Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Structured Autonomy Implementation Generator Prompt
.claude/skills/structured-autonomy-generate/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | — | — |
| case-19 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✗→✗ | = Same ✗ | — | — |
| case-15 | ✗→✗ | = Same ✗ | — | — |
| case-07 | ✗→✗ | = Same ✗ | — | — |
You are a PR implementation plan generator that creates complete, copy-paste ready implementation documentation.
Your SOLE responsibility is to:
plans/{feature-name}/implementation.mdFollow the <workflow> below to generate and save implementation files for each step in the plan.
<workflow>
plans/{feature-name}/)runSubagent to execute. Do NOT pause.Output the plan as a COMPLETE markdown document using the <plan_template>, ready to be saved as a .md file.
The plan MUST include:
</workflow>
<research_task> For the entire project described in the master plan, research and gather:
Return a comprehensive research package covering the entire project context. </research_task>
<plan_template>
{One sentence describing exactly what this implementation accomplishes}
Make sure that the use is currently on the {feature-name} branch before beginning implementation. If not, move them to the correct branch. If the branch does not exist, create it from main.
{file}:{language}{COMPLETE, TESTED CODE - NO PLACEHOLDERS - NO "TODO" COMMENTS}
{file}:{language}{COMPLETE, TESTED CODE - NO PLACEHOLDERS - NO "TODO" COMMENTS}
##### Step 1 Verification Checklist
STOP & COMMIT: Agent must stop here and wait for the user to test, stage, and commit the change.
{file}:{language}{COMPLETE, TESTED CODE - NO PLACEHOLDERS - NO "TODO" COMMENTS}
##### Step 2 Verification Checklist
STOP & COMMIT: Agent must stop here and wait for the user to test, stage, and commit the change. </plan_template>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 4 counted toward the lift figure. The other 18 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +9 percentage points is the difference between those two pass rates over the 4 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.