Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Connect an MCP-capable coding agent to OpenChatCut and edit local video projects. Use when the user asks to install, connect, or set up OpenChatCut; inspect or edit an OpenChatCut project; work with its timeline, transcript, captions, media, generation, motion graphics, audio, color, or export tools; or recover from an OpenChatCut MCP error.
.claude/skills/0xsline-openchatcut/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -65% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -43% | 0% |
OpenChatCut is a local-first, agent-native video editor. This skill is the single external entry point; specialized editing guidance remains inside the running editor and is loaded on demand with load_skill.
references/getting-started.md.
references/editing-workflow.md.read references/known-errors.md.
http://localhost:5199/api/external-mcp/mcp.
openchatcut_status, then list_projects. Select a project only whenthe user names it or the current context identifies it.
load_skill before specialized work. It is read-only and requiresneither begin_edit_session nor editSessionId; available names and support files come from the live MCP tool description. With progressive exposure enabled, this call reveals the skill's referenced tools and emits tools/list_changed; refresh the list before continuing.
begin_edit_session. Keep itseditSessionId and pass it to every draft-safe editor tool.
approvalMode: "manual" unless the user explicitly asks for unattendedapplication. In manual mode, the user approves the complete proposal in OpenChatCut. In auto mode, review_edit_session applies the complete draft.
review_edit_session. Report success only afterget_edit_session returns applied.
2026-08-10.1
The OpenChatCut MCP server announces its required skill baseline. If the server baseline is newer, run:
bashnpx skills update openchatcut
Fallback command:
bashnpx skills add 0xsline/OpenChatCut --skill openchatcut
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 8,252 | 4,751 | -42% | 1 | 1 | 0% | 1,227 | 745 | -39% | 0 | 0 | — |
case-02 | fail→fail | 10,221 | 14,402 | +41% | 1 | 1 | 0% | 1,674 | 2,326 | +39% | 0 | 0 | — |
case-03 | fail→fail | 5,933 | 12,138 | +105% | 1 | 1 | 0% | 946 | 2,191 | +132% | 0 | 0 | — |
case-04 | fail→pass | 6,615 | 2,479 | -63% | 1 | 1 | 0% | 1,044 | 931 | -11% | 0 | 0 | — |
case-05 | pass→pass | 8,500 | 1,608 | -81% | 1 | 1 | 0% | 1,210 | 719 | -41% | 0 | 0 | — |
case-06 | pass→pass | 9,387 | 2,504 | -73% | 1 | 1 | 0% | 1,409 | 866 | -39% | 0 | 0 | — |
case-07 | fail→pass | 10,174 | 3,845 | -62% | 1 | 1 | 0% | 1,631 | 1,137 | -30% | 0 | 0 | — |
case-08 | fail→pass | 9,709 | 1,613 | -83% | 1 | 1 | 0% | 1,960 | 688 | -65% | 0 | 0 | — |
case-09 | fail→pass | 9,224 | 1,321 | -86% | 1 | 1 | 0% | 1,543 | 689 | -55% | 0 | 0 | — |
case-10 | fail→pass | 7,509 | 1,291 | -83% | 1 | 1 | 0% | 1,181 | 672 | -43% | 0 | 0 | — |
case-11 | fail→pass | 9,629 | 1,591 | -83% | 1 | 1 | 0% | 1,679 | 670 | -60% | 0 | 0 | — |
case-12 | fail→pass | 10,691 | 1,449 | -86% | 1 | 1 | 0% | 1,808 | 693 | -62% | 0 | 0 | — |
case-13 | pass→pass | 6,062 | 1,875 | -69% | 1 | 1 | 0% | 1,053 | 785 | -25% | 0 | 0 | — |
case-14 | fail→pass | 3,985 | 2,102 | -47% | 1 | 1 | 0% | 698 | 784 | +12% | 0 | 0 | — |
case-15 | pass→pass | 2,114 | 2,469 | +17% | 1 | 1 | 0% | 335 | 789 | +136% | 0 | 0 | — |
case-16 | pass→pass | 8,682 | 2,310 | -73% | 1 | 1 | 0% | 1,297 | 751 | -42% | 0 | 0 | — |
case-17 | fail→pass | 8,010 | 1,740 | -78% | 1 | 1 | 0% | 1,294 | 773 | -40% | 0 | 0 | — |
case-18 | pass→pass | 7,348 | 1,860 | -75% | 1 | 1 | 0% | 1,172 | 721 | -38% | 0 | 0 | — |
case-19 | fail→pass | 5,124 | 1,603 | -69% | 1 | 1 | 0% | 720 | 703 | -2% | 0 | 0 | — |
case-20 | pass→pass | 3,616 | 2,914 | -19% | 1 | 1 | 0% | 681 | 1,036 | +52% | 0 | 0 | — |
case-21 | pass→pass | 2,945 | 3,049 | +4% | 1 | 1 | 0% | 431 | 968 | +125% | 0 | 0 | — |
case-22 | pass→pass | 16,259 | 14,786 | -9% | 1 | 1 | 0% | 2,611 | 2,956 | +13% | 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 21 counted toward the lift figure. The other 1 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 +45 percentage points is the difference between those two pass rates over the 21 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.