@simplysm/sd-claude 13.0.41 → 13.0.42

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: sd-skill
3
3
  description: Use when creating new skills, editing existing skills, or verifying skills work before deployment
4
- model: sonnet
4
+ model: opus
5
5
  ---
6
6
 
7
7
  # Writing Skills
@@ -401,6 +401,15 @@ Different skill types need different test approaches:
401
401
  - Variation scenarios: Do they handle edge cases?
402
402
  - Missing information tests: Do instructions have gaps?
403
403
 
404
+ **How to test:** Give a subagent a problem the technique solves, WITHOUT the skill. Observe what approach they use naturally. Then give the SAME problem WITH the skill and verify they apply the technique correctly.
405
+
406
+ ```
407
+ Example: Testing a "condition-based-waiting" skill
408
+ 1. Ask subagent: "Fix this flaky test that uses setTimeout(500)"
409
+ 2. WITHOUT skill: Agent increases timeout to 2000ms (wrong approach)
410
+ 3. WITH skill: Agent replaces with polling/condition check (correct)
411
+ ```
412
+
404
413
  **Success criteria:** Agent successfully applies technique to new scenario
405
414
 
406
415
  ### Pattern Skills (mental models)
@@ -437,6 +446,7 @@ Different skill types need different test approaches:
437
446
  | "I'm confident it's good" | Overconfidence guarantees issues. Test anyway. |
438
447
  | "Academic review is enough" | Reading ≠ using. Test application scenarios. |
439
448
  | "No time to test" | Deploying untested skill wastes more time fixing it later. |
449
+ | "I already know the baseline failures" | You know what YOU think the failures are. Run a subagent to see what ACTUALLY happens. Knowledge ≠ observation. |
440
450
 
441
451
  **All of these mean: Test before deploying. No exceptions.**
442
452
 
@@ -527,6 +537,8 @@ Run pressure scenario with subagent WITHOUT the skill. Document exact behavior:
527
537
 
528
538
  This is "watch the test fail" - you must see what agents naturally do before writing the skill.
529
539
 
540
+ **You MUST actually run a subagent.** Do not substitute your own knowledge of "what agents would probably do." Your prediction of baseline behavior ≠ observed baseline behavior. Run the subagent, read the output, document what actually happened.
541
+
530
542
  ### GREEN: Write Minimal Skill
531
543
 
532
544
  Write skill that addresses those specific rationalizations. Don't add extra content for hypothetical cases.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@simplysm/sd-claude",
3
- "version": "13.0.41",
3
+ "version": "13.0.42",
4
4
  "description": "Simplysm Claude Code CLI — asset installer and cross-platform npx wrapper",
5
5
  "author": "김석래",
6
6
  "license": "Apache-2.0",