Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Orchestrate complete PRP workflow from feature request to pull request. Run create branch, create PRP, execute implementation, commit changes, and create PR in sequence. Use when implementing features using PRP methodology or when user requests full PRP workflow.
.claude/skills/microck-prp-core-runner/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -71% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -74% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -15% | 0% |
When the user requests to implement a feature using the PRP workflow or wants end-to-end automation from idea to PR, use the SlashCommand tool to invoke /prp-core-run-all with the user's feature description as the argument.
Step-by-step execution:
/prp-core-run-all {feature-description}Error Handling:
Example 1: Autonomous invocation
User: "Can you implement user authentication using JWT with the PRP workflow?"
Assistant: I'll use the prp-core-runner skill to execute the complete PRP workflow for implementing JWT authentication.
[Invokes: /prp-core-run-all Implement user authentication using JWT]Example 2: Feature request
User: "I need to add a search API with Elasticsearch integration using PRP"
Assistant: I'll run the full PRP workflow to implement the search API with Elasticsearch.
[Invokes: /prp-core-run-all Add search API with Elasticsearch integration]Example 3: Refactoring with PRP
User: "Use the PRP methodology to refactor the database layer for better performance"
Assistant: I'll execute the PRP workflow for refactoring the database layer.
[Invokes: /prp-core-run-all Refactor database layer for better performance]Use this skill when:
Do NOT use this skill when:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,129 | 1,984 | -87% | 1 | 1 | 0% | 2,921 | 834 | -71% | 0 | 0 | — |
case-02 | fail→fail | 21,770 | 2,580 | -88% | 1 | 1 | 0% | 4,385 | 871 | -80% | 0 | 0 | — |
case-03 | fail→fail | 25,081 | 2,352 | -91% | 1 | 1 | 0% | 5,088 | 846 | -83% | 0 | 0 | — |
case-04 | pass→pass | 13,938 | 7,887 | -43% | 1 | 1 | 0% | 2,203 | 1,880 | -15% | 0 | 0 | — |
case-05 | pass→pass | 6,907 | 7,192 | +4% | 1 | 1 | 0% | 1,328 | 2,104 | +58% | 0 | 0 | — |
case-06 | pass→pass | 12,932 | 12,498 | -3% | 1 | 1 | 0% | 2,066 | 2,510 | +21% | 0 | 0 | — |
case-07 | fail→fail | 17,917 | 4,145 | -77% | 1 | 1 | 0% | 3,524 | 841 | -76% | 0 | 0 | — |
case-08 | fail→fail | 14,942 | 2,223 | -85% | 1 | 1 | 0% | 2,808 | 817 | -71% | 0 | 0 | — |
case-09 | fail→pass | 17,302 | 1,404 | -92% | 1 | 1 | 0% | 3,101 | 806 | -74% | 0 | 0 | — |
case-10 | fail→fail | 22,932 | 2,777 | -88% | 1 | 1 | 0% | 4,864 | 831 | -83% | 0 | 0 | — |
case-11 | fail→fail | 17,912 | 1,463 | -92% | 1 | 1 | 0% | 3,469 | 806 | -77% | 0 | 0 | — |
case-12 | pass→pass | 7,323 | 3,277 | -55% | 1 | 1 | 0% | 1,173 | 1,157 | -1% | 0 | 0 | — |
case-13 | pass→pass | 6,303 | 2,434 | -61% | 1 | 1 | 0% | 869 | 929 | +7% | 0 | 0 | — |
case-14 | fail→pass | 10,858 | 1,738 | -84% | 1 | 1 | 0% | 1,557 | 857 | -45% | 0 | 0 | — |
case-15 | fail→pass | 10,939 | 3,498 | -68% | 1 | 1 | 0% | 1,740 | 1,188 | -32% | 0 | 0 | — |
case-16 | fail→fail | 16,738 | 2,373 | -86% | 1 | 1 | 0% | 3,186 | 797 | -75% | 0 | 0 | — |
case-17 | fail→fail | 19,583 | 2,094 | -89% | 1 | 1 | 0% | 4,097 | 812 | -80% | 0 | 0 | — |
case-18 | fail→fail | 21,776 | 1,482 | -93% | 1 | 1 | 0% | 4,453 | 784 | -82% | 0 | 0 | — |
case-19 | fail→fail | 16,070 | 2,542 | -84% | 1 | 1 | 0% | 2,843 | 845 | -70% | 0 | 0 | — |
case-20 | fail→fail | 16,159 | 2,244 | -86% | 1 | 1 | 0% | 2,582 | 856 | -67% | 0 | 0 | — |
case-21 | fail→fail | 13,839 | 2,104 | -85% | 1 | 1 | 0% | 2,666 | 818 | -69% | 0 | 0 | — |
case-22 | fail→fail | 20,768 | 1,420 | -93% | 1 | 1 | 0% | 3,757 | 782 | -79% | 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 +18 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.