Orchestrates batched Python code analysis tools with disk-persisted, resumable workflows.
npx skills add https://github.com/axel-kaliff/dotfiles --skill review-seq
Please help me install this Agent Skill. Skill: review-seq Source: https://github.com/axel-kaliff/dotfiles/tree/main/claude/.claude/skills/review-seq Command: npx skills add https://github.com/axel-kaliff/dotfiles --skill review-seq
Provides a resilient, disk-backed code review orchestration that prevents findings from being lost to context overflow by persisting per-tool outputs, compacting context between waves, and supporting resume after interruptions. It ensures every automated analysis gets full attention and that large or long-running reviews remain deterministic and recoverable.
Run the review-seq pipeline on the current branch in review-fix mode to persist findings, score and analyze root causes, and produce a prioritized fix plan.
High-intent search queries and answers about installing and using this skill.
Batched code review with disk persistence writes per-tool findings to a claude_session directory, compacts context between analysis waves, and supports resume after interruptions so no results depend on ephemeral context windows.
Yes, interrupted multi-batch code reviews resume deterministically because all per-tool findings are persisted to a claude_session directory on disk, preserving a full audit trail and allowing recovery without re-running completed analysis waves.
Python branch diff pre-merge reviews require ruff, ty, semgrep, and pytest, with optional import-linter for full checks. You also need repository git access and the ability to write claude_session state files to disk.
Batched static analysis with semgrep and ruff persists findings to disk, then aggregates, deduplicates, and scores them. Root-cause analysis waves produce a prioritized fix plan with anchors for safe automated fixes in review-fix mode.
Reviewing and auto-fixing large Python changesets is best handled by a disk-persisted batched pipeline that runs analysis tools in parallel, compacts context between waves, and produces a prioritized fix plan with anchors for safe automated fixes.
A disk-persisted batched code review pipeline is not suited for environments lacking git access, the ability to write claude_session state files, or required analysis tools like ruff, ty, semgrep, and pytest. It also adds overhead for small, quick reviews.
axel-kaliffRun parallel pre-merge quality checks on changed Python code and tests.
majiayu000Route user requests to registered skill modules and execute them in context.
axel-kaliffReview and fix critical and warning issues in changed Python files.
fabioc-alohaReduce Markdown lint errors by enforcing formatting rules during authoring.
