Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Fast file editing via Morph Apply API (10,500 tokens/sec, 98% accuracy)
.claude/skills/morph-apply/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 177% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 307% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -33% | 0% |
Fast, AI-powered file editing using the Morph Apply API. Edit files without reading them first. Processes at 10,500 tokens/sec with 98% accuracy.
Use // ... existing code ... (or language-appropriate comments) to mark where edits go:
python# ... existing code ... try: result = process() except Exception as e: log.error(e) # ... existing code ...
The API intelligently places your edit in the right location.
bashuv run python -m runtime.harness scripts/mcp/morph_apply.py \ --file "src/auth.py" \ --instruction "Add error handling to login function" \ --code_edit "# ... existing code ... try: user = authenticate(credentials) except AuthError as e: log.error(f'Auth failed: {e}') raise # ... existing code ..."
bashuv run python -m runtime.harness scripts/mcp/morph_apply.py \ --file "src/api.py" \ --instruction "Add debug logging" \ --code_edit "# ... existing code ... logger.debug(f'Processing request: {request.id}') # ... existing code ..."
bashuv run python -m runtime.harness scripts/mcp/morph_apply.py \ --file "src/types.ts" \ --instruction "Add user validation" \ --code_edit "// ... existing code ... if (!user) throw new Error('User not found'); if (!user.isActive) throw new Error('User inactive'); // ... existing code ..."
| Parameter | Description | |-----------|-------------| | --file | File path to edit (required) | | --instruction | Human description of the change (required) | | --code_edit | Code snippet with markers showing where to place edit (required) |
| Tool | Best For | |------|----------| | morph-apply | Fast edits, don't need to read file first, large files, batch edits | | Claude Edit | Small precise edits when file is already in context |
Use morph-apply when:
Use Claude Edit when:
Requires morph server in mcp_config.json with MORPH_API_KEY.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | pass→pass | 8,009 | 3,190 | -60% | 1 | 1 | 0% | 1,408 | 1,327 | -6% | 0 | 0 | — |
case-01 | fail→pass | 6,392 | 1,833 | -71% | 1 | 1 | 0% | 402 | 1,115 | +177% | 0 | 0 | — |
case-21 | fail→pass | 5,596 | 2,646 | -53% | 1 | 1 | 0% | 816 | 1,339 | +64% | 0 | 0 | — |
case-02 | fail→pass | 10,208 | 6,288 | -38% | 1 | 1 | 0% | 1,878 | 1,198 | -36% | 0 | 0 | — |
case-03 | fail→pass | 5,364 | 1,875 | -65% | 1 | 1 | 0% | 269 | 1,094 | +307% | 0 | 0 | — |
case-04 | pass→pass | 4,836 | 3,505 | -28% | 1 | 1 | 0% | 758 | 1,364 | +80% | 0 | 0 | — |
case-05 | fail→pass | 10,296 | 2,369 | -77% | 1 | 1 | 0% | 1,720 | 1,157 | -33% | 0 | 0 | — |
case-10 | fail→pass | 4,602 | 4,821 | +5% | 1 | 1 | 0% | 751 | 1,589 | +112% | 0 | 0 | — |
case-06 | pass→pass | 4,487 | 1,237 | -72% | 1 | 1 | 0% | 826 | 929 | +12% | 0 | 0 | — |
case-07 | pass→pass | 14,928 | 4,560 | -69% | 1 | 1 | 0% | 1,300 | 1,707 | +31% | 0 | 0 | — |
case-08 | fail→pass | 5,845 | 2,800 | -52% | 1 | 1 | 0% | 1,213 | 1,333 | +10% | 0 | 0 | — |
case-09 | fail→pass | 10,678 | 2,599 | -76% | 1 | 1 | 0% | 1,857 | 1,239 | -33% | 0 | 0 | — |
case-12 | fail→pass | 7,849 | 3,205 | -59% | 1 | 1 | 0% | 1,442 | 1,361 | -6% | 0 | 0 | — |
case-13 | fail→pass | 5,941 | 2,174 | -63% | 1 | 1 | 0% | 1,010 | 1,201 | +19% | 0 | 0 | — |
case-14 | fail→pass | 8,450 | 1,553 | -82% | 1 | 1 | 0% | 1,349 | 1,048 | -22% | 0 | 0 | — |
case-15 | pass→pass | 6,507 | 1,858 | -71% | 1 | 1 | 0% | 1,155 | 1,131 | -2% | 0 | 0 | — |
case-16 | pass→pass | 7,234 | 1,123 | -84% | 1 | 1 | 0% | 1,161 | 908 | -22% | 0 | 0 | — |
case-17 | fail→pass | 8,430 | 1,214 | -86% | 1 | 1 | 0% | 1,408 | 931 | -34% | 0 | 0 | — |
case-18 | fail→fail | 12,284 | 6,209 | -49% | 1 | 1 | 0% | 1,892 | 1,697 | -10% | 0 | 0 | — |
case-19 | fail→pass | 9,227 | 2,903 | -69% | 1 | 1 | 0% | 1,712 | 1,383 | -19% | 0 | 0 | — |
case-20 | fail→pass | 10,351 | 2,217 | -79% | 1 | 1 | 0% | 2,051 | 1,117 | -46% | 0 | 0 | — |
case-22 | fail→fail | 5,015 | 2,182 | -56% | 1 | 1 | 0% | 846 | 1,133 | +34% | 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 20 counted toward the lift figure. The other 2 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 +64 percentage points is the difference between those two pass rates over the 20 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 | 7/30/2026 | +86% |
Other measured skills in the registry, with their headline benchmark lift.