Adr Review
技能 活跃Review code changes against accepted ADRs for compliance violations
To automate the review of code changes against established Architecture Decision Records, ensuring architectural consistency and compliance before code merges.
功能
- Reviews code changes against ADRs
- Detects compliance violations and drift
- Supports specified branches for diff analysis
- Generates a structured compliance report
使用场景
- Before merging a Pull Request
- During periodic compliance checks
- After significant code refactoring
非目标
- Performing code style checks
- Identifying security vulnerabilities
- Generating new ADRs
Documentation
- info:Configuration & parameter referenceThe SKILL.md mentions an optional `--branch` parameter but does not explicitly document its default value or behavior.
Trust
- warning:Issues AttentionWith 68 issues opened and 373 closed in the last 90 days, the closure rate is approximately 35%, suggesting maintainers may be slow to address issues.
Code Execution
- info:ValidationWhile the skill uses specific tools and queries, it's unclear if input arguments like file paths or branch names are strictly validated against a schema.
- info:Error HandlingThe SKILL.md outlines a reporting structure for violations, but it does not explicitly detail how specific error conditions (e.g., malformed ADRs, git errors) are caught and handled with structured output.
Errors
- info:Actionable error messagesThe report structure in step 6 provides a good overview of findings, but specific error messages for individual tool failures or ADR parsing issues are not detailed.
Practical Utility
- info:Usage examplesWhile the workflow steps are clear, there are no explicit end-to-end examples showing sample input, invocation, and expected output.
- info:Edge casesThe skill outlines failure modes implicitly (e.g., finding ADRs, checking violations), but does not explicitly document specific failure modes with observable symptoms and recovery steps.
Safety
- info:Halt on unexpected stateWhile the workflow implies halting on certain conditions (e.g., unable to find ADRs), there's no explicit machine-readable checklist of preconditions or documented rollback procedures.
安装
请先添加 Marketplace
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-adr@ruflo质量评分
类似扩展
Prepare Inspection Readiness
100Prepare an organisation for regulatory inspection by assessing readiness against agency-specific focus areas (FDA, EMA, MHRA). Covers warning letter and 483 theme analysis, mock inspection protocols, document bundle preparation, inspection logistics, and response template creation. Use when a regulatory inspection has been announced or is anticipated, when a periodic self-assessment is due, when new systems have been implemented since the last inspection, or after a significant audit finding that may attract regulatory attention.
Master Claude for Legal
100Master skill for legal teams using Claude. Loads the right reference for the user's question (privilege configuration, MCP hardening, verification, long documents, practice-area patterns, skill authoring) and routes to specialized starter skills (NDA triage, version diff, meeting brief, citation verification, status synthesis). Auto-invokes when the user mentions legal work, contracts, redlines, NDAs, privilege, attorney-client, court filings, depositions, regulatory compliance, or asks how to set up Claude for a law firm or in-house legal team.
Create Pull Request
99Create and manage pull requests using GitHub CLI. Covers branch preparation, writing PR titles and descriptions, creating PRs, handling review feedback, and merge/cleanup workflows. Use when proposing changes from a feature or fix branch for review, merging completed work into the main branch, requesting code review from collaborators, or documenting the purpose and scope of a set of changes.
Git Commit
99Create a git commit with a good message. Use when the user says "commit", "save changes", "commit this", or asks to create a commit after making code changes.
Review Pull Request
100Review a pull request end-to-end using GitHub CLI. Covers diff analysis, commit history review, CI/CD check verification, severity-leveled feedback (blocking/suggestion/nit/praise), and gh pr review submission. Use when a pull request is assigned for review, performing a self-review before requesting others' input, conducting a second review after feedback is addressed, or auditing a merged PR for post-merge quality assessment.
Oh My Claudecode
100Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly