pr-review-enforcer
- Repo stars 1
- Author updated Live
- Author repo claude-skills
- Domain
- Security
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @00PrabalK00 · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: pr-review-enforcer
description: Review diffs like a senior engineer by checking correctness, architectural fit, style, missing t…
category: security
runtime: no special runtime
---
# pr-review-enforcer output preview
## PART A: Task fit
- Use case: Review diffs like a senior engineer by checking correctness, architectural fit, style, missing tests, security smells, and migration or operational risk. Use when asked to review a pull request, patch, staged changes, or proposed code edits..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Overview / Core Workflow / Deliver” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Review diffs like a senior engineer by checking correctness, architectural fit, style, missing tests, security smells, and migration or operational risk. Use when asked to review a pull request, patch, staged changes, or proposed code edits.”.
- **02** When the source has headings, the agent prioritizes “Overview / Core Workflow / Deliver” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “Overview / Core Workflow / Deliver”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: pr-review-enforcer
description: Review diffs like a senior engineer by checking correctness, architectural fit, style, missing t…
category: security
source: 00PrabalK00/claude-skills
---
# pr-review-enforcer
## When to use
- Review diffs like a senior engineer by checking correctness, architectural fit, style, missing tests, security smells…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Overview / Core Workflow / Deliver” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "pr-review-enforcer" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Overview / Core Workflow / Deliver
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Pr Review Enforcer
Overview
Review code with a findings-first mindset instead of a summary-first mindset.
Core Workflow
- Read the diff and the surrounding code before judging the change.
- Look for correctness issues first: regressions, edge cases, state handling, concurrency, data integrity, and compatibility.
- Check architecture and maintainability: layering, ownership boundaries, duplication, naming, and hidden complexity.
- Check safety gaps: missing tests, weak observability, migrations, rollout risk, secrets, and authorization concerns.
- Report findings in priority order with file references and concise reasoning.
Deliver
- Lead with actionable findings, ordered by severity.
- Include open questions only after concrete issues.
- Mention testing gaps and residual risk even when the diff looks sound.
- State explicitly when no findings are discovered.
Guardrails
- Avoid generic praise or style-only comments unless they affect clarity or risk.
- Do not review from the diff alone when nearby code changes the meaning.
- Keep comments specific enough that the author can act on them quickly.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review