Skip to content
Skill category

Code Review and Quality skills

Agent skills for code review, test-driven development, debugging and refactoring. Compare methods that keep AI-written code correct and easy to maintain.

47 skills

About Code Review and Quality

Agents write code fast, and speed makes mistakes easy to miss. The skills here put checks around the work: a reviewer with fresh context reads the diff, a failing test comes before the code that fixes it, and a bug is reproduced before anyone proposes a patch.

The category covers four kinds of work. Review skills grade a change on correctness, design and risk, and sort findings by severity. Testing skills cover test-driven development, property-based tests, mutation testing and browser tests. Debugging skills enforce a sequence of reproduce, localize and fix the root cause. Refactoring skills describe small, behavior-preserving steps and when to stop.

When choosing, start with how the skill enforces its rules. Some only describe a checklist, while others run a reviewer subagent or require command output as proof before a task counts as done. Check what the skill assumes about your stack, since several target one test runner or one language. Prefer a small set that cover review, tests and debugging once each, because overlapping skills give an agent conflicting instructions.

Pair a review skill with a test-first skill, then add a debugging skill for the day something breaks. That combination catches most problems before a change reaches the main branch.

Showing 47 skills
Model-led700 tokens in use

implement-patch

8,320

Code Review And Quality

The patcher stage of patching-bugs: find the broken invariant, write a regression test that fails first, fix it, and leave one local commit.

Skill
26idle
700in use
700up to
Tokens, counted offlineView skill
Model-led1,365 tokens in use

mutation-testing

8,320

Code Review And Quality

Configures mewt and muton mutation testing campaigns, analyzes surviving mutants and uses them to find bugs in weakly tested code.

Skill
47idle
1,365in use
14,982up to
Tokens, counted offlineView skill
Model-led1,651 tokens in use

patching-bugs

8,320

Code Review And Quality

The orchestrator for fixing one known bug: reproduce it, validate it, patch it, prove the patch, hunt regressions, and render reports for review.

Skill
30idle
1,651in use
1,651up to
Tokens, counted offlineView skill
Model-led1,448 tokens in use

PR Improver

8,320

Code Review And Quality

Runs a review-and-fix loop over the current branch's changes until a PR review reports no critical or major findings, scoped to the touched directories.

Skill
108idle
1,448in use
1,448up to
Tokens, counted offlineView skill
Model-led800 tokens in use

property-based-testing

8,320

Code Review And Quality

Write, review and debug property-based tests across Hypothesis, fast-check, proptest and Echidna, with a catalog of properties and failure triage.

Skill
189idle
800in use
4,696up to
Tokens, counted offlineView skill
Model-led1,062 tokens in use

prove-patch

8,320

Code Review And Quality

The prover stage of patching-bugs: run scoped cases on baseline and patched trees, then confirm the bug returns when the patch is reverted.

Skill
19idle
1,062in use
1,062up to
Tokens, counted offlineView skill
Model-led653 tokens in use

reproduce-bug

8,320

Code Review And Quality

The reproduction stage of patching-bugs: build the baseline, exercise the named bug with a PoC or compiler run, and save the raw receipts.

Skill
21idle
653in use
653up to
Tokens, counted offlineView skill
Mixed1,504 tokens in use

review-walkthrough

8,320

Code Review And Quality

Turns the current branch into a self-contained HTML walkthrough: the diff split into ordered steps, each with an explanation and review findings anchored to lines.

Skill
22idle
1,504in use
1,504up to
Tokens, counted offlineView skill
Model-led986 tokens in use

second-opinion

8,320

Code Review And Quality

Runs an external CLI review (Codex, Antigravity or Gemini) on your uncommitted changes, a branch diff or a commit, and reports the findings with severity and file lines.

Skill
63idle
986in use
4,137up to
Tokens, counted offlineView skill
Model-led423 tokens in use

validate-bug

8,320

Code Review And Quality

The validation stage of patching-bugs: a fresh agent reruns the unchanged PoC and decides whether the claim and its invariant hold.

Skill
22idle
423in use
423up to
Tokens, counted offlineView skill
Model-led1,032 tokens in use

impl-validator

3,794

Code Review And Quality

A critical reviewer subagent that checks whether files or output match their stated goal and returns PASS, WARN or FAIL for each check.

Skill
37idle
1,032in use
1,032up to
Tokens, counted offlineView skill
Model-led88 tokens in use

Clean Code

3,324

Code Review And Quality

Robert C. Martin-inspired rules for readable names, small focused functions and tests that protect behavior.

Skill
29idle
88in use
3,445up to
Tokens, counted offlineView skill
Model-led91 tokens in use

Code Complete

3,324

Code Review And Quality

Steve McConnell-inspired construction rules for routines, data, control flow, defensive code, debugging and testing.

Skill
26idle
91in use
3,817up to
Tokens, counted offlineView skill
Model-led92 tokens in use

Refactoring

3,324

Code Review And Quality

Martin Fowler-inspired rules for behavior-preserving refactoring in small steps, separate from feature changes.

Skill
20idle
92in use
4,465up to
Tokens, counted offlineView skill
Model-led101 tokens in use

Refactoring.Guru

3,324

Code Review And Quality

Refactoring.Guru-inspired rules for diagnosing code smells, choosing the smallest treatment and stopping on time.

Skill
31idle
101in use
13,275up to
Tokens, counted offlineView skill
Model-led114 tokens in use

The Pragmatic Programmer

3,324

Code Review And Quality

Engineering rules inspired by The Pragmatic Programmer: one owner per fact, independent modules, tracer bullets, automation and fast feedback.

Skill
38idle
114in use
4,113up to
Tokens, counted offlineView skill
Model-led117 tokens in use

Working Effectively with Legacy Code

3,324

Code Review And Quality

Change hard-to-test code safely with rules inspired by Michael Feathers: characterization tests, seams, sprout and wrap methods, dependency breaking.

Skill
37idle
117in use
3,891up to
Tokens, counted offlineView skill
Mixed1,683 tokens in use

Playwright Skill

3,307

Code Review And Quality

Lets a coding agent write and run its own Playwright scripts to test sites, check layouts, fill forms and capture screenshots.

Skill
69idle
1,683in use
5,639up to
Tokens, counted offlineView skill
Model-led2,703 tokens in use

Code Review

687

Code Review And Quality

Review code for correctness first, with performance and security as options, and report only defects that survived a check of the strongest counterargument.

Skill
36idle
2,703in use
6,240up to
Tokens, counted offlineView skill
Model-led2,736 tokens in use

derive-tests

687

Code Review And Quality

Turns documented intent into a test coverage map: which rules have tests today, which are proposed, and which gaps are left, ranked by what crossing them exposes.

Skill
32idle
2,736in use
2,914up to
Tokens, counted offlineView skill
Mixed6,459 tokens in use

independent-review

687

Code Review And Quality

A release gate built on a fresh, read-only reviewer that never saw the build: git-computed subjects, a five-part brief, mandatory triage and a clear stopping rule.

Skill
39idle
6,459in use
12,239up to
Tokens, counted offlineView skill
Model-led798 tokens in use

intended-vs-implemented

687

Code Review And Quality

A review method that compares AI-built code with its recorded intent to find unenforced permissions, public cron endpoints and private data leaking onto public surfaces.

Skill
37idle
798in use
798up to
Tokens, counted offlineView skill
Model-led4,094 tokens in use

test-harness

687

Code Review And Quality

Rules for tests where a green gate means something: what each harness fakes, how to run and report the gate, regression tests for fixes, and lessons from real bugs.

Skill
43idle
4,094in use
21,069up to
Tokens, counted offlineView skill

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers