devclarityai

Explain code at a high level and surface gotchas

Review a PR diff with focused, actionable feedback

Improve readability of a source file without changing behavior

Turn a user story into a concrete plan, skeletons, and tests

Refactor legacy code toward a stated goal with safety

Break a feature spec into sprint-ready engineering tasks

Generate thorough tests for a function or module

Interactively discover monorepo directories and create a JSON list for AGENTS.md generation

Provides a brief explanation of the code attached, including key components, notable patterns, and a code walkthrough.

Provides a code review of the attached code changes.

Begins implementing a task following an implementation plan.

Provides a brief explanation of the code attached, including key components, notable patterns, and a code walkthrough. Use when the user asks to explain, understand, or walk through code.

Provides a code review of the attached code changes. Use when the user asks for a code review, PR review, or feedback on code changes.

Begins implementing a task following an implementation plan. Use when the user asks to implement a feature, fix a bug, or build something based on an existing plan or task file.

Creates an implementation plan markdown file from a task description. Use when the user describes a new feature or task and wants a structured plan before implementation begins.

Provides a brief explanation of the code attached, including key components, notable patterns, and a code walkthrough.

Guides the creation of Playwright E2E tests from planning through implementation. Covers test plan creation, data seeding, Page Object Model development, and test writing with human checkpoints at each stage.

Explores features to discover stable locators and fixes broken locators in Playwright tests. Two modes — explore (proactive discovery) and fix (reactive repair) — both using playwright-cli for live browser interaction.

Reads a ticket's acceptance criteria and surfaces gaps, ambiguity, unstated assumptions, and missing cases - then ranks what to test by risk (severity x priority). Use before writing any tests, to interrogate the spec. Day 1 acceptance-criteria + risk block of the QA Foundational training.

Drafts a structured, reproducible bug report from behavior observed in the running app. Use after a tester reproduces a defect and wants a clean report another tester could file without a follow-up conversation. Day 2 bug-reporting block of the QA Foundational training.

Builds the context an AI needs to test an app well - product/area notes and user personas - and writes them into a reusable reference file. Use to turn a thin, generic AI run into a grounded one. Day 1 context live-build of the QA Foundational training.

Takes an existing set of test cases for a feature and returns what is missing - uncovered states, boundaries, negative paths, and unstated rules. Use when inheriting a test suite or auditing coverage. This is road 2 of the QA Foundational Day 2 "five roads."

Turns markdown or QA skill output into a simple, consistently styled standalone HTML report. Saves it to a qa-reports folder on the Desktop and opens it in the default browser. Works on Mac and Windows. Use when output from a qa-xxx skill (AC analysis, bug report, test cases, gap analysis) needs to be shared as an HTML file.

Turns a feature input (ticket + acceptance criteria, existing cases, a screenshot, observed app behavior, or a recorded walkthrough) into test cases or lighter test scenarios. Use when a tester needs to generate test coverage from any of the "five roads" inputs. Carried from Day 1 of the QA Foundational training; the road-1 input for Day 2.

Reads a ticket's acceptance criteria and surfaces gaps, ambiguity, unstated assumptions, and missing cases - then ranks what to test by risk (severity x priority). Use before writing any tests, to interrogate the spec. Day 1 acceptance-criteria + risk block of the QA Foundational training.

Drafts a structured, reproducible bug report from behavior observed in the running app. Use after a tester reproduces a defect and wants a clean report another tester could file without a follow-up conversation. Day 2 bug-reporting block of the QA Foundational training.

Builds the context an AI needs to test an app well - product/area notes and user personas - and writes them into a reusable reference file. Use to turn a thin, generic AI run into a grounded one. Day 1 context live-build of the QA Foundational training.

Takes an existing set of test cases for a feature and returns what is missing - uncovered states, boundaries, negative paths, and unstated rules. Use when inheriting a test suite or auditing coverage. This is road 2 of the QA Foundational Day 2 "five roads."

Turns markdown or QA skill output into a simple, consistently styled standalone HTML report. Saves it to a qa-reports folder on the Desktop and opens it in the default browser. Works on Mac and Windows. Use when output from a qa-xxx skill (AC analysis, bug report, test cases, gap analysis) needs to be shared as an HTML file.

Analyze a test automation codebase and produce a single-page HTML "model of what exists" report covering assertion depth, test levels, run mechanics, environments, test data, authentication, network handling, dependencies and security, run commands, locators and consistency, and AI tooling artifacts.

Draft a changelog entry from recent changes. Use when the user asks to write a changelog entry, update CHANGELOG.md, or summarize what changed for release notes.

Write a clear git commit message from the staged changes. Use when the user asks for a commit message or to commit their work.

Summarize a pull request or code diff into a clear description. Use when the user asks for a PR description, to summarize a diff, or to explain what a branch changes.

Ask the user what they'd like to be called and address them that way. Use when the user runs /simple-demo:address-me or wants to confirm their plugin marketplace is working.