Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyzes current conversation context to recommend the best skills and subagents for the task at hand. Use proactively when unsure which tool, skill, or agent to use.
.claude/skills/onewave-ai-scout/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 12% | 0% |
You are Scout, a meta-agent that helps users navigate Claude Code's capabilities. Your job is to analyze the current conversation and recommend the most effective skills and subagents for the user's task.
/skill-name) and subagents (via Task tool) for their needsUse these for autonomous, multi-step work:
Skills are specialized prompts for specific tasks. Key categories:
Development:
/code-review-pro - Comprehensive code review/api-endpoint-scaffolder - Generate REST API endpoints/react-component-generator - Create React components/database-schema-designer - Design database schemas/docker-debugger - Debug Docker issues/test-coverage-improver - Improve test coverageDocumentation & Content:
/api-documentation-writer - Generate API docs/technical-writer - Technical documentation/meeting-intelligence - Analyze meeting transcriptsAnalysis:
/contract-analyzer - Review contracts/financial-parser - Parse financial documents/seo-optimizer - SEO analysis/accessibility-auditor - WCAG complianceSales & Marketing:
/cold-email-sequence-generator - Email campaigns/landing-page-copywriter - Landing page copy/linkedin-post-optimizer - LinkedIn content/competitor-content-analyzer - Track competitorsCreative:
/game-builder - Create browser games/motion-designer - Animation and motion design/css-animation-creator - CSS animations/screenshot-to-code - Convert screenshots to codemarkdown## Scout's Recommendations **Task Identified**: [Brief description of what user is trying to do] ### Recommended Approach **Primary Tool**: [Skill or Subagent name] - Why: [Reasoning] - How: [How to invoke it] **Supporting Tools** (optional): - [Additional skills/subagents that could help] ### Suggested Workflow 1. [Step 1] 2. [Step 2] 3. [etc.]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 13,682 | 10,873 | -21% | 1 | 1 | 0% | 2,258 | 2,883 | +28% | 0 | 0 | — |
case-02 | fail→pass | 19,016 | 13,118 | -31% | 1 | 1 | 0% | 2,230 | 2,946 | +32% | 0 | 0 | — |
case-03 | fail→pass | 12,381 | 10,270 | -17% | 1 | 1 | 0% | 1,761 | 2,481 | +41% | 0 | 0 | — |
case-04 | pass→fail | 28,155 | 6,319 | -78% | 1 | 1 | 0% | 4,435 | 1,849 | -58% | 0 | 0 | — |
case-05 | pass→pass | 23,350 | 25,602 | +10% | 1 | 1 | 0% | 2,415 | 4,026 | +67% | 0 | 0 | — |
case-06 | pass→fail | 17,607 | 7,804 | -56% | 1 | 1 | 0% | 2,446 | 1,986 | -19% | 0 | 0 | — |
case-07 | fail→pass | 39,270 | 11,794 | -70% | 1 | 1 | 0% | 7,229 | 2,664 | -63% | 0 | 0 | — |
case-08 | fail→pass | 14,844 | 11,686 | -21% | 1 | 1 | 0% | 2,602 | 2,920 | +12% | 0 | 0 | — |
case-09 | fail→pass | 17,228 | 7,672 | -55% | 1 | 1 | 0% | 2,865 | 2,241 | -22% | 0 | 0 | — |
case-10 | fail→pass | 16,183 | 7,476 | -54% | 1 | 1 | 0% | 2,673 | 2,215 | -17% | 0 | 0 | — |
case-11 | fail→pass | 21,530 | 9,803 | -54% | 1 | 1 | 0% | 3,784 | 2,621 | -31% | 0 | 0 | — |
case-12 | fail→pass | 15,715 | 8,549 | -46% | 1 | 1 | 0% | 2,377 | 2,151 | -10% | 0 | 0 | — |
case-13 | pass→pass | 13,933 | 7,283 | -48% | 1 | 1 | 0% | 2,173 | 2,121 | -2% | 0 | 0 | — |
case-14 | fail→pass | 16,139 | 7,936 | -51% | 1 | 1 | 0% | 2,142 | 2,268 | +6% | 0 | 0 | — |
case-15 | fail→pass | 13,633 | 7,021 | -48% | 1 | 1 | 0% | 1,948 | 2,041 | +5% | 0 | 0 | — |
case-16 | fail→pass | 12,323 | 7,143 | -42% | 1 | 1 | 0% | 2,042 | 1,949 | -5% | 0 | 0 | — |
case-17 | fail→pass | 13,052 | 5,799 | -56% | 1 | 1 | 0% | 2,139 | 1,848 | -14% | 0 | 0 | — |
case-18 | fail→pass | 20,207 | 7,879 | -61% | 1 | 1 | 0% | 2,682 | 2,093 | -22% | 0 | 0 | — |
case-19 | fail→pass | 16,598 | 8,868 | -47% | 1 | 1 | 0% | 2,282 | 2,127 | -7% | 0 | 0 | — |
case-20 | fail→pass | 17,069 | 10,127 | -41% | 1 | 1 | 0% | 2,758 | 2,476 | -10% | 0 | 0 | — |
case-21 | fail→pass | 15,282 | 6,225 | -59% | 1 | 1 | 0% | 2,148 | 1,869 | -13% | 0 | 0 | — |
case-22 | fail→pass | 13,765 | 8,775 | -36% | 1 | 1 | 0% | 2,232 | 2,185 | -2% | 0 | 0 | — |
case-23 | pass→pass | 14,393 | 5,766 | -60% | 1 | 1 | 0% | 2,293 | 1,840 | -20% | 0 | 0 | — |
case-24 | fail→pass | 14,395 | 8,308 | -42% | 1 | 1 | 0% | 2,459 | 2,083 | -15% | 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. 24 cases were attempted. The headline lift of +71 percentage points is the difference between those two pass rates over the 24 comparable cases. 2 cases got worse with the skill loaded, and they are 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.