Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Run the code and documentation simplification passes together over one scope, launching every review agent concurrently before applying a single round of fixes. Use when the user asks to "simplify all", "simplify everything", "simplify code and docs", "clean up code and docs", "run both simplify skills", or "simplify code and docs in parallel".
.claude/skills/tobihagemann-simplify-all/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -52% | 0% |
| case-22 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 232% | 0% |
$simplify-code and $simplify-docs SkillsRun the $simplify-code and $simplify-docs skills together, passing along any scope that was provided so both passes cover identical files.
Issue the spawn_agent calls for every review sub-agent the two skills define in one batch. Do not issue one and await its result before issuing the rest. Hold every fix for Step 2 in place of each skill's own fix step.
Once wait_agent has joined every sub-agent, aggregate the findings and apply one round of fixes, following each skill's own guidance for resolving its findings.
Once this round's fixes have landed, including any resolved at a gate, make one pass over the agents' findings: any whose verdict depended on code the fixes changed, moved, added, or deleted gets decided again against the current tree, keeping resolutions the user already chose.
Then call update_plan to mark this step completed and continue with the next step of the active workflow.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 7,268 | 6,749 | -7% | 1 | 1 | 0% | 1,039 | 591 | -43% | 0 | 0 | — |
case-02 | fail→fail | 3,499 | 7,993 | +128% | 1 | 1 | 0% | 344 | 830 | +141% | 0 | 0 | — |
case-03 | fail→fail | 25,193 | 4,230 | -83% | 1 | 1 | 0% | 842 | 500 | -41% | 0 | 0 | — |
case-04 | pass→pass | 2,082 | 5,064 | +143% | 1 | 1 | 0% | 312 | 1,036 | +232% | 0 | 0 | — |
case-05 | pass→pass | 1,764 | 4,191 | +138% | 1 | 1 | 0% | 269 | 898 | +234% | 0 | 0 | — |
case-06 | pass→pass | 2,602 | 3,997 | +54% | 1 | 1 | 0% | 386 | 879 | +128% | 0 | 0 | — |
case-07 | fail→pass | 11,704 | 9,607 | -18% | 1 | 1 | 0% | 1,695 | 1,754 | +3% | 0 | 0 | — |
case-08 | pass→pass | 9,406 | 3,424 | -64% | 1 | 1 | 0% | 1,315 | 828 | -37% | 0 | 0 | — |
case-09 | fail→fail | 11,218 | 7,215 | -36% | 1 | 1 | 0% | 1,840 | 1,436 | -22% | 0 | 0 | — |
case-10 | pass→pass | 12,289 | 4,415 | -64% | 1 | 1 | 0% | 1,845 | 920 | -50% | 0 | 0 | — |
case-11 | pass→pass | 11,299 | 3,631 | -68% | 1 | 1 | 0% | 1,667 | 839 | -50% | 0 | 0 | — |
case-12 | fail→pass | 11,070 | 9,369 | -15% | 1 | 1 | 0% | 1,935 | 1,297 | -33% | 0 | 0 | — |
case-13 | fail→fail | 7,658 | 2,528 | -67% | 1 | 1 | 0% | 1,176 | 637 | -46% | 0 | 0 | — |
case-14 | pass→pass | 13,087 | 3,010 | -77% | 1 | 1 | 0% | 2,018 | 766 | -62% | 0 | 0 | — |
case-15 | fail→pass | 12,897 | 4,681 | -64% | 1 | 1 | 0% | 2,248 | 1,076 | -52% | 0 | 0 | — |
case-16 | pass→pass | 17,731 | 6,466 | -64% | 1 | 1 | 0% | 2,632 | 1,299 | -51% | 0 | 0 | — |
case-17 | pass→pass | 8,347 | 3,708 | -56% | 1 | 1 | 0% | 1,272 | 883 | -31% | 0 | 0 | — |
case-18 | fail→fail | 11,166 | 6,796 | -39% | 1 | 1 | 0% | 1,973 | 724 | -63% | 0 | 0 | — |
case-19 | pass→pass | 12,239 | 2,254 | -82% | 1 | 1 | 0% | 1,859 | 603 | -68% | 0 | 0 | — |
case-20 | pass→pass | 11,122 | 5,114 | -54% | 1 | 1 | 0% | 1,663 | 1,005 | -40% | 0 | 0 | — |
case-21 | fail→fail | 11,398 | 2,126 | -81% | 1 | 1 | 0% | 1,783 | 552 | -69% | 0 | 0 | — |
case-22 | fail→pass | 11,724 | 4,847 | -59% | 1 | 1 | 0% | 1,759 | 1,075 | -39% | 0 | 0 | — |
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 18 counted toward the lift figure. The other 4 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 +18 percentage points is the difference between those two pass rates over the 18 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/21/2026 | +27% |
Other measured skills in the registry, with their headline benchmark lift.