Development Skill
Angular Migration
Migrate from AngularJS to Angular using hybrid mode, incremental component rewriting, and…
$15
Code Review Excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and…
Code Review Excellence transforms pull-request reviews from gatekeeping into knowledge sharing, catching bugs and security issues early while keeping team morale intact. It gives reviewers a structured four-phase process, severity-labeled feedback (blocking, important, nit) and a question-driven, empathy-first communication style that teaches rather than commands. The result is faster review cycles, fewer regressions, and a review culture that mentors junior developers instead of demoralizing them.
$15 one-time
Add to a kit → Prices include 20% VAT. · Forged on real agency work · one-time, no lock-in
- Type Skill
- Category Development
- Delivery Email · instant
- License One-time
Inside the run · no black box
See the actual work before you buy it.
The skill runs a timed four-phase review loop on every pull request. No vibes-based approving, this is the actual pass it makes:
- Context gathering (2-3 min): reads the PR description and linked issue, checks CI status, and measures PR size. Anything over 400 lines gets a split request before any line is reviewed.
- High-level pass (5-10 min): judges whether the solution fits the problem, whether a simpler approach exists, whether files land in the right places, and whether the testing strategy covers edge cases.
- Line-by-line pass (10-20 min): per file it hunts logic bugs (off-by-one, null checks, race conditions), security holes (injection, auth checks, secret leaks), performance traps (N+1 queries, blocking I/O) and maintainability issues.
- Every comment gets a severity label: [blocking] for security or data-loss risk, [important] for should-fix, [nit] for preference, plus [suggestion], [learning] and [praise]. Unlabeled feedback is not allowed because it stretches review cycles by days.
- Feedback is phrased as questions and suggestions, not commands: "What happens if items is an empty array?" instead of "This is wrong." Formatting nits are left to linters, never to humans.
- Closes with a summary and an explicit verdict: approve, comment, or request changes, with an offer to pair on anything complex.
One power source. 6 lines out.
code-review-excellence · core
core active · 6 lines
- ✓ reviewing pull requests
Reviewing pull requests with a structured process
- ✓ establishing team-wide c…
Establishing team-wide code review standards
- ✓ mentoring junior develop…
Mentoring junior developers through reviews
- ✓ security and architecture
Security and architecture reviews
- ✓ reducing review cycle time
Reducing review cycle time with severity labels
- ✓ building review checklists
Building review checklists and PR comment templates
Yours to keep.
Drag time forward. Watch what stays.
Forever
That's what owning means.
The rented stack
ai writing tool: subscription
expired · access lostanalytics suite: subscription
expired · access lostdesign platform: subscription
expired · access lost(nothing left)
Your forge
-
Catch bugs, race conditions and security holes before they ship
license: perpetual -
Cut review cycle time with clear blocking/important/nit labels
license: perpetual -
Reviews that mentor and motivate instead of demoralize
license: perpetual -
Right-sized scrutiny via blast-radius analysis on every PR
license: perpetual
subscriptions expire · deeds don't
Everything in the box.
Pick a piece up. Watch it work.
Four-phase review process from context gathering to final verdict
6 parts · one working system · ships instantly by email
This wasn't forged for everyone.
- Not for you if you'd rather rent a tool than own one.
- Not for you if you want someone else to run your stack.
- Not for you if you're happy guessing.
Engineering teams and tech leads who want reviews that catch real defects, move quickly, and grow developers rather than gatekeep them.
then this was forged for you.Works with
Universal by design: these run in any AI. Delivered in the open Agent Skills + MCP format (native in Claude); ChatGPT, Gemini, Cursor and Copilot adapt the same files their own way.
- Claude Native format
- ChatGPT Adapts via open standards
- Gemini Adapts via open standards
- Cursor Adapts via open standards
- Copilot Adapts via open standards
Catch what's on your mind.
the air is clear. nothing between you and the forge.
catch a spark: the forge will answer
-
Is this a tool that scans my pull requests, or a way of reviewing?
It is a structured method: a four-phase review process with severity-labeled feedback you apply to your own pull requests. It shapes how the review reads, so it fits whatever platform your PRs already live on.
-
Does labeling feedback as blocking, important or nit really speed things up?
It does, because the author instantly sees what must change versus what is a preference, instead of treating every comment as a wall. A nit no longer stalls a merge, and a real defect is not lost in the noise.
-
Does this catch every bug so I can skip a careful look?
No, it makes a human review sharper and kinder, it does not replace the reviewer's judgment. It raises the odds of catching real defects, but the reading still has to happen.
-
How is it delivered?
By email right after purchase: ready to run, downloaded instantly, no setup wait.
-
One-time or subscription?
A one-time purchase; no subscription or hidden fees. VAT (20%) is included.
-
Can I get a refund?
As a digital product, it can’t be refunded once downloaded. That’s why we show exactly what’s inside and who it’s for, right here.