Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.
.claude/skills/oliver-kriska-phx-quick/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -69% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -6% | 0% |
Skip the planning ceremony. Get working code fast.
bash/skill:phx-quick Add pagination to posts /skill:phx-quick Fix the login redirect bug /skill:phx-quick Add CSV export to reports
$ARGUMENTS = What to implement
| Normal Mode | Quick Mode | |-------------|------------| | Spawn research agents | No agents | | Create plan document | Mental model only | | Parallel review | Optional single review | | Multiple iterations | Single pass |
mix compile --warnings-as-errors after every change, even in quick mode/skill:phx-planmix formatGood for:
Not for:
bash/skill:phx-quick Add phone field to users
→ Migration + schema + changeset + form field
bash/skill:phx-quick Fix: posts not showing for admin users
→ Find issue + fix + verify
bash/skill:phx-quick Add GET /api/health endpoint
→ Route + controller + response
If quick mode hits complexity:
This needs more planning. Switching to normal mode.
Run /skill:phx-plan [task] for full analysis.After quick implementation:
Run mix compile --warnings-as-errors. If you touched Ecto schemas or migrations, run mix ecto.migrate. Then run mix test test/path_test.exs for affected tests.
User: /skill:phx-quick Add archived_at timestamp to posts
Claude:
1. Reading lib/my_app/blog/post.ex...
2. Creating migration...
# priv/repo/migrations/xxx_add_archived_at_to_posts.exs
def change do
alter table(:posts) do
add :archived_at, :utc_datetime
end
end
3. Updating schema...
# lib/my_app/blog/post.ex
field :archived_at, :utc_datetime
4. Adding to changeset...
def changeset(post, attrs) do
post
|> cast(attrs, [:title, :body, :archived_at])
...
end
5. Verifying...
$ mix compile --warnings-as-errors ✓
$ mix ecto.migrate ✓
Done. Run `mix test` to verify.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 5,546 | 4,496 | -19% | 1 | 1 | 0% | 1,109 | 1,017 | -8% | 0 | 0 | — |
case-02 | pass→pass | 2,305 | 2,792 | +21% | 1 | 1 | 0% | 341 | 1,102 | +223% | 0 | 0 | — |
case-03 | pass→pass | 3,573 | 1,701 | -52% | 1 | 1 | 0% | 529 | 1,090 | +106% | 0 | 0 | — |
case-04 | fail→pass | 12,957 | 4,870 | -62% | 1 | 1 | 0% | 1,955 | 1,581 | -19% | 0 | 0 | — |
case-05 | fail→pass | 16,028 | 4,390 | -73% | 1 | 1 | 0% | 2,964 | 1,473 | -50% | 0 | 0 | — |
case-06 | fail→pass | 20,065 | 3,724 | -81% | 1 | 1 | 0% | 4,194 | 1,321 | -69% | 0 | 0 | — |
case-07 | pass→pass | 20,256 | 12,099 | -40% | 1 | 1 | 0% | 3,389 | 3,055 | -10% | 0 | 0 | — |
case-08 | pass→pass | 10,647 | 3,371 | -68% | 1 | 1 | 0% | 1,579 | 1,413 | -11% | 0 | 0 | — |
case-09 | fail→pass | 6,717 | 4,046 | -40% | 1 | 1 | 0% | 1,142 | 1,432 | +25% | 0 | 0 | — |
case-10 | fail→pass | 8,111 | 1,590 | -80% | 1 | 1 | 0% | 1,156 | 1,085 | -6% | 0 | 0 | — |
case-11 | pass→pass | 6,803 | 1,239 | -82% | 1 | 1 | 0% | 1,170 | 981 | -16% | 0 | 0 | — |
case-12 | pass→pass | 7,856 | 2,735 | -65% | 1 | 1 | 0% | 1,287 | 1,278 | -1% | 0 | 0 | — |
case-13 | pass→pass | 15,288 | 6,710 | -56% | 1 | 1 | 0% | 2,441 | 1,927 | -21% | 0 | 0 | — |
case-14 | pass→pass | 11,863 | 4,520 | -62% | 1 | 1 | 0% | 1,898 | 1,599 | -16% | 0 | 0 | — |
case-15 | pass→pass | 2,561 | 1,755 | -31% | 1 | 1 | 0% | 457 | 1,115 | +144% | 0 | 0 | — |
case-16 | pass→pass | 7,338 | 5,304 | -28% | 1 | 1 | 0% | 1,354 | 1,789 | +32% | 0 | 0 | — |
case-17 | pass→pass | 7,221 | 2,538 | -65% | 1 | 1 | 0% | 1,062 | 1,160 | +9% | 0 | 0 | — |
case-18 | fail→pass | 9,934 | 1,499 | -85% | 1 | 1 | 0% | 1,459 | 1,010 | -31% | 0 | 0 | — |
case-19 | pass→pass | 7,678 | 1,764 | -77% | 1 | 1 | 0% | 1,200 | 1,069 | -11% | 0 | 0 | — |
case-20 | fail→pass | 9,393 | 1,932 | -79% | 1 | 1 | 0% | 1,444 | 1,130 | -22% | 0 | 0 | — |
case-21 | pass→pass | 5,852 | 2,234 | -62% | 1 | 1 | 0% | 1,058 | 1,226 | +16% | 0 | 0 | — |
case-22 | pass→pass | 7,179 | 4,826 | -33% | 1 | 1 | 0% | 1,240 | 1,706 | +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, and 21 counted toward the lift figure. The other 1 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 +32 percentage points is the difference between those two pass rates over the 21 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.