Generate a prioritized improvement roadmap to increase AI readiness. Trigger phrases: "generate roadmap", "what should I improve", "how to reach the next level", "autonomy improvement plan", "what are my next steps for AI readiness"
How this skill is triggered — by the user, by Claude, or both
Slash command
/codebase-ai-readiness:generate-roadmap [target-level] (L1-L5, defaults to next level above current)[target-level] (L1-L5, defaults to next level above current)This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Produce a detailed, prioritized improvement plan to advance the codebase to the next autonomy level (or a specified target level).
Produce a detailed, prioritized improvement plan to advance the codebase to the next autonomy level (or a specified target level).
Search for readiness-report.md in the codebase root. If it exists, read it and extract:
If no report exists, inform the user: "No readiness report found. Run /assess-readiness first to generate a baseline assessment."
Also extract from the report if present: workflow artifacts summary, compound engineering score, collaboration effectiveness recommendations.
references/level-transitions.md for transition requirements.For each category, compare the current score to what is needed for the target level. Load references/improvement-actions.md and references/improvement-actions-agent.md for common actions. Load references/implementation-phases.md for the strategic phasing model and prioritization principles.
Focus on:
If compound engineering readiness or progressive context disclosure is below the threshold
for the target level, load references/workflow-and-surfaces.md. Plan paired improvements:
Track A (CI, types, hooks, instruction files) and Track B (workflow artifact dirs, packaged
skills for repeatable agent workflows). Do not recommend only infrastructure fixes when session
context is absent.
If the readiness report lacks collaboration metrics or marks them "not measured", add roadmap
actions from ../assess-readiness/references/collaboration-metrics.md (tracking, PR template,
post-review rule updates).
For each recommended action, specify:
Order actions by: (1) unblock the next level first, (2) highest impact/effort ratio, (3) foundational actions before dependent ones.
Write a new readiness-roadmap.md file in the codebase root:
# AI Readiness Roadmap
**Current level**: LX | **Target level**: LY | **Current score**: XX/100
## Critical path (must-do for next level)
| # | Action | Category | Effort | Impact | Details |
|---|--------|----------|--------|--------|---------|
| 1 | ... | ... | ... | ... | ... |
## Session infrastructure (dual track)
Include this section when compound engineering or progressive context disclosure is below
target. Pair one Track A action (durable surfaces / CI) with one Track B action (workflow
artifacts or packaged skill) per row.
| # | Track A (durable surfaces) | Track B (workflow artifacts / skills) | Effort | Impact |
|---|----------------------------|---------------------------------------|--------|--------|
| 1 | ... | ... | ... | ... |
## Collaboration effectiveness
| # | Action | Effort | Impact | Details |
|---|--------|--------|--------|---------|
| 1 | ... | ... | ... | ... |
## High-impact improvements
| # | Action | Category | Effort | Impact | Details |
|---|--------|----------|--------|--------|---------|
| 1 | ... | ... | ... | ... | ... |
## Nice-to-have
| # | Action | Category | Effort | Impact | Details |
|---|--------|----------|--------|--------|---------|
| 1 | ... | ... | ... | ... | ... |
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub krokoko/cairn --plugin codebase-ai-readiness