Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate @moduledoc/@doc for tested Elixir features; may update their README section or ADR. Not for docs lookup, documentation audits/reviews, or capturing standalone decisions.
.claude/skills/oliver-kriska-phx-document/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -25% | 0% |
Generate documentation for newly implemented features.
/skill:phx-document .claude/plans/magic-link-auth/plan.md
/skill:phx-document magic link authentication
/skill:phx-document # Auto-detect from recent plan| Output | Description | |--------|-------------| | @moduledoc | For new modules missing documentation | | @doc | For public functions without docs | | README section | For user-facing features | | ADR | For significant architectural decisions |
Run git diff --name-only HEAD~5 | grep '\.ex$' | head -20 to check for new .ex files.
If NO new .ex files were added (only modifications), skip the full audit and report: "No new modules — documentation coverage unchanged." This prevents 35-message analysis sessions that conclude "PASS" with zero output (confirmed: session bb0a0454 wasted ~2K tokens on no-op).
@moduledoc, @doc).claude/plans/{slug}/reviews/{feature}-docs.md| Trigger | Create ADR | |---------|-----------| | New external dependency | Yes | | New database table | Maybe (if schema non-obvious) | | New OTP process | Yes (explain why process needed) | | New context | Maybe (if boundaries non-obvious) | | New auth mechanism | Yes | | Performance optimization | Yes |
text/skill:phx-plan → /skill:phx-work → /skill:phx-review ↓ /skill:phx-document ← YOU ARE HERE (optional, suggested after review passes)
references/doc-templates.md — @moduledoc, @doc, README, ADR templatesreferences/output-format.md — Documentation report formatreferences/doc-best-practices.md — Elixir documentation best practicesreferences/documentation-patterns.md — Detailed documentation patterns| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 26,742 | 3,361 | -87% | 1 | 1 | 0% | 4,152 | 987 | -76% | 0 | 0 | — |
case-02 | fail→fail | 21,738 | 2,991 | -86% | 1 | 1 | 0% | 3,809 | 1,099 | -71% | 0 | 0 | — |
case-03 | fail→fail | 15,541 | 4,123 | -73% | 1 | 1 | 0% | 2,419 | 1,021 | -58% | 0 | 0 | — |
case-04 | fail→fail | 7,931 | 4,585 | -42% | 1 | 1 | 0% | 1,289 | 1,577 | +22% | 0 | 0 | — |
case-05 | pass→pass | 7,791 | 4,355 | -44% | 1 | 1 | 0% | 1,227 | 1,374 | +12% | 0 | 0 | — |
case-06 | pass→pass | 12,696 | 9,284 | -27% | 1 | 1 | 0% | 2,044 | 2,240 | +10% | 0 | 0 | — |
case-07 | pass→pass | 13,425 | 7,275 | -46% | 1 | 1 | 0% | 1,981 | 1,831 | -8% | 0 | 0 | — |
case-08 | pass→pass | 10,661 | 9,885 | -7% | 1 | 1 | 0% | 1,737 | 2,318 | +33% | 0 | 0 | — |
case-09 | fail→pass | 11,221 | 3,423 | -69% | 1 | 1 | 0% | 1,749 | 1,231 | -30% | 0 | 0 | — |
case-10 | pass→pass | 12,687 | 5,267 | -58% | 1 | 1 | 0% | 1,960 | 1,565 | -20% | 0 | 0 | — |
case-11 | pass→pass | 10,090 | 5,505 | -45% | 1 | 1 | 0% | 1,605 | 1,553 | -3% | 0 | 0 | — |
case-12 | pass→pass | 11,470 | 7,553 | -34% | 1 | 1 | 0% | 1,728 | 1,949 | +13% | 0 | 0 | — |
case-13 | fail→pass | 14,287 | 2,299 | -84% | 1 | 1 | 0% | 2,631 | 1,081 | -59% | 0 | 0 | — |
case-14 | fail→pass | 8,898 | 8,329 | -6% | 1 | 1 | 0% | 1,480 | 2,172 | +47% | 0 | 0 | — |
case-15 | fail→pass | 9,330 | 4,442 | -52% | 1 | 1 | 0% | 1,463 | 1,378 | -6% | 0 | 0 | — |
case-16 | fail→pass | 13,390 | 4,744 | -65% | 1 | 1 | 0% | 1,943 | 1,463 | -25% | 0 | 0 | — |
case-17 | pass→pass | 9,272 | 4,068 | -56% | 1 | 1 | 0% | 1,677 | 1,460 | -13% | 0 | 0 | — |
case-18 | pass→pass | 10,732 | 4,287 | -60% | 1 | 1 | 0% | 1,572 | 1,410 | -10% | 0 | 0 | — |
case-19 | pass→pass | 10,679 | 5,824 | -45% | 1 | 1 | 0% | 1,650 | 1,690 | +2% | 0 | 0 | — |
case-20 | pass→pass | 7,266 | 4,021 | -45% | 1 | 1 | 0% | 1,281 | 1,521 | +19% | 0 | 0 | — |
case-21 | pass→pass | 12,853 | 10,613 | -17% | 1 | 1 | 0% | 2,195 | 2,479 | +13% | 0 | 0 | — |
case-22 | pass→pass | 10,919 | 9,195 | -16% | 1 | 1 | 0% | 1,983 | 2,209 | +11% | 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 20 counted toward the lift figure. The other 2 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 20 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.