not twenty questions at once. Skip known answers.

  1. Business: what the client does, how they make money, what stage they are at (new, rebrand, growing).
  2. Audience: who buys now, who they WANT to buy, price positioning (budget, mid, premium).
  3. Competitors: two or three names, what the client envies or hates about each.
  4. Personality: three to five adjectives the brand should own, two or three it must never be.
  5. Style direction: references they love, styles or colours that are off-limits.
  6. Deliverables: exactly what the project produces (logo, identity system, guidelines, packaging, website, motion, other).
  7. Timeline and budget: deadline and budget range, mapped against the user's own tiers if a pricing config exists (see the proposal-writer skill).

Step 3: Write the two documents

The brief (default Brief.md in the client's folder): status, started date, scope checklist, and every answer organized under the seven areas. Keep the client's own words where they are vivid; quote them. Unknowns stay visible as open items, never filled with guesses.

The strategy starter (default Strategy/01_Strategy.md):

# <Client> Strategy Starter

## Positioning (draft)
One sentence: for WHOM, the brand is WHAT, unlike COMPETITOR because REASON.

## Audience snapshot
## Competitive picture
What competitors do visually or verbally, and where the gap is.

## Personality and tone
The adjectives, and what each means in practice.

## Direction hypotheses
Two or three distinct directions worth exploring, two lines each.

## Open questions
Everything discovery did not answer.

Step 4: Report

Summarize the positioning sentence and the direction hypotheses in chat, with both file paths. Suggest the natural next step (a proposal, or moodboards).

Rules

  • Never fabricate answers. Unanswered questions go under Open questions.
  • One project per run. Discovery does not batch.
  • No em dashes in any output.

Output

A completed brief and a strategy starter document, plus a chat summary of positioning and direction hypotheses.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.