Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Display knowledge base status and recent learnings
.claude/skills/aiskillstore-knowledge/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 3% | 0% |
Display the current state of the project's knowledge base and recent learnings.
Shows:
knowledge/state.json for learning mode statusknowledge/cache/classifications.mdknowledge/learnings/patterns.mdknowledge/learnings/quirks.mdknowledge/learnings/decisions.md╔═══════════════════════════════════════════════════╗
║ Project Knowledge Base ║
╚═══════════════════════════════════════════════════╝
📚 Learning Status
───────────────────────────────────────────────────
Mode: ON (since 2026-01-08 14:00)
Last Extraction: 5 minutes ago
Extractions This Session: 3
📊 Knowledge Statistics
───────────────────────────────────────────────────
Cache:
- Classification entries: 23
Learnings:
- Patterns: 8 entries
- Quirks: 3 entries
- Decisions: 5 entries
- Total: 16 insights
📝 Recent Learnings
───────────────────────────────────────────────────
[Pattern] "Use async/await for API calls in this codebase"
Discovered: 2026-01-08 | Confidence: high
[Quirk] "Auth module uses non-standard token format"
Discovered: 2026-01-07 | Confidence: high
[Decision] "Chose Redis over in-memory cache for session storage"
Made: 2026-01-06 | Confidence: high
💡 Commands
───────────────────────────────────────────────────
/learn - Extract insights now
/learn-on - Enable continuous learning
/learn-off - Disable continuous learning╔═══════════════════════════════════════════════════╗
║ Project Knowledge Base ║
╚═══════════════════════════════════════════════════╝
📚 Learning Status
───────────────────────────────────────────────────
Mode: OFF
No extractions yet
📊 Knowledge Statistics
───────────────────────────────────────────────────
Knowledge base is empty.
💡 Get Started
───────────────────────────────────────────────────
Use /learn to extract insights from your current session.
Use /learn-on to enable continuous learning.
The knowledge base will grow as you work, capturing:
- Patterns that work well in this project
- Quirks and gotchas to remember
- Decisions and their rationaleknowledge/state.json## Pattern:, ## Quirk:, ## Decision: headers)entry_count field or by counting ## headers| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,768 | 10,706 | +125% | 1 | 1 | 0% | 783 | 2,709 | +246% | 0 | 0 | — |
case-02 | fail→fail | 18,837 | 4,309 | -77% | 1 | 1 | 0% | 2,564 | 962 | -62% | 0 | 0 | — |
case-03 | fail→fail | 4,276 | 9,468 | +121% | 1 | 1 | 0% | 574 | 1,633 | +184% | 0 | 0 | — |
case-04 | pass→pass | 8,047 | 3,604 | -55% | 1 | 1 | 0% | 1,265 | 1,362 | +8% | 0 | 0 | — |
case-05 | fail→pass | 15,247 | 2,805 | -82% | 1 | 1 | 0% | 2,442 | 1,232 | -50% | 0 | 0 | — |
case-06 | pass→pass | 10,296 | 4,869 | -53% | 1 | 1 | 0% | 1,713 | 1,542 | -10% | 0 | 0 | — |
case-07 | fail→pass | 12,433 | 4,273 | -66% | 1 | 1 | 0% | 1,883 | 1,417 | -25% | 0 | 0 | — |
case-08 | pass→fail | 6,819 | 6,791 | -0% | 1 | 1 | 0% | 1,061 | 1,095 | +3% | 0 | 0 | — |
case-09 | pass→pass | 14,626 | 2,682 | -82% | 1 | 1 | 0% | 2,474 | 1,142 | -54% | 0 | 0 | — |
case-10 | pass→pass | 8,159 | 5,153 | -37% | 1 | 1 | 0% | 1,368 | 1,618 | +18% | 0 | 0 | — |
case-11 | fail→pass | 18,963 | 2,306 | -88% | 1 | 1 | 0% | 1,832 | 1,130 | -38% | 0 | 0 | — |
case-12 | fail→pass | 10,463 | 3,483 | -67% | 1 | 1 | 0% | 1,663 | 1,155 | -31% | 0 | 0 | — |
case-13 | fail→pass | 7,966 | 2,509 | -69% | 1 | 1 | 0% | 1,160 | 1,196 | +3% | 0 | 0 | — |
case-14 | fail→pass | 7,542 | 4,566 | -39% | 1 | 1 | 0% | 1,268 | 1,530 | +21% | 0 | 0 | — |
case-15 | fail→pass | 10,841 | 5,054 | -53% | 1 | 1 | 0% | 1,761 | 1,568 | -11% | 0 | 0 | — |
case-16 | pass→pass | 8,351 | 4,172 | -50% | 1 | 1 | 0% | 1,315 | 1,500 | +14% | 0 | 0 | — |
case-17 | fail→pass | 12,533 | 8,561 | -32% | 1 | 1 | 0% | 2,013 | 2,244 | +11% | 0 | 0 | — |
case-18 | fail→pass | 13,259 | 4,311 | -67% | 1 | 1 | 0% | 1,905 | 1,428 | -25% | 0 | 0 | — |
case-19 | pass→pass | 8,653 | 5,276 | -39% | 1 | 1 | 0% | 1,487 | 1,690 | +14% | 0 | 0 | — |
case-20 | fail→pass | 9,350 | 7,988 | -15% | 1 | 1 | 0% | 1,358 | 1,525 | +12% | 0 | 0 | — |
case-21 | fail→fail | 9,089 | 12,169 | +34% | 1 | 1 | 0% | 1,368 | 2,269 | +66% | 0 | 0 | — |
case-22 | fail→fail | 3,828 | 8,456 | +121% | 1 | 1 | 0% | 667 | 1,350 | +102% | 0 | 0 | — |
case-23 | fail→fail | 6,001 | 5,371 | -10% | 1 | 1 | 0% | 908 | 1,026 | +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. 23 cases were attempted, and 18 counted toward the lift figure. The other 5 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 +39 percentage points is the difference between those two pass rates over the 18 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.