skilldrop-cli 1.1.2 → 1.1.3

package/README.md

@@ -25,10 +25,11 @@ The blind judge picked the skill's answer: *"A misses this and recommends a Clai
 
 ## The receipts
 
-Every skill runs as a real agent session twice: once with the skill, once without. The results are [published either way](https://sananthanarayan.github.io/skilldrop/evals/). In the last full run (5 October 2026: 100 skills, 209 evals, `claude-sonnet-5`):
+Every skill runs as a real agent session twice: once with the skill, once without. The results are [published either way](https://sananthanarayan.github.io/skilldrop/evals/). In the last full run (23 October 2026: 117 skills, 520 evals, `claude-sonnet-5`):
 
-- **With a skill, answers met 75% of their checks; without one, 44%.** The checks were written by each skill's author, so the fairer number is the next one.
-- **Two blind judges preferred the skill's answer in 61% of pairs** (95% interval 55–68%). Each judge saw only the request and both answers, in shuffled order.
+- **With a skill, answers met 73% of their checks; without one, 53%.** The checks were written by each skill's author, so the fairer numbers are the next ones.
+- **Two blind judges preferred the skill's answer in 62% and 61% of pairs.** Each judge saw only the request and both answers, in shuffled order. On the 176 held-out evals that no revision or admission was based on, it was 49% and 48%: no preference.
+- **On Sonnet 5.5, now the standard tier, the judges preferred the plain agent.** On all 308 held-out evals the skill won 40% and 43% of pairs ([what the benchmark showed](guides/explanation/what-the-benchmark-showed.md#standard-on-sonnet-55)).
 - **4 skills that didn't beat the plain agent were [retired](https://sananthanarayan.github.io/skilldrop/evals/#retired)**, and they're listed. Each new skill has to win on held-out evals before it ships.
 
 [Get started](https://sananthanarayan.github.io/skilldrop/start/) · [Browse the packs](https://sananthanarayan.github.io/skilldrop/packs/) · [Search all skills](https://sananthanarayan.github.io/skilldrop/catalogue/) · [Docs](https://sananthanarayan.github.io/skilldrop/docs/) · [What stays stable in 1.x](guides/reference/versioning-and-stability.md) · [Contribute](CONTRIBUTING.md)

package/model-routing.json

@@ -21,7 +21,7 @@
       "label": "Claude Code (Anthropic)",
       "models": {
         "light": "claude-haiku-5-5",
-        "standard": "claude-sonnet-5",
+        "standard": "claude-sonnet-5-5",
         "heavy": "claude-opus-5-5"
       },
       "select_via": "`/model <model-id>` in the session, or hand the skill to the model-router agent for automatic dispatch.",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "skilldrop-cli",
-  "version": "1.1.2",
+  "version": "1.1.3",
   "description": "Portable AI-agent skills, measured against the agent without them. ADRs, PRDs, runbooks, decks and reviews, installable into Claude Code, Cursor, Kiro, and any IDE that takes custom instructions. One command per skill or per role-based pack.",
   "author": {
     "name": "Sanjay Ananthanarayan",