Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Root index of x-cmd skill0 sub-skills. Defines the OKR-style agent workflow (goal → rule-verified results → execute), skill discovery, and agent tooling preferences. Style: principle-first, concise, delegate specifics to authoritative external sources.
.claude/skills/x-cmd-skill0/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -64% | 0% |
The LLM absorbs common sense continuously; skill0's job is to encode conventions and source pointers, then thin over time as the LLM catches up. Verify via first-party data (x rfc, x cve, x wkp, agent-browser) and current best practice (x skill, x clawhub), then reconstruct with formal logic instead of memorization.
Buckets: core/, data/, it/, life/. Path: <bucket>/<slug>/SKILL.md. The machine-readable catalog (name + description) is at index.tsv. One doc used to live here as a manager/lifestyle interaction guide; it was moved to .x-cmd/todo/ai-human-interaction-guide.md as it is not part of the skill0 graph.
Objective: What to achieve Key Results: How to verify Verification: x rule check/audit
x skill — x-cmd's curated, human-vetted skill catalog.x clawhub — global skill registry. Caution: free upload, MUST run x clawhub skill moderate <name> for the auto-generated safety report.x roadmap, x cron, x agent job, x ondb, x wiki / x llmwiki — project management, scheduling, background agents, ontology, wiki. Run x [mod] --help.See skill0-writer for the conventions.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 8,268 | 5,043 | -39% | 1 | 1 | 0% | 1,077 | 1,050 | -3% | 0 | 0 | — |
case-02 | fail→pass | 9,436 | 5,481 | -42% | 1 | 1 | 0% | 1,560 | 1,404 | -10% | 0 | 0 | — |
case-03 | fail→pass | 9,615 | 7,759 | -19% | 1 | 1 | 0% | 1,460 | 1,463 | +0% | 0 | 0 | — |
case-04 | pass→pass | 7,952 | 6,461 | -19% | 1 | 1 | 0% | 1,402 | 1,447 | +3% | 0 | 0 | — |
case-05 | pass→pass | 21,420 | 16,868 | -21% | 1 | 1 | 0% | 3,122 | 3,160 | +1% | 0 | 0 | — |
case-06 | pass→pass | 12,158 | 11,081 | -9% | 1 | 1 | 0% | 2,136 | 2,508 | +17% | 0 | 0 | — |
case-07 | pass→pass | 12,691 | 7,006 | -45% | 1 | 1 | 0% | 1,981 | 1,626 | -18% | 0 | 0 | — |
case-08 | pass→pass | 4,440 | 3,223 | -27% | 1 | 1 | 0% | 665 | 841 | +26% | 0 | 0 | — |
case-09 | pass→pass | 6,692 | 14,061 | +110% | 1 | 1 | 0% | 1,096 | 806 | -26% | 0 | 0 | — |
case-10 | fail→pass | 6,987 | 4,380 | -37% | 1 | 1 | 0% | 1,010 | 823 | -19% | 0 | 0 | — |
case-11 | fail→pass | 13,783 | 2,532 | -82% | 1 | 1 | 0% | 1,983 | 719 | -64% | 0 | 0 | — |
case-12 | pass→pass | 13,863 | 2,861 | -79% | 1 | 1 | 0% | 2,315 | 722 | -69% | 0 | 0 | — |
case-13 | fail→pass | 15,640 | 3,577 | -77% | 1 | 1 | 0% | 2,503 | 715 | -71% | 0 | 0 | — |
case-14 | fail→pass | 69,998 | 2,270 | -97% | 1 | 1 | 0% | 4,903 | 689 | -86% | 0 | 0 | — |
case-15 | fail→pass | 11,348 | 2,530 | -78% | 1 | 1 | 0% | 1,943 | 806 | -59% | 0 | 0 | — |
case-16 | pass→pass | 6,138 | 4,234 | -31% | 1 | 1 | 0% | 849 | 885 | +4% | 0 | 0 | — |
case-17 | fail→pass | 9,954 | 2,700 | -73% | 1 | 1 | 0% | 1,753 | 724 | -59% | 0 | 0 | — |
case-18 | fail→pass | 57,579 | 3,161 | -95% | 1 | 1 | 0% | 2,334 | 839 | -64% | 0 | 0 | — |
case-19 | fail→pass | 14,202 | 2,512 | -82% | 1 | 1 | 0% | 2,920 | 676 | -77% | 0 | 0 | — |
case-20 | fail→pass | 4,740 | 3,549 | -25% | 1 | 1 | 0% | 801 | 851 | +6% | 0 | 0 | — |
case-21 | pass→pass | 18,576 | 15,295 | -18% | 1 | 1 | 0% | 2,761 | 1,555 | -44% | 0 | 0 | — |
case-22 | pass→pass | 15,493 | 7,736 | -50% | 1 | 1 | 0% | 2,335 | 1,493 | -36% | 0 | 0 | — |
case-23 | fail→pass | 14,798 | 3,331 | -77% | 1 | 1 | 0% | 2,482 | 866 | -65% | 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 22 counted toward the lift figure. The other 1 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 +57 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.