Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.
.claude/skills/kunanonj-cursor-migrate-to-skills/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -30% | 0% |
Convert Cursor rules ("Applied intelligently") and slash commands to Agent Skills format.
CRITICAL: Preserve the exact body content. Do not modify, reformat, or "improve" it - copy verbatim.
| Level | Source | Destination | |-------|--------|-------------| | Project | {workspaceFolder}/**/.cursor/rules/*.mdc, {workspaceFolder}/.cursor/commands/*.md | .cursor/skills/ | | User | ~/.cursor/commands/*.md | ~/.cursor/skills/ |
Notes:
Rules: Migrate if rule has a description but NO globs and NO alwaysApply: true.
Commands: Migrate all - they're plain markdown without frontmatter.
markdown# Before: .cursor/rules/my-rule.mdc --- description: What this rule does globs: alwaysApply: false --- # Title Body content...
markdown# After: .cursor/skills/my-rule/SKILL.md --- name: my-rule description: What this rule does --- # Title Body content...
Changes: Add name field, remove globs/alwaysApply, keep body exactly.
markdown# Before: .cursor/commands/commit.md # Commit current work Instructions here...
markdown# After: .cursor/skills/commit/SKILL.md --- name: commit description: Commit current work with standardized message format disable-model-invocation: true --- # Commit current work Instructions here...
Changes: Add frontmatter with name (from filename), description (infer from content), and disable-model-invocation: true, keep body exactly.
name must be lowercase with hyphens onlydescription is critical for skill discoverydescription, no globs, no alwaysApply: true). Commands are always migrated.CRITICAL: Copy the body content character-for-character. Do not reformat, fix typos, or "improve" anything.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | 13,217 | 6,187 | -53% | 1 | 1 | 0% | 2,591 | 1,383 | -47% | 0 | 0 | — |
case-09 | pass→pass | 10,077 | 1,643 | -84% | 1 | 1 | 0% | 1,881 | 974 | -48% | 0 | 0 | — |
case-02 | fail→fail | 3,318 | 4,710 | +42% | 1 | 1 | 0% | 473 | 1,150 | +143% | 0 | 0 | — |
case-01 | fail→fail | 1,506 | 4,230 | +181% | 1 | 1 | 0% | 272 | 1,459 | +436% | 0 | 0 | — |
case-04 | pass→pass | 9,146 | 2,800 | -69% | 1 | 1 | 0% | 1,703 | 1,188 | -30% | 0 | 0 | — |
case-05 | pass→pass | 9,956 | 2,762 | -72% | 1 | 1 | 0% | 1,754 | 1,182 | -33% | 0 | 0 | — |
case-06 | fail→pass | 10,013 | 2,169 | -78% | 1 | 1 | 0% | 1,833 | 971 | -47% | 0 | 0 | — |
case-07 | fail→pass | 8,932 | 2,546 | -71% | 1 | 1 | 0% | 1,689 | 1,170 | -31% | 0 | 0 | — |
case-08 | pass→pass | 7,587 | 2,484 | -67% | 1 | 1 | 0% | 1,348 | 1,188 | -12% | 0 | 0 | — |
case-10 | pass→pass | 9,086 | 1,712 | -81% | 1 | 1 | 0% | 1,684 | 997 | -41% | 0 | 0 | — |
case-11 | pass→pass | 8,662 | 1,892 | -78% | 1 | 1 | 0% | 1,342 | 1,028 | -23% | 0 | 0 | — |
case-12 | fail→pass | 8,474 | 1,570 | -81% | 1 | 1 | 0% | 1,605 | 930 | -42% | 0 | 0 | — |
case-13 | fail→pass | 8,419 | 1,709 | -80% | 1 | 1 | 0% | 1,467 | 915 | -38% | 0 | 0 | — |
case-14 | fail→pass | 7,624 | 1,877 | -75% | 1 | 1 | 0% | 1,421 | 992 | -30% | 0 | 0 | — |
case-15 | pass→pass | 6,145 | 1,509 | -75% | 1 | 1 | 0% | 977 | 924 | -5% | 0 | 0 | — |
case-16 | pass→pass | 8,391 | 1,842 | -78% | 1 | 1 | 0% | 1,364 | 1,017 | -25% | 0 | 0 | — |
case-17 | pass→pass | 6,301 | 2,195 | -65% | 1 | 1 | 0% | 1,152 | 1,036 | -10% | 0 | 0 | — |
case-18 | fail→pass | 7,341 | 1,875 | -74% | 1 | 1 | 0% | 1,209 | 1,013 | -16% | 0 | 0 | — |
case-19 | pass→pass | 11,400 | 2,714 | -76% | 1 | 1 | 0% | 2,022 | 1,198 | -41% | 0 | 0 | — |
case-20 | fail→pass | 8,500 | 1,648 | -81% | 1 | 1 | 0% | 1,593 | 978 | -39% | 0 | 0 | — |
case-21 | fail→pass | 9,740 | 2,299 | -76% | 1 | 1 | 0% | 1,786 | 1,045 | -41% | 0 | 0 | — |
case-22 | fail→pass | 9,490 | 2,570 | -73% | 1 | 1 | 0% | 1,689 | 1,144 | -32% | 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. The headline lift of +41 percentage points is the difference between those two pass rates over the 22 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.
Other measured skills in the registry, with their headline benchmark lift.