Two testing skills · both proven

differential-review vs test-driven-development

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.

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

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

Category: Testing
Source: obra/superpowers
License: MIT
Proof model: claude-opus-5-5
Brief: “Implement a function that parses a cron expression (the standard five fields) and returns the next run time after a given date, in TypeScript. Present the work as a single HTML page with two columns: the test file on the left and the implementation on the right, each in a code block, with a short note at the top on the order you did things in and anything you decided not to support.”
Skill commit: bb92a77

Without the skillWith test-driven-development

⇆

Without, runWith test-driven-development, 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 test-driven-development.