Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →The 100th skill! Your intelligent guide to all 99 other skills. Recommends the perfect skill for any task, creates skill combinations, and helps you discover capabilities you didn't know you had.
.claude/skills/microck-skill-navigator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 14% | 0% |
The 100th skill! Your intelligent guide to all 99 other skills. Recommends the perfect skill for any task, creates skill combinations, and helps you discover capabilities you didn't know you had.
You are the master skill navigator and orchestrator. You have knowledge of all 99 Claude skills in the library. When a user describes what they want to accomplish, you: 1) Identify which skill(s) can help, 2) Explain how to trigger them, 3) Suggest skill combinations for complex workflows, 4) Provide example prompts, 5) Recommend related skills they might not have considered. You're the ultimate guide to the skill ecosystem. Available skills: Communication (slack-message-formatter, sms-text-optimizer, internal-email-composer, company-announcement-writer, linkedin-post-optimizer), Sales Intelligence (competitor-price-tracker, deal-momentum-analyzer, objection-pattern-detector, sales-call-prep-assistant, prospect-research-compiler), Marketing (webinar-to-content-multiplier, competitor-content-analyzer, seo-keyword-cluster-builder, email-subject-line-optimizer, utm-parameter-generator), Creative (brand-consistency-checker, presentation-design-enhancer, stock-photo-finder, font-pairing-suggester), Expert Simulation (debate-simulator, expert-panel), Content (content-repurposer, game-builder, podcast-studio, flashcard-generator, quiz-maker), Sports (19 skills including game-recap-generator, fantasy-lineup-optimizer, player-comparison-tool, highlight-reel-scripter, scouting-report-builder, sports-betting-analyzer, practice-plan-creator, play-by-play-generator, injury-report-tracker, trash-talk-generator, sports-trivia-builder, post-game-press-conference-simulator, bracket-predictor, training-log-analyzer, team-chemistry-evaluator, sports-meme-creator, game-strategy-simulator, athlete-social-media-manager, sports-podcast-outline-generator, mvp-case-builder), Finance (portfolio-analyzer, budget-optimizer, financial-goal-planner, tax-strategy-optimizer, raise-negotiation-prep), Sales Leadership (sales-forecast-builder, rep-performance-scorecard, quota-setting-calculator, territory-planning-optimizer, sales-comp-plan-designer, deal-review-framework, sales-coaching-plan-generator, ramping-rep-tracker), Meta-Skills (conversation-archaeologist, weak-signal-synthesizer, hypothesis-testing-engine, cross-conversation-project-manager, skill-composer-studio), Advanced (knowledge-base-builder, itinerary-optimizer, workout-program-designer). Help users unlock the full power of their skill library!
markdown# Skill Navigator Output **Generated**: {timestamp} --- ## Results [Your formatted output here] --- ## Recommendations [Actionable next steps]
Trigger Phrases:
Example Request: > "Sample user request here]"
Response Approach:
Remember: Focus on delivering value quickly and clearly!
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | 17,765 | 12,466 | -30% | 1 | 1 | 0% | 2,909 | 3,223 | +11% | 0 | 0 | — |
case-03 | fail→pass | 17,293 | 12,970 | -25% | 1 | 1 | 0% | 2,554 | 3,129 | +23% | 0 | 0 | — |
case-01 | fail→pass | 14,715 | 13,842 | -6% | 1 | 1 | 0% | 2,354 | 3,409 | +45% | 0 | 0 | — |
case-04 | pass→fail | 6,461 | 9,187 | +42% | 1 | 1 | 0% | 978 | 2,308 | +136% | 0 | 0 | — |
case-05 | pass→fail | 7,469 | 9,917 | +33% | 1 | 1 | 0% | 1,342 | 2,528 | +88% | 0 | 0 | — |
case-06 | pass→fail | 8,044 | 10,200 | +27% | 1 | 1 | 0% | 1,302 | 2,517 | +93% | 0 | 0 | — |
case-07 | fail→pass | 19,264 | 13,079 | -32% | 1 | 1 | 0% | 3,163 | 3,072 | -3% | 0 | 0 | — |
case-08 | fail→pass | 17,806 | 14,779 | -17% | 1 | 1 | 0% | 2,718 | 3,095 | +14% | 0 | 0 | — |
case-09 | fail→pass | 17,392 | 14,113 | -19% | 1 | 1 | 0% | 2,789 | 3,098 | +11% | 0 | 0 | — |
case-10 | fail→pass | 13,461 | 13,558 | +1% | 1 | 1 | 0% | 2,056 | 3,167 | +54% | 0 | 0 | — |
case-11 | fail→pass | 14,448 | 10,055 | -30% | 1 | 1 | 0% | 2,187 | 2,858 | +31% | 0 | 0 | — |
case-12 | pass→pass | 15,491 | 9,607 | -38% | 1 | 1 | 0% | 2,329 | 2,276 | -2% | 0 | 0 | — |
case-13 | fail→pass | 17,932 | 14,293 | -20% | 1 | 1 | 0% | 2,666 | 3,205 | +20% | 0 | 0 | — |
case-14 | fail→pass | 16,842 | 14,144 | -16% | 1 | 1 | 0% | 2,576 | 2,977 | +16% | 0 | 0 | — |
case-15 | fail→pass | 15,011 | 13,047 | -13% | 1 | 1 | 0% | 2,593 | 3,150 | +21% | 0 | 0 | — |
case-16 | fail→pass | 13,702 | 11,256 | -18% | 1 | 1 | 0% | 1,920 | 2,749 | +43% | 0 | 0 | — |
case-17 | pass→pass | 9,363 | 10,905 | +16% | 1 | 1 | 0% | 1,394 | 2,590 | +86% | 0 | 0 | — |
case-18 | fail→pass | 12,168 | 10,926 | -10% | 1 | 1 | 0% | 1,728 | 2,620 | +52% | 0 | 0 | — |
case-19 | pass→pass | 9,884 | 8,185 | -17% | 1 | 1 | 0% | 1,496 | 2,221 | +48% | 0 | 0 | — |
case-20 | fail→pass | 13,102 | 10,911 | -17% | 1 | 1 | 0% | 2,035 | 2,576 | +27% | 0 | 0 | — |
case-21 | pass→pass | 12,465 | 11,569 | -7% | 1 | 1 | 0% | 1,900 | 2,840 | +49% | 0 | 0 | — |
case-22 | fail→pass | 8,465 | 10,239 | +21% | 1 | 1 | 0% | 1,361 | 2,487 | +83% | 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 +55 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 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.