xiaoxue_admin
/
ponytail
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
ponytail/examples
History
DietrichGebert ff5d0936be
docs: sweep em dashes out of the active published surface (#180) 
Em dashes crept back into examples, docs/platform-native.md, several READMEs,
the ponytail-debt skill, and a command file since 88431de. Replaced with plain
punctuation (commas, matching the house convention), .openclaw mirror
regenerated. Follows 88431de's scope: leaves untouched the vendored caveman
SKILL.md and the dated benchmarks/results/ writeups (historical records).

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 		2026-06-19 02:37:02 +02:00
..
README.md docs: sweep em dashes out of the active published surface (#180) 2026-06-19 02:37:02 +02:00
csv-sum.md docs: sweep em dashes out of the active published surface (#180) 2026-06-19 02:37:02 +02:00
debounce.md docs: sweep em dashes out of the active published surface (#180) 2026-06-19 02:37:02 +02:00
deep-clone.md docs: sweep em dashes out of the active published surface (#180) 2026-06-19 02:37:02 +02:00
email-validation.md docs: sweep em dashes out of the active published surface (#180) 2026-06-19 02:37:02 +02:00
group-by.md docs: sweep em dashes out of the active published surface (#180) 2026-06-19 02:37:02 +02:00
infinite-scroll.md docs: sweep em dashes out of the active published surface (#180) 2026-06-19 02:37:02 +02:00
modal-dialog.md docs: sweep em dashes out of the active published surface (#180) 2026-06-19 02:37:02 +02:00
number-formatting.md examples: add 6 new over-engineering survivors + platform-native guide (#109) 2026-06-19 00:24:29 +02:00
rate-limit.md docs: sweep em dashes out of the active published surface (#180) 2026-06-19 02:37:02 +02:00
react-countdown.md docs: sweep em dashes out of the active published surface (#180) 2026-06-19 02:37:02 +02:00
url-params.md examples: add 6 new over-engineering survivors + platform-native guide (#109) 2026-06-19 00:24:29 +02:00

README.md

Examples

Real model output, verbatim from benchmark runs, the same task answered by the same model with no skill (## Without Ponytail) and with ponytail (## With Ponytail), so you can compare side by side. Model: Claude Haiku 4.5, temperature 1, source benchmarks/output.json.

These are not hand-written. Reproduce them yourself: npx promptfoo@latest eval -c benchmarks/promptfooconfig.yaml. Method, all three models, and median-of-10 numbers: ../benchmarks/.

Example Without (LOC) With (LOC)
Email Validation 75 3
Debounce 116 10
CSV Sum 20 3
Countdown Timer 267 9
Rate Limiting 128 10