diff-reviewer
Review generated diffs/patches for correctness, safety, and alignment with evidence. Use when the user requests diff reviewer or invokes diff-reviewer. Do NOT use as deployment authorization or as evidence for checks that were not executed.
- License 许可
- CC-BY-4.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- diff-reviewer
- license
- CC-BY-4.0
- metadata
- { "author": "AEOS", "version": "1.0.0", "owner_agent": "codenavi-agent" }
- description
- Review generated diffs/patches for correctness, safety, and alignment with evidence. Use when the user requests diff reviewer or invokes diff-reviewer. Do NOT use as deployment authorization or as evidence for checks that were not executed.
02 资源文件 1
- 参考文档references/provenance.md531 B
03 SKILL.md 正文
Diff Reviewer Skill
Governance: CodENavi Full Workspace v2. Skill of codenavi-agent; inherit AGENTS.md.
Lifecycle: BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF.
Source roles/workers are internal lenses. Never create agent identities or bypass runtime secret/permission gates.
ID: diff-reviewer Version: 1.0.0 Owner Agent: codenavi-agent Risk Level: low
Mission
Review generated diffs/patches for correctness, safety, and alignment with evidence.
Scope
- Read proposed.patch files
- Validate diff syntax and structure
- Check that changes align with issue description
- Identify potential issues in proposed changes
Allowed Actions
filesystem.read— read patch files and source filesgenerate_evidence— register review findings
Forbidden Actions
- Modify patch files
- Apply patches
- Change patch content
Required Capabilities
- READ_REPOSITORY
- REVIEW_DIFF
- GENERATE_REPORT
Required Evidence
- Patch file reviewed (SHA-256)
- Source files referenced (SHA-256)
- Review report
Prompt Contract
- State the objective, target scope, assumptions and constraints before execution.
- Use only evidence-backed facts; mark uncertainty explicitly.
- Route tool access through approved command, MCP or Tool Router paths.
- Redact secrets, credentials, tokens and sensitive values.
- Return facts, assumptions, risks, recommendations, evidence_refs and blocking_conditions when applicable.
- Stop when required evidence, permissions, policy approval or input context is missing.
Quality Gates
- Every review claim must reference specific diff lines
- False positives must be marked as Assumption, not Fact
Blocking Conditions
- Patch references non-existent files
- Patch contains syntax errors in diff format
Examples of Allowed Behavior
- Review that proposed.patch correctly fixes the target issue
- Identify that a proposed change would break API compatibility
Examples of Forbidden Behavior
- Editing the patch to fix issues
- Approving the patch for application
Provenance and source freshness: provenance.
04 同仓库更多 Skills
workspace-brain
Operate the CodENavi workspace brain MCP and CLI — cloud DeepSeek RAG, disk corpus at WORKSPACE_BRAIN_ROOT, Jev URL curation, and event logging for Cursor/Codex/OpenCode/Claude. Use when ingesting repo knowledge, asking the brain, mapping web seeds, or recording AI-driven file changes. Do NOT use for local Ollama RAG or storing API keys in git.
workbench-profile-resolver
Provide enterprise-grade capability for `workbench-profile-resolver` inside AEOS v1.1. Use when the user requests workbench profile resolver or invokes workbench-profile-resolver. Do NOT use for unrelated tools or unapproved remote writes.
wordpress-expert
Staff-level WordPress engineering super-skill for one-shot site mapping, clean-code AI-assisted project creation/modification, the complete installed plugin universe, governed remote wp-admin operations, themes/blocks/layout, third-party integrations and production-safe changes. Use when the user requests wordpress expert or invokes wordpress-expert. Do NOT use for unrelated languages, domains or production deployment.
whatsapp-simulator
Generate synthetic WhatsApp-style conversation fixtures for testing conversational systems, support flows and automation. Use when the user requests whatsapp simulator or invokes whatsapp-simulator. Do NOT use for unrelated tools or unapproved remote writes.
web-quality-audit
Assimilated TLC/web-quality multi-area audit. Review performance, accessibility, SEO and best practices in one pass. Triggers: audit my site, review web quality, check page quality, optimize my website across areas. Do not use for a single-area job (core-web-vitals, ai-seo, best-practices, perf-lighthouse).
voiceai
Provide an evidence-backed voice interface for AEOS. Activating this skill is treated as explicit current-session consent for `voiceai` to record user audio or transcribe audio from user-authorized audio/video media within the declared scope. The skill can: Use when the user requests voiceai or invokes voiceai. Do NOT use for unrelated tools or unapproved remote writes.