Source profileQuality 69/100

yun520-1/mark-heartflow-skill/skills/pr-reviewer/SKILL.md

pr-reviewer

Automated GitHub PR code review with diff analysis, lint integration, and structured reports. Use when reviewing pull requests, checking for security issues, error handling gaps, test coverage, or code style problems. Supports Go, Python, and JavaScript/TypeScript. Requires `gh` CLI authenticated with repo access.

Source repository stars
36
Declared platforms
0
Static risk flags
1
Last source update
2026-07-28
Source checked
2026-07-28

Decision brief

What it does—and where it fits

Automated code review for GitHub pull requests. Analyzes diffs for security issues, error handling gaps, style problems, and test coverage.

Best for

  • Use when reviewing pull requests, checking for security issues, error handling gaps, test coverage, or code style problems.

Not for

  • Tasks that require unconfirmed production actions or broad system permissions.
  • Environments where the pinned source and install steps cannot be inspected.

Compatibility matrix

Platform support, with evidence labels

PlatformStatusEvidenceWhat to check
CodexNot declaredNo explicit evidencePortability before use
Claude CodeNot declaredNo explicit evidencePortability before use
CursorNot declaredNo explicit evidencePortability before use
Gemini CLINot declaredNo explicit evidencePortability before use
Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource
npx skills add https://github.com/yun520-1/mark-heartflow-skill --skill "skills/pr-reviewer"
Safe inspection promptEditorial

Inspect the Agent Skill "pr-reviewer" from https://github.com/yun520-1/mark-heartflow-skill/blob/20bbbb4eacf56c941ddc3420dcbc81c04d55ec5c/skills/pr-reviewer/SKILL.md at commit 20bbbb4eacf56c941ddc3420dcbc81c04d55ec5c. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

  1. 01

    Quick Start

    Review the “Quick Start” section in the pinned source before continuing.

    Review and apply the “Quick Start” source section.
  2. 02

    Review all open PRs in current repo

    scripts/github/pr-reviewer.sh check

    scripts/github/pr-reviewer.sh check
  3. 03

    Review a specific PR

    scripts/github/pr-reviewer.sh review 42

    scripts/github/pr-reviewer.sh review 42
  4. 04

    Post review as GitHub comment

    scripts/github/pr-reviewer.sh post 42

    scripts/github/pr-reviewer.sh post 42

Permission review

Static risk signals and limitations

Reads files

low · line 14

The documentation asks the agent to read local files, directories, or repositories.

# Review all open PRs in current repo

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial
SignalValueEvidence typeMeaning
Quality score69/100ComputedDocumentation, specificity, maintenance, and trust rules
Repository stars36SourceRepository attention, not individual Skill quality
Compatibility0 platformsSourceDeclared in the catalog source record
Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository
yun520-1/mark-heartflow-skill
Skill path
skills/pr-reviewer/SKILL.md
Commit
20bbbb4eacf56c941ddc3420dcbc81c04d55ec5c
License
Not declared
Collected
2026-07-28
Default branch
main
View the original SKILL.md

PR Reviewer

Automated code review for GitHub pull requests. Analyzes diffs for security issues, error handling gaps, style problems, and test coverage.

Prerequisites

  • gh CLI installed and authenticated (gh auth status)
  • Repository access (read at minimum, write for posting comments)
  • Optional: golangci-lint for Go linting, ruff for Python linting

Quick Start

# Review all open PRs in current repo
scripts/github/pr-reviewer.sh check

# Review a specific PR
scripts/github/pr-reviewer.sh review 42

# Post review as GitHub comment
scripts/github/pr-reviewer.sh post 42

# Check status of all open PRs
scripts/github/pr-reviewer.sh status

# List unreviewed PRs (useful for heartbeat/cron integration)
scripts/github/pr-reviewer.sh list-unreviewed

Configuration

Set these environment variables or the script auto-detects from the current git repo:

  • PR_REVIEW_REPO — GitHub repo in owner/repo format (default: detected from gh repo view)
  • PR_REVIEW_DIR — Local checkout path for lint (default: git root of cwd)
  • PR_REVIEW_STATE — State file path (default: ./data/pr-reviews.json)
  • PR_REVIEW_OUTDIR — Report output directory (default: ./data/pr-reviews/)

Directories Written

  • PR_REVIEW_STATE (default: ./data/pr-reviews.json) — Tracks reviewed PRs and their HEAD SHAs
  • PR_REVIEW_OUTDIR (default: ./data/pr-reviews/) — Markdown review reports

What It Checks

CategoryIconExamples
Security🔴Hardcoded credentials, AWS keys, secrets in code
Error Handling🟡Discarded errors (Go _ :=), bare except: (Python), unchecked Close()
Risk🟠panic() calls, process.exit()
Style🔵fmt.Print/print()/console.log in prod, very long lines
TODOs📝TODO, FIXME, HACK, XXX markers
Test Coverage📊Source files changed without corresponding test changes

Smart Re-Review

Tracks HEAD SHA per PR. Only re-reviews when new commits are pushed. Use review <PR#> to force re-review.

Report Format

Reports are saved as markdown files in the output directory. Each report includes:

  • PR metadata (author, branch, changes)
  • Commit list
  • Changed file categorization by language/type
  • Automated diff findings with file, line, category, and context
  • Test coverage analysis
  • Local lint results (when repo is checked out locally)
  • Summary verdict: 🔴 SECURITY / 🟡 NEEDS ATTENTION / 🔵 MINOR NOTES / ✅ LOOKS GOOD

Heartbeat/Cron Integration

Add to a periodic check (heartbeat, cron job, or CI):

UNREVIEWED=$(scripts/github/pr-reviewer.sh list-unreviewed)
if [ -n "$UNREVIEWED" ]; then
  scripts/github/pr-reviewer.sh check
fi

Extending

The analysis patterns in the script are organized by language. Add new patterns by appending to the relevant pattern list in the analyze_diff() function:

# Add a new Go pattern
go_patterns.append((r'^\+.*os\.Exit\(', 'RISK', 'Direct os.Exit() — consider returning error'))

Alternatives

Compare before choosing

Computed 6736

yun520-1/mark-heartflow-skill

code-error-fixer

Systematic code error diagnosis and fix skill. Handles compilation errors, runtime exceptions, type errors, logic bugs, crash analysis, dependency conflicts, and unexpected behavior. TRIGGER when: user reports an error/exception/bug/crash, build or test failures, unexpected behavior in code, type errors, runtime stack traces, dependency resolution failures, or asks "why is this not working" / "fix this error" / "debug this". DO NOT TRIGGER when: user asks for code review without errors, general

Computed 8610,762

Jeffallan/claude-skills

code-reviewer

Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural concerns, then produces a structured review report with prioritized, actionable feedback. Use when reviewing pull requests, conducting code quality audits, identifying refactoring opportunities, or checking for security issues. Invoke for PR reviews, code quality checks, refactoring suggestions, review code, code quali

Computed 85234,327

affaan-m/ECC

dmux-workflows

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

Computed 83234,327

affaan-m/ECC

dmux-workflows

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.