Skip to content

TechTalk AI Readiness Assessment

A self-contained plugin for Claude Code and GitHub Copilot CLI that assesses how ready a team — and its codebase — is to collaborate with AI.

Invoke it once in any repository and it scans for evidence, asks a few clarifying questions, and produces a timestamped report that places the team on two complementary maps:

The distance between them is the Habitat/Workflow Gap — a coherence diagnostic that points at the single most valuable next move.

Run your first assessment Install the plugin Product overview (techtalk.at)

See a real report

Curious what the output looks like? We ran the assessment against this plugin's own repo — read the example self-assessment (markdown + rendered HTML).


Find your way around

This documentation follows the Diátaxis framework — four kinds of documentation for four kinds of need.

Tutorials — learning-oriented Start here. A guided, end-to-end run that produces your first assessment.
How-to guides — task-oriented Recipes: install in each tool, run an assessment, read the gap, render the HTML report.
Reference — information-oriented The model's fourteen dimensions, the cognitive ladder, the gap formula, the output structure.
Explanation — understanding-oriented Why two maps, why coherence beats level, why the instrument is standalone.

What you get from one run

  1. A discovery report of the habitat documents and signals found (with paths).
  2. A Habitat Maturity Profile — all fourteen model dimensions placed L1–L5, with the model's own verbs, and a headline Habitat Maturity Level.
  3. A cognitive level (L0–L5) with a one-line rationale anchored in the weakest of three disciplines.
  4. The Habitat/Workflow Gap and its regime (Coherent / Ambition outpaces enablement / Inherited habitat).
  5. Strengths, gaps, and three evidence-anchored recommendations.
  6. A gap-anchored reading path into The Sovereign Engineer and a single TechTalk engagement suggestion.

The assessment is fully self-contained — it depends on no other plugin, agent, or service. See Why it is self-contained.


More than one repository?

A team that owns several repositories carries the same habits into all of them — what changes is the environment those habits meet. The spread of that difference is a finding a single-repository assessment cannot produce.

I want to… Invoke Start here
Summarise assessments that already exist across repos /ai-readiness-rollup Roll up existing assessments
Assess a whole estate in one session /ai-readiness-assess --scope Assess a team across repositories

Both need a scope manifest. With none present, /ai-readiness-assess behaves exactly as described above — the multi-repo layer is entirely opt-in.

There is deliberately no portfolio score: averaging the gaps erases the spread, which is the only thing a portfolio view adds. See why.