principal-engineer-review
Review local diffs and design changes from a principal engineer standpoint: MVP scope, correctness, maintainability, security, reliability, and reuse of…
Skill by veverkap
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/veverkap-principal-engineer-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/principal-engineer-review
Tools it pre-approves 5
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
ReadGlobGrepBashAgent
What's inside
- Skill name
principal-engineer-review- Description
- Review local diffs and design changes from a principal engineer standpoint: MVP scope, correctness, maintainability, security, reliability, and reuse of existing primitives.
- License
- MIT
- Allowed tools
- Read, Glob, Grep, Bash, Agent
- Instructions
- 69 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves any shell command
Files (4)
- SKILL.md
- README.md · evals/
- evals.json · evals/
- trigger-queries.json · evals/
SKILL.md (first lines)
# Principal Engineer Review ## Mission Provide a high-signal review of local changes with emphasis on business impact and long-term maintainability. ## Scope - Review current local diff and adjacent context. - Focus on material risks, not style trivia. ## Review Workflow 1. Discover review context. - Read the current branch with `git branch --show-current`. - Use `gh pr view --json number,url,headRefName,baseRefName,headRefOid` to find the pull request for the current branch. - Treat a PR as present only when `headRefName` matches the current branch. If `gh` is unavailable, unauthenticated, or no matching PR exists, continue with the local review and markdown output. 2. Understand intent. - What business problem is being solved now? - What is explicitly out of scope? 3. Inspect changed behavior. - correctness and edge cases - authorization and data handling - error paths and rollback behavior - coupling, ownership, and maintenance burden 4. Check for overbuilding. - speculative abstractions - premature optimization - unnecessary dependencies - duplicate primitives instead of reuse 5. Validate evidence. - tests for changed behavior - operational safety (timeouts, retries, idempotency where relevant) - migration/deploy safety where relevant 6. Produce decision. - ready for handoff - needs changes before handoff ## Output Format If a matching PR exists: - Do not create or update `reports/principal-engineer-review.md`. - Add one inline PR review comment for each blocking or non-blocking finding when its location is commentable in the PR diff. Include the risk and concrete fix direction. - Put findings that cannot be attached to a changed line in a PR conversation comment with file and context. - Add a final PR conversation comment containing the decision, a concise findings summary, what looks right, and suggested next steps. - Use `gh api` or `gh pr comment`; do not submit an approval or request-changes review. If no matching PR exists, write `reports/principal-engineer-review.md` with: - Decision - Blocking findings (ordered by severity) - Non-blocking findings - What looks right - Suggested next steps Each finding should include: file, line/context, risk, and concrete fix direction. ## Guardrails - Prefer smallest responsible change. - Require evidence for claims. - Do not invent requirements not implied by the change. - Keep feedback concise and actionable.
From veverkap/skills, MIT.
More from veverkap/skills
- 0.524score
duplicate-code-detector
veverkap
Detect significant duplicate code patterns in recently changed files using semantic analysis and open focused remediation issues (one per pattern, up to 3).
SkillBFreshness: BClaude Code +9 - 0.521score
ci-coach
veverkap
Analyze local CI workflow definitions, identify low-risk efficiency improvements, implement focused updates, and generate a data-backed optimization report.
SkillBFreshness: BClaude Code +9 - 0.521score
code-simplifier
veverkap
Analyze recently modified local code and simplify it for clarity and maintainability while preserving behavior.
SkillBFreshness: BClaude Code +9 - 0.521score
grumpy-reviewer
veverkap
Perform a critical, grumpy senior-style review of local diffs, focusing on correctness, security, performance, and maintainability.
SkillBFreshness: BClaude Code +9 - 0.521score
nitpick-reviewer
veverkap
Perform a detailed local diff nitpick review focused on subtle naming, structure, and consistency issues that linters often miss.
SkillBFreshness: BClaude Code +9 - 0.521score
resolve-review-notes
veverkap
Find the GitHub pull request for the current branch, collect and validate all review comments against current code, apply valid fixes, resolve addressed…
SkillBFreshness: BClaude Code +9 - 0.521score
change-fix
veverkap
Diagnose and fix local branch failures or requested issues, verify with project checks, and produce a clear fix summary.
SkillBFreshness: BClaude Code +9 - 0.496score
improve-codebase-architecture
veverkap
Scan a codebase for deepening opportunities, present them as a visual HTML report, then drill into the selected option with concrete interface and migration…
SkillBFreshness: BClaude Code +9 - 0.281score
babysit-changes
veverkap
No description from the publisher yet.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 8, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/veverkap/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from veverkap
- 0.524score
duplicate-code-detector
veverkap
Detect significant duplicate code patterns in recently changed files using semantic analysis and open focused remediation issues (one per pattern, up to 3).
SkillBFreshness: BClaude Code +9 - 0.521score
ci-coach
veverkap
Analyze local CI workflow definitions, identify low-risk efficiency improvements, implement focused updates, and generate a data-backed optimization report.
SkillBFreshness: BClaude Code +9 - 0.521score
code-simplifier
veverkap
Analyze recently modified local code and simplify it for clarity and maintainability while preserving behavior.
SkillBFreshness: BClaude Code +9 - 0.521score
grumpy-reviewer
veverkap
Perform a critical, grumpy senior-style review of local diffs, focusing on correctness, security, performance, and maintainability.
SkillBFreshness: BClaude Code +9 - 0.521score
nitpick-reviewer
veverkap
Perform a detailed local diff nitpick review focused on subtle naming, structure, and consistency issues that linters often miss.
SkillBFreshness: BClaude Code +9 - 0.521score
resolve-review-notes
veverkap
Find the GitHub pull request for the current branch, collect and validate all review comments against current code, apply valid fixes, resolve addressed…
SkillBFreshness: BClaude Code +9
Cite this page
principal-engineer-review skill. Agent Mart. https://agentmart.dev/skills/veverkap-principal-engineer-review (last updated 2026-10-24)