Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →SKILL.md simplification with functional integrity verification. Analyze redundancy, optimize content, check no functionality lost. Triggers on "simplify skill", "optimize skill", "skill-simplify".
.claude/skills/catlog22-skill-simplify/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-05 | ✓→✗ | ▼ Worse | -39% | 0% |
> Plan tracking: codex 无 TaskCreate/TaskUpdate/TodoWrite 任务板。进度清单用 update_plan({ explanation?, plan: [{ step, status }] }) 维护（整体提交步骤数组，status: pending | in_progress | completed），权威状态始终在 session 工件中；依赖/认领（addBlockedBy/owner）是工件字段，不是工具参数。
Three-phase pipeline: analyze functional inventory, apply optimization rules, verify integrity.
Phase Reference Documents (read on-demand):
| Phase | Document | Purpose | |-------|----------|---------| | 1 | phases/01-analysis.md | Extract functional inventory, identify redundancy, validate pseudo-code format | | 2 | phases/02-optimize.md | Apply simplification rules, fix format issues | | 3 | phases/03-check.md | Verify functional integrity, validate format |
.workflow/codebase/ARCHITECTURE.md exists, read for project contextmaestro load --type spec --category coding — load coding conventionsmaestro search "skill design optimization" --json — top 5 entries as prior contextjavascriptconst targetPath = input.trim() const targetFile = targetPath.endsWith('.md') ? targetPath : `${targetPath}/SKILL.md` const originalContent = Read(targetFile) const originalLineCount = originalContent.split('\n').length
javascriptupdate_plan({ todos: [ { content: `Phase 1: Analyzing ${targetFile}`, status: "in_progress", activeForm: "Extracting functional inventory" }, { content: "Phase 2: Optimize", status: "pending" }, { content: "Phase 3: Integrity Check", status: "pending" } ]})
functional (logic, routing, schemas) from descriptive (ASCII art, examples, display templates) — only descriptive blocks may be deleted| Error | Resolution | |-------|------------| | Target file not found | Report error, stop | | Check FAIL (missing functional elements) | Show delta, revert to original, report which elements lost | | Check WARN (descriptive decrease or merge) | Show delta with justification | | Format issues found | Report in check, fix in Phase 2 |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | fail→fail | 11,246 | 4,949 | -56% | 1 | 1 | 0% | 1,628 | 1,579 | -3% | 0 | 0 | — |
case-20 | fail→fail | 2,249 | 16,136 | +617% | 1 | 1 | 0% | 324 | 3,460 | +968% | 0 | 0 | — |
case-06 | fail→pass | 11,363 | 5,152 | -55% | 1 | 1 | 0% | 1,683 | 1,626 | -3% | 0 | 0 | — |
case-01 | fail→fail | 4,688 | 7,556 | +61% | 1 | 1 | 0% | 650 | 1,120 | +72% | 0 | 0 | — |
case-02 | fail→fail | 2,162 | 7,197 | +233% | 1 | 1 | 0% | 305 | 1,163 | +281% | 0 | 0 | — |
case-03 | fail→fail | 8,712 | 5,092 | -42% | 1 | 1 | 0% | 930 | 1,059 | +14% | 0 | 0 | — |
case-04 | fail→fail | 6,479 | 6,661 | +3% | 1 | 1 | 0% | 879 | 1,143 | +30% | 0 | 0 | — |
case-05 | pass→fail | 12,154 | 7,953 | -35% | 1 | 1 | 0% | 2,165 | 1,330 | -39% | 0 | 0 | — |
case-08 | fail→pass | 12,275 | 6,111 | -50% | 1 | 1 | 0% | 1,850 | 1,614 | -13% | 0 | 0 | — |
case-09 | pass→pass | 7,775 | 5,607 | -28% | 1 | 1 | 0% | 1,201 | 1,562 | +30% | 0 | 0 | — |
case-10 | pass→pass | 10,567 | 6,357 | -40% | 1 | 1 | 0% | 1,540 | 1,756 | +14% | 0 | 0 | — |
case-11 | pass→pass | 4,964 | 3,445 | -31% | 1 | 1 | 0% | 816 | 1,382 | +69% | 0 | 0 | — |
case-12 | fail→fail | 5,142 | 4,895 | -5% | 1 | 1 | 0% | 735 | 1,563 | +113% | 0 | 0 | — |
case-13 | fail→pass | 9,995 | 4,678 | -53% | 1 | 1 | 0% | 1,350 | 1,543 | +14% | 0 | 0 | — |
case-14 | pass→pass | 2,696 | 4,997 | +85% | 1 | 1 | 0% | 365 | 1,565 | +329% | 0 | 0 | — |
case-15 | pass→pass | 5,908 | 16,560 | +180% | 1 | 1 | 0% | 915 | 2,495 | +173% | 0 | 0 | — |
case-16 | pass→fail | 15,186 | 6,991 | -54% | 1 | 1 | 0% | 2,055 | 1,878 | -9% | 0 | 0 | — |
case-17 | fail→fail | 14,555 | 1,957 | -87% | 1 | 1 | 0% | 2,226 | 1,132 | -49% | 0 | 0 | — |
case-18 | fail→pass | 8,400 | 2,901 | -65% | 1 | 1 | 0% | 1,315 | 1,269 | -3% | 0 | 0 | — |
case-19 | fail→fail | 10,276 | 5,031 | -51% | 1 | 1 | 0% | 1,572 | 1,545 | -2% | 0 | 0 | — |
case-21 | pass→fail | 21,677 | 12,324 | -43% | 1 | 1 | 0% | 3,897 | 1,112 | -71% | 0 | 0 | — |
case-22 | pass→fail | 13,736 | 5,675 | -59% | 1 | 1 | 0% | 2,705 | 1,018 | -62% | 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 15 counted toward the lift figure. The other 7 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 0 percentage points is the difference between those two pass rates over the 15 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
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.
Other measured skills in the registry, with their headline benchmark lift.