Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create a new Architecture Decision Record with sequential numbering and AgentDB registration
.claude/skills/ruvnet-adr-create/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | -39% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -10% | 0% |
Create a new Architecture Decision Record with the next sequential number, register it in the AgentDB graph, and link it to related ADRs.
When a significant architectural decision needs to be recorded -- new technology adoption, API design choices, data model changes, infrastructure decisions, or any cross-cutting concern that affects multiple components.
Glob for docs/adr/ADR-*.md and parse existing numbers to determine the next sequential ID (ADR-001, ADR-002, etc.). Create docs/adr/ if it does not exist.use-postgresql-for-persistence).Write the file at docs/adr/ADR-NNN-<slug>.md using the standard template:markdown # ADR-NNN: <Title>
## Context
<!-- What is the issue that motivates this decision? -->
## Decision
<!-- What is the change that we are proposing? -->
## Consequences
### Positive -
### Negative -
### Neutral -
## Links
mcp__plugin_ruflo-core_ruflo__agentdb_hierarchical-store with:mem:ADR-NNNsemantic{ "id": "ADR-NNN", "title": "<title>", "status": "proposed", "date": "<today>", "file": "docs/adr/ADR-NNN-<slug>.md" }mcp__plugin_ruflo-core_ruflo__memory_search with the title as query in namespace adr-patterns to find related decisions. If matches are found, add them to the Links section and call mcp__plugin_ruflo-core_ruflo__agentdb_causal-edge for each relationship with:mem:ADR-NNNmem:ADR-RELATEDdepends-onmcp__plugin_ruflo-core_ruflo__memory_store in namespace adr-patterns with key ADR-NNN and the title + context as value for future semantic search.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | pass→fail | 4,711 | 5,019 | +7% | 1 | 1 | 0% | 946 | 1,028 | +9% | 0 | 0 | — |
case-01 | fail→fail | 4,444 | 4,304 | -3% | 1 | 1 | 0% | 303 | 1,192 | +293% | 0 | 0 | — |
case-02 | fail→fail | 4,553 | 13,192 | +190% | 1 | 1 | 0% | 334 | 1,253 | +275% | 0 | 0 | — |
case-03 | fail→fail | 20,327 | 5,949 | -71% | 1 | 1 | 0% | 3,542 | 886 | -75% | 0 | 0 | — |
case-04 | fail→fail | 6,580 | 4,816 | -27% | 1 | 1 | 0% | 1,197 | 1,129 | -6% | 0 | 0 | — |
case-05 | fail→fail | 13,677 | 7,784 | -43% | 1 | 1 | 0% | 2,061 | 839 | -59% | 0 | 0 | — |
case-06 | fail→fail | 6,699 | 9,631 | +44% | 1 | 1 | 0% | 1,326 | 2,486 | +87% | 0 | 0 | — |
case-07 | fail→fail | 7,433 | 7,176 | -3% | 1 | 1 | 0% | 1,330 | 1,199 | -10% | 0 | 0 | — |
case-09 | pass→pass | 9,706 | 1,768 | -82% | 1 | 1 | 0% | 1,671 | 942 | -44% | 0 | 0 | — |
case-10 | fail→pass | 10,726 | 2,552 | -76% | 1 | 1 | 0% | 2,037 | 1,250 | -39% | 0 | 0 | — |
case-11 | fail→pass | 8,878 | 1,619 | -82% | 1 | 1 | 0% | 1,582 | 936 | -41% | 0 | 0 | — |
case-12 | fail→pass | 7,641 | 1,430 | -81% | 1 | 1 | 0% | 1,577 | 917 | -42% | 0 | 0 | — |
case-13 | fail→pass | 7,507 | 2,620 | -65% | 1 | 1 | 0% | 1,417 | 1,148 | -19% | 0 | 0 | — |
case-14 | fail→pass | 6,072 | 2,032 | -67% | 1 | 1 | 0% | 1,177 | 1,058 | -10% | 0 | 0 | — |
case-15 | pass→pass | 10,662 | 2,056 | -81% | 1 | 1 | 0% | 1,769 | 953 | -46% | 0 | 0 | — |
case-16 | pass→pass | 2,870 | 2,030 | -29% | 1 | 1 | 0% | 513 | 1,034 | +102% | 0 | 0 | — |
case-17 | fail→pass | 8,689 | 2,113 | -76% | 1 | 1 | 0% | 1,487 | 1,005 | -32% | 0 | 0 | — |
case-18 | fail→pass | 9,498 | 1,476 | -84% | 1 | 1 | 0% | 1,665 | 848 | -49% | 0 | 0 | — |
case-19 | fail→pass | 11,761 | 3,246 | -72% | 1 | 1 | 0% | 2,255 | 1,350 | -40% | 0 | 0 | — |
case-20 | fail→fail | 6,632 | 2,361 | -64% | 1 | 1 | 0% | 1,228 | 1,003 | -18% | 0 | 0 | — |
case-21 | pass→pass | 4,475 | 1,877 | -58% | 1 | 1 | 0% | 743 | 954 | +28% | 0 | 0 | — |
case-22 | fail→pass | 17,301 | 1,820 | -89% | 1 | 1 | 0% | 1,553 | 1,005 | -35% | 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 15 counted toward the lift figure. The other 7 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 +36 percentage points is the difference between those two pass rates over the 15 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.