Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →End-to-end processing pipeline that chains the full 6R sequence: seed, reduce, reflect, reweave, verify. Runs per-item or in batch mode. Three depth levels control thoroughness vs. speed. The orchestrator for all processing skills. Triggers on: "pipeline", "process", "full pipeline", "6R"
.claude/skills/miosa-osa-pipeline/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -65% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -57% | 0% |
/pipeline --stage <stage>] --owner <agent>] --health]
Display current pipeline status with deal progression, forecasting, and health metrics.
| Arg | Type | Required | Description | |-----|------|----------|-------------| | --stage | string | No | Filter by stage: research, outreach, discovery, demo, proposal, negotiate, close | | --owner | string | No | Filter by owning agent | | --health | flag | No | Include pipeline health score and recommendations |
Genre: report Format: Markdown table + metrics summary
Produces:
1. Pull all active deals from pipeline state
2. Calculate stage distribution, total value, coverage ratio
3. Generate three-tier forecast (commit/upside/best case)
4. If --health: run pipeline health checks per director's framework
5. Output formatted report per director's Weekly Pipeline Report template/pipeline
/pipeline --stage discovery
/pipeline --health
/pipeline --owner closer --health| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→fail | 18,856 | 18,826 | -0% | 1 | 1 | 0% | 3,229 | 3,539 | +10% | 0 | 0 | — |
case-06 | fail→fail | 8,500 | 18,832 | +122% | 1 | 1 | 0% | 1,503 | 4,187 | +179% | 0 | 0 | — |
case-01 | fail→pass | 17,847 | 13,439 | -25% | 1 | 1 | 0% | 2,779 | 2,779 | 0% | 0 | 0 | — |
case-02 | fail→pass | 15,445 | 12,958 | -16% | 1 | 1 | 0% | 2,750 | 2,677 | -3% | 0 | 0 | — |
case-03 | fail→pass | 23,110 | 19,514 | -16% | 1 | 1 | 0% | 4,183 | 3,496 | -16% | 0 | 0 | — |
case-04 | fail→fail | 4,487 | 9,556 | +113% | 1 | 1 | 0% | 721 | 1,935 | +168% | 0 | 0 | — |
case-07 | fail→pass | 15,962 | 2,088 | -87% | 1 | 1 | 0% | 2,039 | 707 | -65% | 0 | 0 | — |
case-08 | fail→pass | 11,212 | 2,245 | -80% | 1 | 1 | 0% | 1,637 | 703 | -57% | 0 | 0 | — |
case-09 | fail→pass | 11,234 | 1,966 | -82% | 1 | 1 | 0% | 1,705 | 645 | -62% | 0 | 0 | — |
case-10 | fail→pass | 9,349 | 1,629 | -83% | 1 | 1 | 0% | 1,452 | 624 | -57% | 0 | 0 | — |
case-15 | fail→pass | 11,702 | 2,799 | -76% | 1 | 1 | 0% | 1,795 | 671 | -63% | 0 | 0 | — |
case-11 | fail→pass | 9,417 | 2,765 | -71% | 1 | 1 | 0% | 1,480 | 677 | -54% | 0 | 0 | — |
case-12 | fail→pass | 7,298 | 1,641 | -78% | 1 | 1 | 0% | 1,202 | 572 | -52% | 0 | 0 | — |
case-13 | fail→pass | 10,690 | 4,269 | -60% | 1 | 1 | 0% | 1,670 | 1,085 | -35% | 0 | 0 | — |
case-14 | pass→fail | 24,337 | 16,569 | -32% | 1 | 1 | 0% | 2,303 | 2,884 | +25% | 0 | 0 | — |
case-16 | fail→pass | 7,727 | 2,301 | -70% | 1 | 1 | 0% | 1,058 | 647 | -39% | 0 | 0 | — |
case-17 | pass→pass | 10,102 | 3,382 | -67% | 1 | 1 | 0% | 1,554 | 932 | -40% | 0 | 0 | — |
case-18 | fail→pass | 6,444 | 2,245 | -65% | 1 | 1 | 0% | 899 | 599 | -33% | 0 | 0 | — |
case-19 | fail→pass | 9,837 | 1,924 | -80% | 1 | 1 | 0% | 1,208 | 597 | -51% | 0 | 0 | — |
case-20 | fail→pass | 12,577 | 2,557 | -80% | 1 | 1 | 0% | 1,679 | 603 | -64% | 0 | 0 | — |
case-21 | fail→fail | 9,200 | 4,211 | -54% | 1 | 1 | 0% | 1,372 | 998 | -27% | 0 | 0 | — |
case-22 | pass→pass | 8,679 | 2,541 | -71% | 1 | 1 | 0% | 1,293 | 798 | -38% | 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. 2 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.