differential-review
Review a commit, pull request, patch, or branch difference for security and reliability regressions by understanding both the changed lines and their…
Skill by NeroWasTrolled
Chalk Labs
Need help deploying differential-review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/nerowastrolled-differential-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: 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/differential-review
What's inside
- Skill name
differential-review- Description
- Review a commit, pull request, patch, or branch difference for security and reliability regressions by understanding both the changed lines and their surrounding execution paths.
- License
- MIT
- Instructions
- 17 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Differential Review Anchor the review to a verified base and target revision. 1. Summarize the intended change from the diff, tests, issue, and affected architecture. 2. Identify new or changed trust boundaries, privileges, inputs, side effects, dependencies, configuration, migrations, and error behavior. 3. Trace callers and callees beyond the diff when they determine exploitability or correctness. 4. Look for removed validation, widened access, fail-open behavior, unsafe defaults, partial updates, concurrency changes, and missing negative tests. 5. Validate each issue against the full resulting code, not an isolated hunk. Report findings first, ordered by severity, with file or symbol evidence, scenario, impact, confidence, and remediation. Separate pre-existing issues from regressions introduced by the change. If no issue is found, state the reviewed scope and blind spots.
From NeroWasTrolled/gabriel-ai-devkit, MIT.
More from NeroWasTrolled/gabriel-ai-devkit
- 0.524score
product-gamification
NeroWasTrolled
Design, critique, or implement ethical gamification for non-game products using meaningful progress, goals, feedback, mastery, narrative, rewards, and social…
SkillBFreshness: BClaude Code +9 - 0.521score
game-playtest
NeroWasTrolled
Playtest an authorized game or gamified product to evaluate onboarding, controls, feedback, pacing, progression, balance signals, failure recovery…
SkillBFreshness: BClaude Code +9 - 0.521score
game-ui-frontend
NeroWasTrolled
Design or implement game-inspired web interfaces, HUDs, progression displays, rewards, status feedback, motion, and information-dense states without…
SkillBFreshness: BClaude Code +9 - 0.521score
modern-python
NeroWasTrolled
Create, review, or modernize Python applications and backend services using current typing, packaging, testing, linting, async, and dependency practices while…
SkillBFreshness: BClaude Code +9 - 0.521score
property-based-testing
NeroWasTrolled
Design or review generative tests for parsers, validators, transformations, state machines, calculations, permissions, and business rules.
SkillBFreshness: BClaude Code +9 - 0.521score
postgres-best-practices
NeroWasTrolled
Design, review, or optimize PostgreSQL schemas, queries, indexes, transactions, migrations, connections, and row-level security.
SkillBFreshness: BClaude Code +9 - 0.521score
security-guidance
NeroWasTrolled
Provide lightweight security guidance while implementing or reviewing application changes, focusing on the changed trust boundaries and common high-impact…
SkillBFreshness: BClaude Code +9 - 0.521score
sharp-edges
NeroWasTrolled
Review an API, configuration surface, library, or developer workflow for misuse-prone defaults and interfaces where the easiest path can create security or…
SkillBFreshness: BClaude Code +9 - 0.521score
claude-security
NeroWasTrolled
Conduct an authorized, deep application security review using the native Claude Security capability when available, with a portable evidence-driven fallback…
SkillBFreshness: BClaude Code +9 - 0.521score
codex-security
NeroWasTrolled
Conduct an authorized, deep application security review using the native Codex Security capability when available, with a portable evidence-driven fallback…
SkillBFreshness: BClaude Code +9 - 0.516score
frontend-app-builder
NeroWasTrolled
Build a complete frontend feature or small web application from a product brief, combining interaction design, maintainable implementation, responsive states…
SkillBFreshness: BClaude Code +9 - 0.516score
audit
NeroWasTrolled
Audit a rendered product experience for usability, information architecture, accessibility, friction, trust, and consistency.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 3, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from NeroWasTrolled
- 0.524score
product-gamification
NeroWasTrolled
Design, critique, or implement ethical gamification for non-game products using meaningful progress, goals, feedback, mastery, narrative, rewards, and social…
SkillBFreshness: BClaude Code +9 - 0.521score
postgres-best-practices
NeroWasTrolled
Design, review, or optimize PostgreSQL schemas, queries, indexes, transactions, migrations, connections, and row-level security.
SkillBFreshness: BClaude Code +9 - 0.521score
game-ui-frontend
NeroWasTrolled
Design or implement game-inspired web interfaces, HUDs, progression displays, rewards, status feedback, motion, and information-dense states without…
SkillBFreshness: BClaude Code +9 - 0.521score
modern-python
NeroWasTrolled
Create, review, or modernize Python applications and backend services using current typing, packaging, testing, linting, async, and dependency practices while…
SkillBFreshness: BClaude Code +9 - 0.521score
game-playtest
NeroWasTrolled
Playtest an authorized game or gamified product to evaluate onboarding, controls, feedback, pacing, progression, balance signals, failure recovery…
SkillBFreshness: BClaude Code +9 - 0.521score
codex-security
NeroWasTrolled
Conduct an authorized, deep application security review using the native Codex Security capability when available, with a portable evidence-driven fallback…
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get differential-review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
differential-review skill. Agent Mart. https://agentmart.dev/skills/nerowastrolled-differential-review (last updated 2026-10-24)