skills: harvest 4 MIT dev skills from obra/superpowers (awesome-claude-skills)

From the ComposioHQ/awesome-claude-skills list. Checked licenses BEFORE copying:
- threat-hunting-with-sigma-rules: repo is gone (GitHub 404) -- not harvested.
- forensics (mhattingpete): repo restructured, those skills no longer exist -- not harvested.
- pdf / mcp-builder (Anthropic official): LICENSE.txt FORBIDS copying out of the
  Service / derivatives / redistribution -- NOT harvestable into this repo (install via
  the official Claude Code marketplace instead if wanted).
- obra/superpowers: MIT -> the only legally harvestable set; imported with attribution.

Imported (each with its own MIT LICENSE copy + SOURCE.md provenance, commit a21956e48c13,
ASCII-normalized to house style, no emojis):
- using-git-worktrees
- test-driven-development (+ testing-anti-patterns.md)
- root-cause-tracing (+ find-polluter.sh helper, emojis -> ASCII markers)
- brainstorming (methodology only; upstream visual websocket server intentionally omitted)

Faithful imports -- content not reworded beyond ASCII typography/emoji normalization.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.claude/skills/test-driven-development/SOURCE.md

@@ -0,0 +1,12 @@
+# Source / Provenance
+
+Harvested from obra/superpowers (MIT, Copyright (c) 2025 Jesse Vincent) at commit a21956e48c13 on 2026-06-17.
+
+## Source paths
+- `skills/test-driven-development/SKILL.md` -> `SKILL.md`
+- `skills/test-driven-development/testing-anti-patterns.md` -> `testing-anti-patterns.md`
+
+## Adaptations (ClaudeTools house style)
+- `SKILL.md`: 5 non-ASCII characters normalized (em-dash `-` -> `-`; not-equal `!=` -> `!=`; unicode arrow `->` -> `->`).
+- `testing-anti-patterns.md`: 15 non-ASCII characters normalized, including emoji replaced with ASCII status markers (cross mark -> `[ERROR]`, check-mark emoji and check symbol -> `[OK]`) plus em-dash and unicode-arrow normalization.
+- No content was reworded; the TDD methodology and anti-patterns are preserved as in the source apart from the normalizations above.