mindit-audit

name

mindit-audit

description

Run a full review of a design through all eight forces (clarity, continuity, constraint, consequence, context, cost, confidence, correctability) and produce a balanced scorecard with weakest-force identification. Use this whenever the user asks for a "full review," "complete audit," "review everything," wants a comprehensive design review, says "find what's wrong," or pastes a design without specifying which lens to use. Also the right starting skill when the user is new to mindit. Produces a scorecard with one score per force and a recommendation for where to focus.

mindit-audit

The first of three meta skills. Run this when the user wants a full review, not a single force.

What this skill does

Runs all eight forces against the same subject and produces a scorecard. Surfaces the lowest-scoring force as the bottleneck to address first. Inspired by the observation that uneven force profiles indicate uneven attention: a design scoring 90 on Clarity and 20 on Correctability has not been thought through, it has been polished.

When to run this

• The user asks for "a review," "full audit," "complete review," "review my design."
• The user has just shown a design and asked an open-ended question like "what do you think" or "what should I change."
• The user is new to mindit and does not yet know which force applies.
• The user wants a launch readiness check before shipping a feature.

How to analyze

1. Capture the subject and the constraints. Same as for any single-force skill: what is being analyzed, what hard limits apply, what audience, what platform. If essential information is missing, ask once before running.

2. Run each force in turn. Follow the procedure in each force's own SKILL.md. Do not shortcut. Eight artifacts get produced, plus a synthesis.

   • mindit-clarity
   • mindit-continuity
   • mindit-constraint
   • mindit-consequence
   • mindit-context
   • mindit-cost
   • mindit-confidence
   • mindit-correctability

3. Identify the bottleneck. Find the lowest-scoring force. That is where the design is weakest, and where attention will produce the largest improvement.

4. Identify the lopsidedness. Look at the spread between the highest and the lowest force. A wide spread (e.g. 90 down to 25) usually means the team is over-investing in some forces and ignoring others.

5. Write the synthesis artifact. See "Output format."

Rubric

The audit does not have its own rubric; it inherits the rubrics of the eight force skills. The audit's own score is reported as the lowest force score (the bottleneck), not an average. Averages mask the failure mode: a 70 average with a 25 in Correctability is still going to fail at launch.

Output format

Produce nine files in .mindit/decisions/:

1. Eight per-force artifacts, one for each force. Filenames as defined in each force's SKILL.md.
2. One audit synthesis artifact:
   • Markdown: audit-<yyyymmdd>-<slug>.md
   • JSON: audit-<yyyymmdd>-<slug>.json with skill: "mindit-audit" and force: "meta". The score field equals the lowest force score. The criteria array contains one entry per force with its individual score.

Synthesis template (markdown)

# Full audit: <subject name>

**Bottleneck score:** <lowest force score>/100 (<force name>)
**Spread:** <highest - lowest> points
**Date:** <ISO date>
**Subject:** <what was analyzed>

## Force profile

| Force | Score | Trend |
|---|---|---|
| Clarity | <s>/100 | <emoji or word> |
| Continuity | <s>/100 | |
| Constraint | <s>/100 | |
| Consequence | <s>/100 | |
| Context | <s>/100 | |
| Cost | <s>/100 | |
| Confidence | <s>/100 | |
| Correctability | <s>/100 | |

## Where to focus

The bottleneck is <force>. Fix that first; the rest of the profile will move with it.

Top three findings, ranked by severity:
1. <finding from force A>
2. <finding from force B>
3. <finding from force C>

## What looks healthy
<the two highest-scoring forces, briefly>

## What looks lopsided
<the spread analysis: are some forces ignored entirely?>

## Open questions
<unmade decisions surfaced by the audit>

Example

Input: "Audit the new checkout flow."

Sample profile:

Force	Score
Clarity	78
Continuity	71
Constraint	42
Consequence	55
Context	39
Cost	60
Confidence	47
Correctability	28

Bottleneck: Correctability at 28. Spread: 50 points (78 down to 28). Lopsided profile — team has spent attention on look and feel (Clarity 78) but has not planned for being wrong (Correctability 28).

Top findings:

1. [critical] No rollback plan for the new checkout if conversion drops on launch day.
2. [high] No telemetry on funnel steps before-vs-after comparison.
3. [high] No mobile breakpoint defined; product ships on iOS.

Focus order: Correctability first, then Context, then Constraint.

What this skill does NOT do

• Does not skip forces because they "don't apply." Every force has something to say. If a force genuinely does not apply (rare), note why in the synthesis.
• Does not average scores. The bottleneck score is the lowest, deliberately. Averages mislead.
• Does not produce design changes. It produces a map. The team makes the changes.