Proven skills / Compare

Testing vs Design · both proven

differential-review vs improve-codebase-architecture

Both skills were run through Claude twice: once on a fixed brief without the skill, once with it. The briefs differ because each is written for the job the skill claims to do, so compare each skill against its own baseline, then decide which difference matters for your work. They are in different categories, so this is a choice of job, not a head-to-head on the same job.

differential-review

Performs security-focused differential review of code changes. Adapts analysis depth to codebase size, uses git blame for context, calculates blast radius by counting callers, checks test coverage of modified code, and generates a markdown report. Use when reviewing a PR, commit, or diff for security vulnerabilities, checking whether a change re-introduces a previously fixed bug, asking what else…

Category
Testing
Source
trailofbits/skills
License
Other
Proof model
claude-opus-5-5
Brief
“Do a security-focused review of this change and present it as a single HTML page. Commit: "Allow admins to impersonate users for support" +app.get('/admin/impersonate/:id', async (req, res) => { + if (req.cookies.role !== 'admin') return res.sendStatus(403); + const user = await User.findById(req.params.id); + req.session.userId = user.id; + res.redirect(req.query.next || '/'); +});”
Skill commit
2be6433
Without the skillWith differential-review
⇆
Without, runWith differential-review, run3 independent runs per side, none selected by hand.

Download the with-skill page

improve-codebase-architecture

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Category
Design
Source
mattpocock/skills
License
MIT
Proof model
claude-opus-5-5
Brief
“Here is the orders module of a small Express app. ```js // orders.js const db = require("./db"); const stripe = require("stripe")(process.env.STRIPE_KEY); const mailer = require("./mailer"); async function createOrder(req, res) { const { items, couponCode } = req.body; if (!req.user) return res.status(401).end(); let total = 0; for (const i of items) { const p = await db.query("select price, stock from products where id = $1", [i.id]); if (p.rows[0].stock < i.qty) return res.status(409).json({ error: "out of stock" }); total += p.rows[0].price * i.qty; } if (couponCode) { const c = await db.query("select pct, expires from coupons where code = $1", [couponCode]); if (c.rows[0] && new Date(c.rows[0].expires) > new Date()) total = total * (1 - c.rows[0].pct / 100); } const charge = await stripe.paymentIntents.create({ amount: Math.round(total * 100), currency: "usd", customer: req.user.stripeId, confirm: true }); const o = await db.query("insert into orders (user_id, total, status) values ($1, $2, $3) returning id", [req.user.id, total, charge.status]); for (const i of items) await db.query("update products set stock = stock - $1 where id = $2", [i.qty, i.id]); await mailer.send(req.user.email, "Order " + o.rows[0].id, "Thanks! Total: $" + total.toFixed(2)); res.json({ id: o.rows[0].id, total }); } module.exports = { createOrder }; ``` The team keeps breaking checkout when they change coupons or stock rules, and the code is hard to test. Review the architecture and present your findings as a single HTML report: the problems you see, the changes you recommend in order of value, and what the code would look like after the most important change.”
Skill commit
5beb35b
Without the skillWith improve-codebase-architecture
⇆
Without, runWith improve-codebase-architecture, run3 independent runs per side, none selected by hand.

Download the with-skill page

We don’t pick a winner for you: the pages are the evidence. Both proofs can be repeated with the brief, model and commit shown above. See alternatives to differential-review or alternatives to improve-codebase-architecture.