Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Check project progress, show context, and route to next action (execute or plan). Use --forensic to append a 6-check integrity audit after the standard report.
.claude/skills/davepoon-gsd-progress/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 338% | 0% |
| case-06 | ✓→✗ | ▼ Worse | -42% | 0% |
| case-04 | ✓→✗ | ▼ Worse | -32% | 0% |
<objective> Check project progress, summarize recent work and what's ahead, then intelligently route to the next action - either executing an existing plan or creating the next one.
Provides situational awareness before continuing work. </objective>
<execution_context> @${CLAUDE_PLUGIN_ROOT}/workflows/progress.md </execution_context>
<process> Execute the progress workflow from @${CLAUDE_PLUGIN_ROOT}/workflows/progress.md end-to-end. Preserve all routing logic (Routes A through F) and edge case handling. </process>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→fail | 4,418 | 5,472 | +24% | 1 | 1 | 0% | 707 | 413 | -42% | 0 | 0 | — |
case-05 | pass→pass | 5,406 | 3,790 | -30% | 1 | 1 | 0% | 916 | 782 | -15% | 0 | 0 | — |
case-01 | fail→fail | 3,825 | 4,439 | +16% | 1 | 1 | 0% | 261 | 380 | +46% | 0 | 0 | — |
case-02 | fail→fail | 5,153 | 3,816 | -26% | 1 | 1 | 0% | 868 | 307 | -65% | 0 | 0 | — |
case-03 | fail→fail | 6,747 | 4,883 | -28% | 1 | 1 | 0% | 1,054 | 479 | -55% | 0 | 0 | — |
case-04 | pass→fail | 4,087 | 5,437 | +33% | 1 | 1 | 0% | 625 | 428 | -32% | 0 | 0 | — |
case-07 | fail→fail | 8,950 | 5,309 | -41% | 1 | 1 | 0% | 1,520 | 399 | -74% | 0 | 0 | — |
case-08 | pass→fail | 10,382 | 20,867 | +101% | 1 | 1 | 0% | 1,682 | 3,066 | +82% | 0 | 0 | — |
case-09 | fail→pass | 5,821 | 9,913 | +70% | 1 | 1 | 0% | 885 | 1,064 | +20% | 0 | 0 | — |
case-10 | fail→fail | 8,141 | 7,528 | -8% | 1 | 1 | 0% | 1,486 | 1,596 | +7% | 0 | 0 | — |
case-15 | pass→fail | 5,132 | 6,140 | +20% | 1 | 1 | 0% | 849 | 504 | -41% | 0 | 0 | — |
case-11 | fail→fail | 10,903 | 4,263 | -61% | 1 | 1 | 0% | 1,722 | 809 | -53% | 0 | 0 | — |
case-12 | pass→fail | 10,723 | 5,572 | -48% | 1 | 1 | 0% | 1,847 | 667 | -64% | 0 | 0 | — |
case-13 | fail→pass | 9,209 | 12,305 | +34% | 1 | 1 | 0% | 1,412 | 1,593 | +13% | 0 | 0 | — |
case-14 | pass→pass | 4,519 | 4,076 | -10% | 1 | 1 | 0% | 697 | 795 | +14% | 0 | 0 | — |
case-16 | pass→fail | 11,510 | 6,980 | -39% | 1 | 1 | 0% | 1,693 | 514 | -70% | 0 | 0 | — |
case-17 | pass→fail | 12,089 | 6,155 | -49% | 1 | 1 | 0% | 1,912 | 415 | -78% | 0 | 0 | — |
case-18 | fail→fail | 10,386 | 5,272 | -49% | 1 | 1 | 0% | 1,742 | 918 | -47% | 0 | 0 | — |
case-19 | fail→pass | 2,218 | 7,427 | +235% | 1 | 1 | 0% | 327 | 1,431 | +338% | 0 | 0 | — |
case-20 | pass→fail | 6,998 | 3,266 | -53% | 1 | 1 | 0% | 1,395 | 267 | -81% | 0 | 0 | — |
case-21 | fail→fail | 10,561 | 13,943 | +32% | 1 | 1 | 0% | 1,576 | 2,102 | +33% | 0 | 0 | — |
case-22 | fail→fail | 3,952 | 4,710 | +19% | 1 | 1 | 0% | 620 | 381 | -39% | 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 10 counted toward the lift figure. The other 12 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 -23 percentage points is the difference between those two pass rates over the 10 comparable cases. 8 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.