feat: add finish-branch skill (clean-room synthesis from obra/superpowers pattern)

Clean-room synthesis of the 'finishing a development branch' pattern from
obra/superpowers (MIT) — adopted as the forced-choice workflow scaffold,
not the substantive rules. Substantive rules defer to existing ones:
- Verification → verification.md
- Commit conventions + no AI attribution → commits.md
- Review discipline → review-code

Core patterns implemented:
- Phase 1 verify-before-options (hard-stop on failing tests)
- Phase 2 base branch + commit range + worktree detection
- Phase 3 forced-choice menu (exactly 4 options, no editorializing, stop+wait)
- Phase 4 execution per-option with:
  - Option 1 (merge locally): re-verify after merge, delete branch, prompt
    about remote-branch cleanup separately
  - Option 2 (push + PR): gh pr create with inline template (no AI
    attribution in the body); do NOT remove worktree
  - Option 3 (keep): no git state changes; preserve worktree
  - Option 4 (discard): typed-word "discard" confirmation gate required;
    lists what will be permanently lost; force-delete + remote cleanup
- Phase 5 worktree cleanup matrix (cleanup for 1 and 4; preserve for 2 and 3)

Notable over the upstream superpowers skill:
- Explicit delegation to verification.md / commits.md / review-code rather
  than re-teaching those standards inline
- Cross-references to /review-code (pre) and /arch-evaluate (if architectural)
- Handles remote-branch cleanup question separately from local branch
  (upstream conflates them)
- "Common Mistakes" section names the specific failure modes this skill
  prevents (open-ended "what now", accidental deletes, merge-then-oops,
  worktree amnesia, trailing AI attribution in PRs)

Rubric coverage vs upstream: M (verify → options → execute → cleanup);
M (forced-choice menu pattern); M (typed-discard confirmation gate);
M (worktree cleanup matrix); M (hard-stop on failing tests);
+ (explicit deferral to existing rules vs upstream's inline rules);
+ (remote-branch cleanup as separate prompt); + (skill integration notes
for /review-code and /arch-evaluate); no dropped capabilities.

Makefile SKILLS extended; make install symlinks globally at
~/.claude/skills/finish-branch.

1 files changed, 2 insertions, 1 deletions

diff --git a/Makefile b/Makefile
index 1fca989..d37e955 100644
--- a/Makefile
+++ b/Makefile
@@ -6,7 +6,8 @@ RULES_DIR  := $(HOME)/.claude/rules
 SKILLS     := c4-analyze c4-diagram debug add-tests respond-to-review review-code fix-issue security-check \
               arch-design arch-decide arch-document arch-evaluate \
               brainstorm codify root-cause-trace five-whys prompt-engineering \
-              playwright-js playwright-py frontend-design pairwise-tests
+              playwright-js playwright-py frontend-design pairwise-tests \
+              finish-branch
 RULES      := $(wildcard claude-rules/*.md)
 LANGUAGES  := $(notdir $(wildcard languages/*))