Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Verify if a specific action is possible and diagnose any blockers.
.claude/skills/majiayu000-capability/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-22 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-13 | ✓→✗ | ▼ Worse | -45% | 0% |
name: capability description: Check if a specific action is possible and what might be blocking it. Use when asking if you can do something, checking permissions, verifying a capability exists, or troubleshooting why something isn't working. Trigger words: can I, capability, able to, permission, possible, how do I. context: fork allowed-tools:
Verify if a specific action is possible and diagnose any blockers.
Full capabilities documentation: ~/.claude-mind/capabilities/inventory.md
bash# Read full inventory (comprehensive reference) cat ~/.claude-mind/capabilities/inventory.md # Search for specific capability grep -ni "search term" ~/.claude-mind/capabilities/inventory.md # List all sections grep "^## " ~/.claude-mind/capabilities/inventory.md
| Capability | Method | Requires | |------------|--------|----------| | Send iMessage | AppleScript via Samara | Samara running, Automation permission | | Send image | send-image script | Pictures folder workaround | | Read calendar | AppleScript | Calendar permission | | Write calendar | AppleScript | Calendar permission | | Read contacts | AppleScript | Contacts permission | | Read/write notes | AppleScript | Notes permission | | Send email | AppleScript | Mail permission | | Post to Bluesky | bluesky-post script | Credentials in config | | Browse web | Playwright MCP | MCP server running | | Take screenshot | screenshot script | Screen recording permission | | Read Messages DB | Direct file access | Full Disk Access | | Run shell commands | Bash | Always available | | Read/write files | Direct | Always available |
bashpgrep -q Samara && echo "Samara: OK" || echo "Samara: Not running" ~/.claude-mind/bin/message "test" --dry-run 2>/dev/null
bashosascript -e 'tell application "Calendar" to get name of calendars' 2>&1
bashosascript -e 'tell application "Contacts" to get name of first person' 2>&1
bashosascript -e 'tell application "Notes" to get name of first note' 2>&1
bashosascript -e 'tell application "Mail" to get name of first account' 2>&1
bashgrep -q "bluesky" ~/.claude-mind/config.json && echo "Bluesky: Configured" || echo "Bluesky: Not configured"
bashls ~/Library/Messages/chat.db 2>/dev/null && echo "FDA: OK" || echo "FDA: Missing"
bashlog show --predicate 'process == "osascript"' --last 2m
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→fail | 3,706 | 5,805 | +57% | 1 | 1 | 0% | 468 | 1,090 | +133% | 0 | 0 | — |
case-06 | fail→fail | 2,778 | 4,955 | +78% | 1 | 1 | 0% | 329 | 1,091 | +232% | 0 | 0 | — |
case-01 | fail→fail | 11,239 | 9,032 | -20% | 1 | 1 | 0% | 1,780 | 1,316 | -26% | 0 | 0 | — |
case-02 | fail→fail | 9,951 | 5,828 | -41% | 1 | 1 | 0% | 553 | 1,123 | +103% | 0 | 0 | — |
case-03 | fail→fail | 4,858 | 5,313 | +9% | 1 | 1 | 0% | 697 | 1,112 | +60% | 0 | 0 | — |
case-04 | fail→fail | 9,091 | 5,177 | -43% | 1 | 1 | 0% | 1,268 | 1,132 | -11% | 0 | 0 | — |
case-07 | fail→fail | 4,190 | 4,687 | +12% | 1 | 1 | 0% | 486 | 1,022 | +110% | 0 | 0 | — |
case-08 | fail→fail | 6,764 | 5,015 | -26% | 1 | 1 | 0% | 763 | 1,057 | +39% | 0 | 0 | — |
case-09 | fail→fail | 3,490 | 4,836 | +39% | 1 | 1 | 0% | 448 | 1,027 | +129% | 0 | 0 | — |
case-10 | fail→pass | 11,686 | 4,627 | -60% | 1 | 1 | 0% | 1,929 | 1,421 | -26% | 0 | 0 | — |
case-11 | pass→pass | 6,793 | 3,372 | -50% | 1 | 1 | 0% | 992 | 1,276 | +29% | 0 | 0 | — |
case-12 | pass→pass | 5,971 | 7,955 | +33% | 1 | 1 | 0% | 841 | 1,256 | +49% | 0 | 0 | — |
case-13 | pass→fail | 12,522 | 5,710 | -54% | 1 | 1 | 0% | 1,922 | 1,062 | -45% | 0 | 0 | — |
case-14 | fail→fail | 9,043 | 4,236 | -53% | 1 | 1 | 0% | 1,271 | 985 | -23% | 0 | 0 | — |
case-15 | fail→fail | 12,670 | 5,491 | -57% | 1 | 1 | 0% | 1,904 | 1,020 | -46% | 0 | 0 | — |
case-16 | fail→pass | 12,054 | 3,960 | -67% | 1 | 1 | 0% | 1,755 | 1,371 | -22% | 0 | 0 | — |
case-17 | pass→fail | 9,861 | 27,826 | +182% | 1 | 1 | 0% | 1,569 | 1,043 | -34% | 0 | 0 | — |
case-18 | fail→pass | 11,147 | 6,541 | -41% | 1 | 1 | 0% | 1,794 | 1,835 | +2% | 0 | 0 | — |
case-19 | pass→fail | 4,531 | 5,273 | +16% | 1 | 1 | 0% | 613 | 1,110 | +81% | 0 | 0 | — |
case-20 | fail→fail | 2,677 | 5,268 | +97% | 1 | 1 | 0% | 330 | 1,100 | +233% | 0 | 0 | — |
case-21 | fail→fail | 5,805 | 5,967 | +3% | 1 | 1 | 0% | 763 | 1,096 | +44% | 0 | 0 | — |
case-22 | fail→pass | 11,901 | 3,344 | -72% | 1 | 1 | 0% | 1,802 | 1,416 | -21% | 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, and 6 counted toward the lift figure. The other 16 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 +5 percentage points is the difference between those two pass rates over the 6 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.