Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when starting a new project, adding a new agent to an existing system, or setting up workflow infrastructure from scratch.
.claude/skills/sharpdeveye-onboard-agent/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -33% | 0% |
Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first.
Bootstrap a new agent workflow from scratch, or add a new agent to an existing system.
markdown## Workflow Conventions ### Prompt Format - Delimiter style: [XML tags / markdown headers / triple-dash] - Section order: [System → Context → Instructions → Input] - Output format: [JSON with schema / markdown template] ### Tool Conventions - Naming: [verb_noun / noun.verb / camelCase] - Description template: [What → When → When Not → Returns] - Error format: [{ code, message, details }] ### Logging - Format: [JSON structured] - Required fields: [workflow_id, step, timestamp, level] ### File Structure - Prompts: [prompts/workflow-name/v1.md] - Tools: [tools/tool-name.{ext}] - Config: [config/environment.yaml] - Tests: [tests/workflow-name/]
textproject/ ├── prompts/ # System prompts, versioned ├── tools/ # Tool definitions ├── config/ # Environment-specific configuration ├── tests/ # Golden test sets and evaluation suites ├── logs/ # Runtime logs (gitignored) └── .maestro.md # Workflow context
After onboarding, run /diagnose for a baseline health check, then /fortify to add production-grade error handling.
NEVER:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→pass | 19,657 | 20,150 | +3% | 1 | 1 | 0% | 4,355 | 4,756 | +9% | 0 | 0 | — |
case-02 | pass→pass | 13,119 | 11,597 | -12% | 1 | 1 | 0% | 2,421 | 2,578 | +6% | 0 | 0 | — |
case-03 | pass→pass | 22,289 | 26,028 | +17% | 1 | 1 | 0% | 3,995 | 4,896 | +23% | 0 | 0 | — |
case-01 | pass→pass | 12,385 | 15,586 | +26% | 1 | 1 | 0% | 2,235 | 3,189 | +43% | 0 | 0 | — |
case-05 | fail→fail | 21,380 | 18,804 | -12% | 1 | 1 | 0% | 4,358 | 4,263 | -2% | 0 | 0 | — |
case-06 | fail→pass | 32,419 | 18,008 | -44% | 1 | 1 | 0% | 6,190 | 4,045 | -35% | 0 | 0 | — |
case-07 | pass→pass | 17,369 | 13,443 | -23% | 1 | 1 | 0% | 2,803 | 2,653 | -5% | 0 | 0 | — |
case-08 | pass→pass | 14,366 | 8,904 | -38% | 1 | 1 | 0% | 2,436 | 2,044 | -16% | 0 | 0 | — |
case-09 | fail→pass | 14,241 | 12,191 | -14% | 1 | 1 | 0% | 2,508 | 2,724 | +9% | 0 | 0 | — |
case-10 | fail→pass | 14,855 | 2,968 | -80% | 1 | 1 | 0% | 2,325 | 937 | -60% | 0 | 0 | — |
case-11 | fail→pass | 8,377 | 2,696 | -68% | 1 | 1 | 0% | 1,311 | 879 | -33% | 0 | 0 | — |
case-12 | fail→pass | 11,408 | 8,335 | -27% | 1 | 1 | 0% | 1,996 | 1,872 | -6% | 0 | 0 | — |
case-13 | pass→pass | 11,394 | 3,785 | -67% | 1 | 1 | 0% | 1,798 | 1,222 | -32% | 0 | 0 | — |
case-14 | pass→pass | 8,799 | 3,831 | -56% | 1 | 1 | 0% | 1,339 | 1,178 | -12% | 0 | 0 | — |
case-15 | fail→pass | 25,413 | 8,234 | -68% | 1 | 1 | 0% | 2,094 | 1,950 | -7% | 0 | 0 | — |
case-16 | fail→pass | 11,324 | 6,416 | -43% | 1 | 1 | 0% | 1,752 | 1,525 | -13% | 0 | 0 | — |
case-17 | fail→pass | 13,420 | 4,908 | -63% | 1 | 1 | 0% | 2,291 | 1,314 | -43% | 0 | 0 | — |
case-18 | pass→pass | 11,097 | 2,863 | -74% | 1 | 1 | 0% | 1,750 | 1,035 | -41% | 0 | 0 | — |
case-19 | fail→pass | 7,754 | 3,570 | -54% | 1 | 1 | 0% | 1,263 | 1,023 | -19% | 0 | 0 | — |
case-20 | fail→pass | 10,641 | 2,500 | -77% | 1 | 1 | 0% | 1,665 | 919 | -45% | 0 | 0 | — |
case-21 | pass→pass | 6,145 | 6,430 | +5% | 1 | 1 | 0% | 921 | 1,602 | +74% | 0 | 0 | — |
case-22 | pass→pass | 9,107 | 7,162 | -21% | 1 | 1 | 0% | 1,440 | 1,670 | +16% | 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 +50 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.