Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create, debug, and iterate on GSD extensions (TypeScript modules that add tools, commands, event hooks, custom UI, and providers to GSD). Use when asked to build an extension, add a tool the LLM can call, register a slash command, hook into GSD events, create custom TUI components, or modify GSD behavior. Triggers on "create extension", "build extension", "add a tool", "register command", "hook into gsd", "custom tool", "gsd plugin", "gsd extension".
.claude/skills/mkurman-create-gsd-extension/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 8% | 0% |
---|---------| | @mariozechner/pi-coding-agent | ExtensionAPI, ExtensionContext, Theme, event types, tool utilities, DynamicBorder, BorderedLoader, CustomEditor, highlightCode | | @sinclair/typebox | Type.Object, Type.String, Type.Number, Type.Optional, Type.Boolean, Type.Array | | @mariozechner/pi-ai | StringEnum (required for string enums), Type re-export | | @mariozechner/pi-tui | Text, Box, Container, Spacer, Markdown, SelectList, Input, matchesKey, Key, truncateToWidth, visibleWidth | | Node.js built-ins | node:fs, node:path, node:child_process, etc. |
</essential_principles>
<routing> Based on user intent, route to the appropriate workflow:
Building a new extension:
workflows/create-extension.mdAdding capabilities to an existing extension:
workflows/add-capability.mdDebugging an extension:
workflows/debug-extension.mdIf user intent is clear from context, skip the question and go directly to the workflow. </routing>
<reference_index> All domain knowledge in references/:
Core architecture: extension-lifecycle.md, events-reference.md API surface: extensionapi-reference.md, extensioncontext-reference.md Capabilities: custom-tools.md, custom-commands.md, custom-ui.md, custom-rendering.md Patterns: state-management.md, system-prompt-modification.md, compaction-session-control.md Infrastructure: model-provider-management.md, remote-execution-overrides.md, packaging-distribution.md, mode-behavior.md Gotchas: key-rules-gotchas.md </reference_index>
<workflows_index> | Workflow | Purpose | |----------|---------| | create-extension.md | Build a new extension from scratch | | add-capability.md | Add tools, commands, hooks, UI to an existing extension | | debug-extension.md | Diagnose and fix extension issues | </workflows_index>
<success_criteria> Extension is complete when:
/reload without errors/command input</success_criteria>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | fail→pass | 10,114 | 3,154 | -69% | 1 | 1 | 0% | 1,744 | 1,231 | -29% | 0 | 0 | — |
case-01 | fail→pass | 15,606 | 18,209 | +17% | 1 | 1 | 0% | 2,994 | 3,885 | +30% | 0 | 0 | — |
case-02 | fail→pass | 15,186 | 9,377 | -38% | 1 | 1 | 0% | 2,828 | 2,327 | -18% | 0 | 0 | — |
case-03 | fail→pass | 15,012 | 8,694 | -42% | 1 | 1 | 0% | 2,635 | 2,301 | -13% | 0 | 0 | — |
case-04 | pass→pass | 9,326 | 9,815 | +5% | 1 | 1 | 0% | 1,671 | 2,375 | +42% | 0 | 0 | — |
case-05 | pass→pass | 9,598 | 14,668 | +53% | 1 | 1 | 0% | 1,804 | 2,480 | +37% | 0 | 0 | — |
case-06 | pass→pass | 14,424 | 11,120 | -23% | 1 | 1 | 0% | 2,635 | 2,504 | -5% | 0 | 0 | — |
case-07 | fail→pass | 7,672 | 3,843 | -50% | 1 | 1 | 0% | 1,252 | 1,351 | +8% | 0 | 0 | — |
case-09 | fail→pass | 9,884 | 3,556 | -64% | 1 | 1 | 0% | 1,429 | 1,281 | -10% | 0 | 0 | — |
case-10 | pass→pass | 9,568 | 1,982 | -79% | 1 | 1 | 0% | 1,393 | 965 | -31% | 0 | 0 | — |
case-11 | fail→pass | 12,586 | 3,411 | -73% | 1 | 1 | 0% | 2,056 | 1,281 | -38% | 0 | 0 | — |
case-12 | fail→pass | 11,295 | 5,357 | -53% | 1 | 1 | 0% | 1,813 | 1,591 | -12% | 0 | 0 | — |
case-13 | fail→fail | 14,733 | 12,297 | -17% | 1 | 1 | 0% | 2,504 | 2,171 | -13% | 0 | 0 | — |
case-14 | fail→pass | 9,118 | 3,728 | -59% | 1 | 1 | 0% | 1,346 | 1,300 | -3% | 0 | 0 | — |
case-15 | pass→fail | 14,067 | 11,545 | -18% | 1 | 1 | 0% | 2,295 | 2,880 | +25% | 0 | 0 | — |
case-16 | pass→pass | 7,037 | 7,697 | +9% | 1 | 1 | 0% | 1,159 | 1,328 | +15% | 0 | 0 | — |
case-17 | fail→pass | 15,612 | 5,469 | -65% | 1 | 1 | 0% | 2,519 | 1,659 | -34% | 0 | 0 | — |
case-18 | fail→pass | 15,033 | 3,084 | -79% | 1 | 1 | 0% | 2,155 | 1,192 | -45% | 0 | 0 | — |
case-19 | fail→pass | 11,226 | 4,120 | -63% | 1 | 1 | 0% | 1,590 | 1,359 | -15% | 0 | 0 | — |
case-20 | fail→pass | 15,284 | 14,569 | -5% | 1 | 1 | 0% | 2,379 | 3,315 | +39% | 0 | 0 | — |
case-21 | fail→pass | 11,213 | 7,518 | -33% | 1 | 1 | 0% | 1,664 | 1,823 | +10% | 0 | 0 | — |
case-22 | pass→pass | 11,910 | 10,820 | -9% | 1 | 1 | 0% | 1,882 | 2,502 | +33% | 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 +59 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.