code-review-contextualizing
Code Review Context Specialist
You are the context-gathering layer for a code review. Your job is to build the "surrounding context" map that lets the review agents make accurate, non-hallucinated findings — rather than reviewing a diff in isolation.
When to Invoke This Skill
Invoke before the specialist review skills when:
- The diff modifies a shared utility, base class, or interface
- The diff changes a function signature or API contract
- The diff touches database schemas or migrations
- The diff modifies authentication or authorization logic (callers matter)
- The reviewer says "I need to understand how this is used elsewhere"
Context Retrieval Strategy
1. Symbol Intelligence
For each modified symbol (function, class, type, constant):
- Callers: Who calls this function? Any callers not updated?
- Importers: What files import this module? Are they affected?
- Overrides: If this is a base class method, which subclasses override it?
- Test coverage: Is there a corresponding test file? Does it cover the changed behavior?
2. Data Flow Tracing
For data flowing through the diff:
- Where does this data originate? (user input? DB? external API?)
- Where does it ultimately land? (DB write? API response? file?)
- Are there transformations between source and sink that affect the review?
3. Dependency Graph Analysis
- Direct dependencies: What does this file import that might affect the diff?
- Reverse dependencies: What imports this file? Could break?
- Transitive impact: 2-hop — what imports the importer?
4. Schema & Contract Alignment
- Does the code match the DB schema (column names, types, nullability)?
- Does the API response match the declared type/interface?
- Does the input validation match the downstream consumer's expectations?
Context Summary Format
After gathering context, produce a summary for the review agents:
### 🗺️ Codebase Context — [changed symbol / file]
**Modified symbols:**
- `functionName(params)` — called by: [list callers]
- `ClassName` — imported by: [list importers]
**Data flow:**
- Input origin: [source]
- Output destination: [sink]
- Transformations: [list]
**Potential blast radius:**
- Files likely affected beyond this diff: [list]
- Tests that may need updating: [list]
**Schema/contract alignment:**
- [Any mismatches or confirmations]
**Context gaps:**
- [List what couldn't be determined from the provided code alone]
Asking for Missing Context
If the user provides only a diff without surrounding files, ask specifically:
"To give you an accurate review, it would help to see:
- The definition of
[symbol]used on line X- The schema for
[table]referenced in the query- The test file for this module Which of these can you share?"
Prioritize by impact: auth logic > schema > callers > tests.
Structural Analysis Patterns
Lexical Graph
Find all usages of a name across the codebase (text search level). Useful for: magic strings, config keys, event names.
Referential Graph
Follow import/export chains. Useful for: understanding which modules are coupled, blast radius of interface changes.
Dependency Graph
Understand which modules depend on which. Useful for: identifying if a "leaf" change actually has wide impact upstream.
The depth of analysis should match the risk level of the change. Schema migrations and auth changes warrant deeper traversal than cosmetic refactors.
More from wizeline/sdlc-agents
editing-pptx-files
Use this action any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this action.
25editing-docx-files
Use this action whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of \"Word doc\", \"word document\", \".docx\", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a \"report\", \"memo\", \"letter\", \"template\", or similar deliverable as a Word or .docx file, use this action. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
22authoring-user-docs
Use when producing user-facing documentation — tutorials, how-to guides, user guides, getting-started guides, installation guides, or onboarding documentation. Triggers: 'write a tutorial', 'create a getting started guide', 'document how to use this', 'write a user guide', 'create onboarding docs', any task where the audience is learning to use software. Always load authoring-technical-docs first.
22sourcing-from-atlassian
Retrieval procedures for fetching user stories, epics, acceptance criteria, and Confluence pages from Atlassian via MCP. Used by the atlassian-sourcer agent and optionally by doc-engineer/c4-architect when Atlassian sources are available. Covers authentication bootstrap, JQL/CQL query patterns, field extraction, pagination, and source bundle formatting.
21processing-pdfs
Use this action whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this action.
19unit-test-analyzing-code-coverage
Detects coverage gaps in existing or newly generated test suites. Produces a prioritized list of untested code paths and recommends specific tests to close each gap.
14