Use when porting a workflow to a different AI provider, deployment environment, model tier, or organizational context.
SkillScore18Maintained
Automatic
◆AI Engineer pack
Last verified 8/21/2026
What it changes
Passed 4 of 22 test cases with the skill, and 3 of 22 without it.
Without skill14%
With skill18%
Checks it passed that the model alone missed
Invokes /agent-workflow or /teach-maestro prior to providing the plan
Recommends executing /evaluate and /diagnose after completing the adaptation
Presents the Adaptation Assessment table containing model provider, tier, deployment env, team structure, and data sensitivity dimensions
1 fixed3 passed either way18 still failing0 broke
Pass-rate lift
+5 pp
Tokens
+9%
Agent turns
0%
Response time
-2%
Model gemini-3.6-flashMeasured 8/21/2026v14 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
Our research assistant workflow was built for internal dev testing, but now we are moving it into a highly regulated healthcare environment with strict data privacy rules and lower latency targets. Please evaluate the impact of this move and generate a comprehensive checklist and plan to adapt our setup.
What was checked, without and with the skill
Checked
Without skill
With skill
Invokes /agent-workflow or /teach-maestro prior to providing the plan
Missed
Passed
Presents the Adaptation Assessment table containing model provider, tier, deployment env, team structure, and data sensitivity dimensions
Missed
Passed
Recommends executing /evaluate and /diagnose after completing the adaptation
Missed
Passed
case-02 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md52 linessingle file
MANDATORY PREPARATION
Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first. Additionally gather: what the workflow is being adapted to.
Adapt a working workflow for a different context.
Adaptation Assessment
Dimension
Current
Target
Impact
Model provider
?
?
Prompt format, capabilities, pricing
Model tier
?
?
Context window, reasoning ability
Deployment env
?
?
Latency, availability, compliance
Team structure
?
?
Monitoring, escalation, ownership
Data sensitivity
?
?
Guardrails, logging, access controls
Provider Adaptation
Prompt format: Adjust for provider-specific features
Context limits: Resize context budget for different window sizes
Capability gaps: Identify features available in one provider but not another
Pricing model: Recalculate cost estimates
API differences: Update tool calling interfaces, error handling, retry logic