got rid of TDD stuff and changed some skills to make it more specific…

.claude-plugin/plugin.json

@@ -1,13 +1,18 @@
 {
   "name": "superpowers",
-  "description": "Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques",
-  "version": "4.0.3",
+  "description": "Core skills library for Claude Code: debugging, collaboration patterns, and proven techniques",
+  "version": "4.0.4",
   "author": {
-    "name": "Jesse Vincent",
-    "email": "jesse@fsck.com"
+    "name": "Jobuii"
   },
-  "homepage": "https://github.com/obra/superpowers",
-  "repository": "https://github.com/obra/superpowers",
+  "forkedFrom": "https://github.com/obra/superpowers",
+  "originalAuthor": "Jesse Vincent",
+  "homepage": "https://github.com/jobuii/superpowers",
+  "repository": "https://github.com/jobuii/superpowers",
   "license": "MIT",
-  "keywords": ["skills", "tdd", "debugging", "collaboration", "best-practices", "workflows"]
+  "keywords": ["skills", "debugging", "collaboration", "best-practices", "workflows"],
+  "skills": "./skills/",
+  "hooks": "./hooks/hooks.json",
+  "commands": "./commands/",
+  "agents": "./agents/"
 }

docs/windows/polyglot-hooks.md

@@ -65,7 +65,6 @@ hooks/
   "hooks": {
     "SessionStart": [
       {
-        "matcher": "startup|resume|clear|compact",
         "hooks": [
           {
             "type": "command",
@@ -80,6 +79,8 @@ hooks/
 
 Note: The path must be quoted because `${CLAUDE_PLUGIN_ROOT}` may contain spaces on Windows (e.g., `C:\Program Files\...`).
 
+**Important:** SessionStart hooks don't use the `matcher` field - that's only for tool hooks like PreToolUse.
+
 ## Requirements
 
 ### Windows
@@ -160,7 +161,6 @@ shift
   "hooks": {
     "SessionStart": [
       {
-        "matcher": "startup",
         "hooks": [
           {
             "type": "command",
@@ -184,6 +184,8 @@ shift
 }
 ```
 
+Note: `matcher` is used for PreToolUse to filter which tool triggers the hook (e.g., "Bash"), but SessionStart hooks don't need or use matcher.
+
 ## Troubleshooting
 
 ### "bash is not recognized"

hooks/hooks.json

@@ -2,7 +2,6 @@
   "hooks": {
     "SessionStart": [
       {
-        "matcher": "startup|resume|clear|compact",
         "hooks": [
           {
             "type": "command",

hooks/run-hook.cmd

@@ -8,7 +8,7 @@ if "%~1"=="" (
     echo run-hook.cmd: missing script name >&2
     exit /b 1
 )
-"C:\Program Files\Git\bin\bash.exe" -l "%~dp0%~1" %2 %3 %4 %5 %6 %7 %8 %9
+"C:\Program Files\Git\bin\bash.exe" --norc --noprofile "%~dp0%~1" %2 %3 %4 %5 %6 %7 %8 %9
 exit /b
 CMDBLOCK
 

skills/subagent-driven-development/SKILL.md

@@ -167,7 +167,7 @@ Done!
 ## Advantages
 
 **vs. Manual execution:**
-- Subagents follow TDD naturally
+- Subagents work methodically with tests
 - Fresh context per task (no confusion)
 - Parallel-safe (subagents don't interfere)
 - Subagent can ask questions (before AND during work)
@@ -233,8 +233,5 @@ Done!
 - **superpowers:requesting-code-review** - Code review template for reviewer subagents
 - **superpowers:finishing-a-development-branch** - Complete development after all tasks
 
-**Subagents should use:**
-- **superpowers:test-driven-development** - Subagents follow TDD for each task
-
 **Alternative workflow:**
 - **superpowers:executing-plans** - Use for parallel session instead of same-session execution

skills/subagent-driven-development/implementer-prompt.md

@@ -30,7 +30,7 @@ Task tool (general-purpose):
 
     Once you're clear on requirements:
     1. Implement exactly what the task specifies
-    2. Write tests (following TDD if task says to)
+    2. Write tests to verify implementation
     3. Verify implementation works
     4. Commit your work
     5. Self-review (see below)
@@ -62,7 +62,7 @@ Task tool (general-purpose):
 
     **Testing:**
     - Do tests actually verify behavior (not just mock behavior)?
-    - Did I follow TDD if required?
+    - Did I write appropriate tests?
     - Are tests comprehensive?
 
     If you find issues during self-review, fix them now before reporting.

skills/systematic-debugging/SKILL.md

@@ -176,7 +176,6 @@ You MUST complete each phase before proceeding to the next.
    - Automated test if possible
    - One-off test script if no framework
    - MUST have before fixing
-   - Use the `superpowers:test-driven-development` skill for writing proper failing tests
 
 2. **Implement Single Fix**
    - Address the root cause identified
@@ -284,7 +283,6 @@ These techniques are part of systematic debugging and available in this director
 - **`condition-based-waiting.md`** - Replace arbitrary timeouts with condition polling
 
 **Related skills:**
-- **superpowers:test-driven-development** - For creating failing test case (Phase 4, Step 1)
 - **superpowers:verification-before-completion** - Verify fix worked before claiming success
 
 ## Real-World Impact