Back to All Tags
Tag • 18 Prompts

#Code Review

Explore all AI prompts tagged with #Code Review.

Prompts tagged with #Code Review

Claude

A debugging discipline in prompt form: hypotheses with evidence both ways and a cheapest-experiment step, with fixes explicitly forbidden until confirmation. Cuts wild-goose-chase time dramatically on unfamiliar codebases.

▸ ready to run
Claude

A debugging discipline in prompt form: hypotheses with evidence both ways and a cheapest-experiment step, with fixes explicitly forbidden until confirmation. Cuts wild-goose-chase time dramatically on unfamiliar codebases.

Stack Trace Hypothesis Ranker

A debugging discipline in prompt form: hypotheses with evidence both ways and a cheapest-experiment step, with fixes explicitly forbidden until confirmation. Cuts wild-goose-chase time dramatically on unfamiliar codebases.

1.5K240
Claude

A performance-review prompt that forces ranking by impact before any fix, which stops the usual memo-everything reflex. The minimal-fix constraint keeps diffs reviewable. Paste one component at a time for best results.

▸ ready to run
Claude

A performance-review prompt that forces ranking by impact before any fix, which stops the usual memo-everything reflex. The minimal-fix constraint keeps diffs reviewable. Paste one component at a time for best results.

React Performance Audit Prompt

A performance-review prompt that forces ranking by impact before any fix, which stops the usual memo-everything reflex. The minimal-fix constraint keeps diffs reviewable. Paste one component at a time for best results.

1.3K212
Claude

Runs a lighter pass than a full review, catching the mechanical issues — naming, dead code, missing null handling — before a human reviewer spends attention on them. Best used as the step between finishing a branch and opening the pull request.

▸ ready to run
Claude

Runs a lighter pass than a full review, catching the mechanical issues — naming, dead code, missing null handling — before a human reviewer spends attention on them. Best used as the step between finishing a branch and opening the pull request.

Code Review Assistant for Pre-Merge Checks

Runs a lighter pass than a full review, catching the mechanical issues — naming, dead code, missing null handling — before a human reviewer spends attention on them. Best used as the step between finishing a branch and opening the pull request.

230
GPT-4

Turns a diff into a clear commit message that explains intent rather than restating the changed lines. Useful for keeping a history that is worth reading during an incident, when the question is always why a change was made and not what it touched.

▸ ready to run
GPT-4

Turns a diff into a clear commit message that explains intent rather than restating the changed lines. Useful for keeping a history that is worth reading during an incident, when the question is always why a change was made and not what it touched.

Commit Message Generator for Readable Git History

Turns a diff into a clear commit message that explains intent rather than restating the changed lines. Useful for keeping a history that is worth reading during an incident, when the question is always why a change was made and not what it touched.

210
Claude

Walks a site's surface area looking for common weaknesses — injection points, weak headers, exposed endpoints — and explains the fix for each. Intended for reviewing infrastructure you own or are authorised to test, as part of routine hardening.

▸ ready to run
Claude

Walks a site's surface area looking for common weaknesses — injection points, weak headers, exposed endpoints — and explains the fix for each. Intended for reviewing infrastructure you own or are authorised to test, as part of routine hardening.

Website Vulnerability Checker for Defensive Review

Walks a site's surface area looking for common weaknesses — injection points, weak headers, exposed endpoints — and explains the fix for each. Intended for reviewing infrastructure you own or are authorised to test, as part of routine hardening.

180
Claude

Reviews an AI feature for prompt injection, data leakage, and unsafe tool use, then proposes mitigations. Increasingly necessary for any product that passes untrusted text to a model, where the attack surface is the content itself rather than the code.

▸ ready to run
Claude

Reviews an AI feature for prompt injection, data leakage, and unsafe tool use, then proposes mitigations. Increasingly necessary for any product that passes untrusted text to a model, where the attack surface is the content itself rather than the code.

LLM Security Specialist for Prompt Injection Defence

Reviews an AI feature for prompt injection, data leakage, and unsafe tool use, then proposes mitigations. Increasingly necessary for any product that passes untrusted text to a model, where the attack surface is the content itself rather than the code.

170
GPT-4

Guides the model through structured diagnosis: gather symptoms, form a hypothesis, test the cheapest one first. Useful for hardware and environment problems where the instinct to change several things at once usually makes the fault harder to find.

▸ ready to run
GPT-4

Guides the model through structured diagnosis: gather symptoms, form a hypothesis, test the cheapest one first. Useful for hardware and environment problems where the instinct to change several things at once usually makes the fault harder to find.

Tech Troubleshooter for Systematic Fault Isolation

Guides the model through structured diagnosis: gather symptoms, form a hypothesis, test the cheapest one first. Useful for hardware and environment problems where the instinct to change several things at once usually makes the fault harder to find.

170
Claude

Sets a mentoring frame where the model explains not just how to do something but why the practice exists. Useful for developers moving from working code toward maintainable code, and for understanding the reasoning behind conventions rather than just following them.

▸ ready to run
Claude

Sets a mentoring frame where the model explains not just how to do something but why the practice exists. Useful for developers moving from working code toward maintainable code, and for understanding the reasoning behind conventions rather than just following them.

Software Development Mentor for Career and Craft

Sets a mentoring frame where the model explains not just how to do something but why the practice exists. Useful for developers moving from working code toward maintainable code, and for understanding the reasoning behind conventions rather than just following them.

180
Claude

Positions the model as a senior engineer who reasons through difficult problems step by step rather than jumping to a snippet. Best reserved for genuinely knotty issues — concurrency, performance cliffs, subtle state bugs — where the reasoning matters more than the code.

▸ ready to run
Claude

Positions the model as a senior engineer who reasons through difficult problems step by step rather than jumping to a snippet. Best reserved for genuinely knotty issues — concurrency, performance cliffs, subtle state bugs — where the reasoning matters more than the code.

Programming Expert for Hard Technical Problems

Positions the model as a senior engineer who reasons through difficult problems step by step rather than jumping to a snippet. Best reserved for genuinely knotty issues — concurrency, performance cliffs, subtle state bugs — where the reasoning matters more than the code.

180
Claude

Frames the model as a product designer who proposes layouts, interaction patterns, and visual hierarchy for a screen you describe. Useful for getting a second opinion on a flow before building it, particularly around what to cut and where the primary action belongs.

▸ ready to run
Claude

Frames the model as a product designer who proposes layouts, interaction patterns, and visual hierarchy for a screen you describe. Useful for getting a second opinion on a flow before building it, particularly around what to cut and where the primary action belongs.

UX/UI Developer for Interface Design Critique

Frames the model as a product designer who proposes layouts, interaction patterns, and visual hierarchy for a screen you describe. Useful for getting a second opinion on a flow before building it, particularly around what to cut and where the primary action belongs.

292
Claude

Sets a security-focused frame for reviewing designs and configurations, surfacing weak points and recommending mitigations. Aimed at defensive work such as hardening a deployment, planning data protection, or preparing for a security review.

▸ ready to run
Claude

Sets a security-focused frame for reviewing designs and configurations, surfacing weak points and recommending mitigations. Aimed at defensive work such as hardening a deployment, planning data protection, or preparing for a security review.

Security Specialist for Defensive Review and Hardening

Sets a security-focused frame for reviewing designs and configurations, surfacing weak points and recommending mitigations. Aimed at defensive work such as hardening a deployment, planning data protection, or preparing for a security review.

320
GPT-4

Turns the model into a QA engineer that writes test cases and reproducible bug reports for a described feature. Useful for building a regression checklist, or for turning a vague complaint into a report a developer can actually act on.

▸ ready to run
GPT-4

Turns the model into a QA engineer that writes test cases and reproducible bug reports for a described feature. Useful for building a regression checklist, or for turning a vague complaint into a report a developer can actually act on.

QA Tester for Manual Test Plans and Bug Reports

Turns the model into a QA engineer that writes test cases and reproducible bug reports for a described feature. Useful for building a regression checklist, or for turning a vague complaint into a report a developer can actually act on.

130
GPT-4

Produces commit messages that follow the Conventional Commits specification, with the right type prefix and a scoped subject line. Keeps a shared history readable and makes automated changelog and semantic-version tooling work properly across a team.

▸ ready to run
GPT-4

Produces commit messages that follow the Conventional Commits specification, with the right type prefix and a scoped subject line. Keeps a shared history readable and makes automated changelog and semantic-version tooling work properly across a team.

Conventional Commit Message Generator From a Diff

Produces commit messages that follow the Conventional Commits specification, with the right type prefix and a scoped subject line. Keeps a shared history readable and makes automated changelog and semantic-version tooling work properly across a team.

160
Claude

Reviews markup or a described interface for accessibility defects: contrast, focus order, labelling, and semantic structure. Use it before shipping a page to catch the issues that automated scanners miss, especially keyboard traps and missing landmarks.

▸ ready to run
Claude

Reviews markup or a described interface for accessibility defects: contrast, focus order, labelling, and semantic structure. Use it before shipping a page to catch the issues that automated scanners miss, especially keyboard traps and missing landmarks.

Accessibility Auditor for WCAG Compliance Review

Reviews markup or a described interface for accessibility defects: contrast, focus order, labelling, and semantic structure. Use it before shipping a page to catch the issues that automated scanners miss, especially keyboard traps and missing landmarks.

130
Claude

Puts the model in reviewer mode so it reads a diff and reports problems, risks, and improvement suggestions instead of rewriting everything. Use it as a first pass before human review to catch obvious defects, naming issues, and missing error handling early.

▸ ready to run
Claude

Puts the model in reviewer mode so it reads a diff and reports problems, risks, and improvement suggestions instead of rewriting everything. Use it as a first pass before human review to catch obvious defects, naming issues, and missing error handling early.

Code Reviewer for Structured Pull Request Feedback

Puts the model in reviewer mode so it reads a diff and reports problems, risks, and improvement suggestions instead of rewriting everything. Use it as a first pass before human review to catch obvious defects, naming issues, and missing error handling early.

120
Claude

A refactoring prompt that puts characterisation tests before any code movement and outlaws behaviour changes — suspected bugs get flagged, not silently fixed. The output is a safe, reviewable migration rather than a rewrite gamble.

▸ ready to run
Claude

A refactoring prompt that puts characterisation tests before any code movement and outlaws behaviour changes — suspected bugs get flagged, not silently fixed. The output is a safe, reviewable migration rather than a rewrite gamble.

Legacy Function Strangler

A refactoring prompt that puts characterisation tests before any code movement and outlaws behaviour changes — suspected bugs get flagged, not silently fixed. The output is a safe, reviewable migration rather than a rewrite gamble.

658105
Claude

A pre-deploy gate for schema changes: every statement gets a lock-level check and the riskiest one is named explicitly. The safer-sequencing requirement regularly converts a table-locking migration into a zero-downtime one.

▸ ready to run
Claude

A pre-deploy gate for schema changes: every statement gets a lock-level check and the riskiest one is named explicitly. The safer-sequencing requirement regularly converts a table-locking migration into a zero-downtime one.

Migration Plan Reviewer

A pre-deploy gate for schema changes: every statement gets a lock-level check and the riskiest one is named explicitly. The safer-sequencing requirement regularly converts a table-locking migration into a zero-downtime one.

54392
Claude

Turns the vaguest part of React — effects — into a table audit with a verdict per effect. The 'should this be an event handler' question catches the majority of real-world effect misuse. Great pre-review pass.

▸ ready to run
Claude

Turns the vaguest part of React — effects — into a table audit with a verdict per effect. The 'should this be an event handler' question catches the majority of real-world effect misuse. Great pre-review pass.

useEffect Dependency Doctor

Turns the vaguest part of React — effects — into a table audit with a verdict per effect. The 'should this be an event handler' question catches the majority of real-world effect misuse. Great pre-review pass.

996175