fix: reduce skill.md by 22% to prevent agents truncating docs (fixes #63)

`playwriter skill` output was ~58KB / 1302 lines. Agents (both Opus and
Sonnet) consistently truncated with `head` or skimmed, missing critical
sections like "working with pages" at line 606.

Reduced to 44KB / 1019 lines (−283 lines, −24%) by:

- Removing BAD examples from mistake sections, keeping only rules + correct patterns
- Removing duplicated sections: "checking page state" (duplicated interaction
  loop), "debugging web apps" (duplicated observation channels), "capabilities"
  list (obvious from rest of doc), "links that open new tabs" (duplicate of
  mistake #10)
- Condensing verbose sections: interaction feedback loop (removed ASCII diagram
  + Framer-specific 4-block example, replaced with compact generic example),
  getCleanHTML internals, recording prose, createDemoVideo (3 blocks → 1)
- Integrated debugging recipe (snapshot + logs + evaluate) into the feedback
  loop section as "deeper observation" examples
- Added explicit instruction in SKILL.md stub: "Do NOT pipe through head, tail,
  or any truncation command — read the entire output"

skills/playwriter/SKILL.md

@@ -21,6 +21,8 @@ This outputs the complete documentation including:
 
 **Do NOT skip this step.** The quick examples below will fail without understanding timeouts, selector rules, and common pitfalls from the full docs.
 
+**Read the ENTIRE output.** Do NOT pipe through `head`, `tail`, or any truncation command. The skill output must be read in its entirety — critical rules about timeouts, selectors, and common pitfalls are spread throughout the document, not just at the top.
+
 ## Minimal Example (after reading full docs)
 
 ```bash