Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Converts unstructured risk assessments into structured Jira tickets. Extracts Likelihood, Impact, Mitigation from natural language and generates JSON formatted for Jira API with clear Definition of Done criteria.
.claude/skills/grcengclub-risk-to-jira-transformer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -9% | 0% |
Converts unstructured risk assessments into structured engineering tickets. Turns "Risk Management" into "Task Management."
Transform a risk assessment:
bashnode plugins/grc-engineer/scripts/transform-risk.js "Vulnerability in authentication service discovered during pen test. High likelihood, critical impact. Mitigation: Implement OAuth2 with PKCE." SEC
Transform with custom project:
bashnode plugins/grc-engineer/scripts/transform-risk.js "<risk description>" INFRA
Accepts natural language risk descriptions. Automatically extracts:
Generates JSON formatted for Jira API:
json{ "fields": { "project": { "key": "SEC" }, "summary": "Implement OAuth2 with PKCE for authentication service", "description": "...", "issuetype": { "name": "Security Task" }, "priority": { "name": "Critical" }, "labels": ["security", "authentication", "risk-mitigation"], "customfield_10001": "High", // Likelihood "customfield_10002": "Critical", // Impact "customfield_10003": "Implement OAuth2 with PKCE" // Mitigation } }
Automatically calculates risk score:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 8,606 | 9,055 | +5% | 1 | 1 | 0% | 1,568 | 1,850 | +18% | 0 | 0 | — |
case-02 | fail→pass | 8,847 | 4,872 | -45% | 1 | 1 | 0% | 1,729 | 1,627 | -6% | 0 | 0 | — |
case-03 | fail→pass | 11,252 | 6,231 | -45% | 1 | 1 | 0% | 2,443 | 1,887 | -23% | 0 | 0 | — |
case-04 | pass→pass | 9,298 | 9,427 | +1% | 1 | 1 | 0% | 1,877 | 2,116 | +13% | 0 | 0 | — |
case-05 | pass→pass | 11,539 | 7,819 | -32% | 1 | 1 | 0% | 1,914 | 1,944 | +2% | 0 | 0 | — |
case-06 | pass→pass | 16,953 | 13,386 | -21% | 1 | 1 | 0% | 2,426 | 2,630 | +8% | 0 | 0 | — |
case-07 | fail→pass | 10,555 | 5,099 | -52% | 1 | 1 | 0% | 1,860 | 1,568 | -16% | 0 | 0 | — |
case-08 | fail→pass | 11,174 | 6,146 | -45% | 1 | 1 | 0% | 1,960 | 1,778 | -9% | 0 | 0 | — |
case-09 | fail→pass | 6,860 | 4,017 | -41% | 1 | 1 | 0% | 1,272 | 1,311 | +3% | 0 | 0 | — |
case-10 | pass→pass | 9,572 | 6,919 | -28% | 1 | 1 | 0% | 1,764 | 2,012 | +14% | 0 | 0 | — |
case-11 | fail→pass | 6,768 | 5,531 | -18% | 1 | 1 | 0% | 1,188 | 1,708 | +44% | 0 | 0 | — |
case-12 | pass→pass | 11,772 | 6,574 | -44% | 1 | 1 | 0% | 2,338 | 1,864 | -20% | 0 | 0 | — |
case-13 | fail→fail | 5,440 | 6,087 | +12% | 1 | 1 | 0% | 992 | 1,835 | +85% | 0 | 0 | — |
case-14 | fail→pass | 12,542 | 5,508 | -56% | 1 | 1 | 0% | 2,489 | 1,791 | -28% | 0 | 0 | — |
case-15 | fail→pass | 11,946 | 7,064 | -41% | 1 | 1 | 0% | 2,265 | 2,078 | -8% | 0 | 0 | — |
case-16 | fail→pass | 12,701 | 5,039 | -60% | 1 | 1 | 0% | 2,590 | 1,577 | -39% | 0 | 0 | — |
case-17 | fail→pass | 10,911 | 5,849 | -46% | 1 | 1 | 0% | 2,175 | 1,755 | -19% | 0 | 0 | — |
case-18 | fail→pass | 5,551 | 6,952 | +25% | 1 | 1 | 0% | 1,076 | 1,927 | +79% | 0 | 0 | — |
case-19 | fail→pass | 8,884 | 5,775 | -35% | 1 | 1 | 0% | 1,856 | 1,718 | -7% | 0 | 0 | — |
case-20 | pass→pass | 11,514 | 5,823 | -49% | 1 | 1 | 0% | 2,438 | 1,745 | -28% | 0 | 0 | — |
case-21 | fail→pass | 6,758 | 4,578 | -32% | 1 | 1 | 0% | 1,171 | 1,521 | +30% | 0 | 0 | — |
case-22 | pass→pass | 8,917 | 5,422 | -39% | 1 | 1 | 0% | 1,703 | 1,659 | -3% | 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 +64 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.