tree-sitter-analyzer: Skill for Claude Code

tsa-refactor-queue — Top-N prioritized refactor slices

Three signals, one ranked list. Health × churn × dead-code → the five files you'd refactor first if you had a week. Each row carries a target symbol, a blast radius, and a concrete action.

When to use

• "What should we refactor next?" — daily/weekly engineering triage
• Post-feature cleanup pass — find rot that accumulated while shipping
• Pre-sprint planning — turn "we should clean up" into 5 concrete tickets
• After a CI grade-drop alert from tsa-health-watch — re-rank with churn

Don't use when:

• You already know the file (one-file deep dive → health action=file or tsa-edit-safety)
• The codebase is brand-new (<2 weeks of git history) — churn signal is noise
• You want to optimize one hot function — use tsa-graph + edit action=refactor directly
• Shallow clone in CI — git_state=shallow makes mod_count_30d unreliable

Procedure

Step 0 — Try the one-call route first (RFC-0027 §L8)

The three-signal join and the Step 2 formula now live in code:

health action=refactor_queue top_n=5          # MCP
uv run python -m tree_sitter_analyzer --refactor-queue --refactor-queue-top-n 5   # CLI

It returns the ranked rows directly (rank, file_path, grade, weakest_dimension, churn_30d, dead_symbols, total_symbols, priority, action) and echoes the formula it used. If it answers status=CHURN_UNAVAILABLE, the AST index has no 30-day churn — build the index and retry rather than hand-computing zeros.

Fall through to Steps 1-4 below only when you need signals the action does not carry (e.g. the heatmap view, or a per-candidate blast radius).

Step 1 — Single fan-out (parallel, 3 MCP calls)

Call these in ONE message:

1. health action=project with min_grade: "D" and max_files: 20 — F/D files + per-file weakest_dimension
2. health action=dead with max_dead: 200 — symbol-level dead candidates, grouped by file
3. health action=heatmap with top_n: 20 — complexity-weighted file list (covers structural smell)