skill-creator: drop ANTHROPIC_API_KEY requirement from description optimizer (#547)

improve_description.py now calls `claude -p`
as a subprocess instead of the Anthropic SDK, so users no longer need a
separate ANTHROPIC_API_KEY to run the description optimization loop. Same
auth pattern run_eval.py already used for the triggering eval.

Prompts go over stdin (they embed the full SKILL.md body). Strips CLAUDECODE
env var to allow nesting inside a Claude Code session. The over-1024-char
retry is now a fresh single-turn call that inlines the too-long version
rather than a multi-turn followup.

SKILL.md: dropped the stale "extended thinking" reference to match.

skills/skill-creator/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: skill-creator
-description: Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
+description: Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
 ---
 
 # Skill Creator
@@ -391,7 +391,7 @@ Use the model ID from your system prompt (the one powering the current session)
 
 While it runs, periodically tail the output to give the user updates on which iteration it's on and what the scores look like.
 
-This handles the full optimization loop automatically. It splits the eval set into 60% train and 40% held-out test, evaluates the current description (running each query 3 times to get a reliable trigger rate), then calls Claude with extended thinking to propose improvements based on what failed. It re-evaluates each new description on both train and test, iterating up to 5 times. When it's done, it opens an HTML report in the browser showing the results per iteration and returns JSON with `best_description` — selected by test score rather than train score to avoid overfitting.
+This handles the full optimization loop automatically. It splits the eval set into 60% train and 40% held-out test, evaluates the current description (running each query 3 times to get a reliable trigger rate), then calls Claude to propose improvements based on what failed. It re-evaluates each new description on both train and test, iterating up to 5 times. When it's done, it opens an HTML report in the browser showing the results per iteration and returns JSON with `best_description` — selected by test score rather than train score to avoid overfitting.
 
 ### How skill triggering works
 
@@ -435,6 +435,11 @@ In Claude.ai, the core workflow is the same (draft → test → review → impro
 
 **Packaging**: The `package_skill.py` script works anywhere with Python and a filesystem. On Claude.ai, you can run it and the user can download the resulting `.skill` file.
 
+**Updating an existing skill**: The user might be asking you to update an existing skill, not create a new one. In this case:
+- **Preserve the original name.** Note the skill's directory name and `name` frontmatter field -- use them unchanged. E.g., if the installed skill is `research-helper`, output `research-helper.skill` (not `research-helper-v2`).
+- **Copy to a writeable location before editing.** The installed skill path may be read-only. Copy to `/tmp/skill-name/`, edit there, and package from the copy.
+- **If packaging manually, stage in `/tmp/` first**, then copy to the output directory -- direct writes may fail due to permissions.
+
 ---
 
 ## Cowork-Specific Instructions
@@ -447,6 +452,7 @@ If you're in Cowork, the main things to know are:
 - Feedback works differently: since there's no running server, the viewer's "Submit All Reviews" button will download `feedback.json` as a file. You can then read it from there (you may have to request access first).
 - Packaging works — `package_skill.py` just needs Python and a filesystem.
 - Description optimization (`run_loop.py` / `run_eval.py`) should work in Cowork just fine since it uses `claude -p` via subprocess, not a browser, but please save it until you've fully finished making the skill and the user agrees it's in good shape.
+- **Updating an existing skill**: The user might be asking you to update an existing skill, not create a new one. Follow the update guidance in the claude.ai section above.
 
 ---