一键导入
diff-analyze
Analyze git diffs for risk scoring, reviewer recommendations, and change classification
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Analyze git diffs for risk scoring, reviewer recommendations, and change classification
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | diff-analyze |
| description | Analyze git diffs for risk scoring, reviewer recommendations, and change classification |
| argument-hint | [ref] (a git ref e.g. HEAD~1, main..feature, or a commit hash; defaults to HEAD) |
| allowed-tools | mcp__ruflo__analyze_diff mcp__ruflo__analyze_diff-risk mcp__ruflo__analyze_diff-classify mcp__ruflo__analyze_diff-reviewers mcp__ruflo__analyze_diff-stats mcp__ruflo__analyze_file-risk Bash |
Analyze git diffs for risk, complexity, and reviewer assignment.
Before submitting a PR or after making significant changes, analyze the diff to understand risk level, get reviewer recommendations, and classify the type of change.
mcp__ruflo__analyze_diff with a ref arg (a git ref to compare against, e.g. HEAD~1, main..feature, or a commit hash; defaults to HEAD) for a comprehensive analysismcp__ruflo__analyze_diff-risk for a quantified risk assessmentmcp__ruflo__analyze_diff-classify to categorize (feature, bugfix, refactor, etc.)mcp__ruflo__analyze_diff-reviewers for recommended reviewers based on code ownershipmcp__ruflo__analyze_diff-stats for line counts, file counts, complexity metricsmcp__ruflo__analyze_file-risk for per-file risk breakdownBuild or rebuild the ADR index + dependency graph in AgentDB by running the in-process `agentdb index` command (one cold-start, all surfaces in one pass — no per-record npx round-trips). Handles v3-style and plugin-style ADR formats.
Create a new Architecture Decision Record with sequential numbering and AgentDB registration
Hive Mind orchestration patterns — queen-led multi-agent coordination with Byzantine/Raft/Gossip/CRDT consensus, typed collective memory, dialectic council, and session checkpoint/resume. Use for decision-bearing work; use swarm-advanced for parallel execution without consensus.
Detect missing test coverage and generate test suggestions
Hive Mind orchestration patterns — queen-led multi-agent coordination with Byzantine/Raft/Gossip/CRDT consensus, typed collective memory, dialectic council, and session checkpoint/resume. Use for decision-bearing work; use swarm-advanced for parallel execution without consensus.
Transfer learned patterns from another project on disk into this one -- the project-to-project pattern transfer that hooks_transfer performs