Analyze product reviews across any e-commerce platform. Extract actionable insights from customer feedback including pain points, praise patterns, feature requests, and sentiment trends.

Review Python code with high quality bar for type hints, Pythonic patterns, and maintainability.

Test coverage, code quality, defect metrics, and QA KPIs

Use proactively when encountering Rails errors, test failures, build issues, or unexpected behavior. Analyzes errors, reproduces issues, and identifies root causes.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Aggressively refactor by tearing out all backward-compatibility and legacy layers. Use when modernizing APIs, demolishing migration debt, ripping out compat shims, killing feature flags, or rewriting a subsystem clean. Assume no callers deserve protection — break everything, rebuild it right.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding

Review pending drift warnings and fix affected documentation or dismiss false positives

Check a PR for unresolved automated review feedback (Copilot, CodeRabbit, Codecov) and invoke the appropriate resolver skills. Use when the user says "resolve PR feedback", "check PR comments", "address review comments", "fix coverage", or wants to handle all automated review feedback on a PR.

Professional retrospective coach based on the GRAI model (Goal-Result-Analysis-Insight) to guide users through structured retrospectives. Transform experiences into lessons, and lessons into capabilities. Use when: (1) Systematic review needed after project/event completion, (2) Learning from failures, (3) Summarizing and replicating success experiences, (4) Creating improvement action plans.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Review a delta's implemented code against specs, designs, and decisions

Set up systematic review monitoring across e-commerce platforms. Track new reviews, detect negative review spikes, monitor competitor reviews, and automate review response workflows.

Review a pull request for issues and feedback.

Comprehensive PR review using specialized agents

Deep PR review that runs `code-review:code-review` and `pr-review-toolkit` agents in parallel, then hands off to `review-pr` for fix or post.

Validate requirements documents for EARS compliance, completeness, and consistency. Use after creating requirements.

Critiques your paper draft as a skeptical reviewer would. Use when asked to review a paper draft, find weaknesses in a paper, prepare for peer review, anticipate reviewer criticism, or stress-test research before submission. Identifies weak claims, missing baselines, unclear explanations, and overclaims.

Verifying a Go project: runs every quality check (lint, vet, imports, format, docs, unit, integration, E2E) and returns a single MERGE_READY or NEEDS_FIX verdict. Report-only: never fixes anything. Use for a quick pre-merge or pre-PR check outside a full dev-cycle. Skip when not a Go project, when you want a single command, or when already inside ring:running-dev-cycle (use its gates).

Execute comprehensive role-based E2E testing with Playwright, testing all user flows for each role

Debug Rstest issues systematically, including performance regressions. First determine whether the slowdown is in build startup or test execution, then run controlled config or code experiments and compare before/after timings.

Run Playwright smoke tests, debug failures, and verify fixes

Test runner checkpoint for conductor gates. Detects test framework (jest, pytest, cargo test, go test, etc.), runs tests, and captures output. Returns structured result with pass/fail status and failed test details. Use when: 'run tests', 'test runner', 'check tests pass'.

Create PR for code review. Use this when the user is ready to submit their work, create a pull request, or send code for review.

Semantic version control analysis. Use sem to understand actual code changes vs cosmetic/stylistic modifications, identify impacted entities, and review diffs at the semantic level.

Fix production issues and review code with Sentry context. Use when asked to fix Sentry errors, debug issues, triage exceptions, review PR comments from Sentry, or resolve bugs.

Use when starting a new feature, project, or bug fix in a repository that uses SGAI for AI-driven development

Final review for code simplicity. Identifies anti-patterns, code smells, and YAGNI violations.

Evaluate skill test run outputs against expectations and extract implicit claims.

This skill MUST be invoked when the user says "implementation strategy", "cycle sequencing", or "implement workflow patterns". SHOULD also invoke when user mentions "execute-then-verify", "targeted retry", "fix pass", or "implementation escalation". Provides implementation-workflow patterns consumed alongside strategy-core for targeted briefings.

Applies a modified Fagan Inspection methodology to systematically resolve persistent bugs and complex issues. You should active this skill when multiple previous fix or debugging attempts have failed repeatedly, or when a methodical root cause analysis or complex problems is needed. Highly effective for complex problems. Do not use for simple troubleshooting.

Scores and prioritizes technical debt by impact, risk, and effort. Provides ranked backlog with ROI analysis and quarterly paydown recommendations. Use for "tech debt", "technical debt management", "code quality", or "refactoring priorities".

Run tests and analyze results. Use when the user wants to run the test suite or test specific functionality.

Generate realistic test data with Faker, create database seeds, manage fixtures, and build factory patterns.

Creates test fixtures, mock data, and test scenarios for unit and integration tests. Use when setting up test data, creating mocks, or generating test fixtures.

Automatically detect test frameworks (Jest, pytest, RSpec, xUnit) in projects by analyzing configuration files and dependencies

Use when a test is failing and you need to determine root cause: is it flaky, an environment issue, or a real regression? Traces failure from symptom to fix.

Continuously run tests, create failure tasks, and delegate fixes to /implement until the suite is fully green. Uses ralph to prevent stopping between iterations.

Get comments from a Jira ticket to review discussion history. Use when the user wants to see ticket comments, check for updates, review feedback, or understand the discussion on an issue.

Run a short active-recall dialogue that helps the user understand their current unstaged code changes. Use when the user wants to understand, review, quiz themselves on, or explain a local diff before accepting, committing, merging, or shipping it.

Verify no behavioral regressions after implementation. Spawns parallel sonnet subagents for semantic diff review + test execution. Use when: user says "verify no regressions", "check for regressions", "make sure nothing broke".

Verify bug fix by running validate target and confirming fix

Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales

Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales

Parent skill for feature and project workflows. Use when the user wants to build a project, add a feature, polish a skill, test all skills, or browse the skill catalog. Routes to add-project (build project from idea), improve-skill (refine one skill in a sandbox), test-skills (validate full skill composition), or any child skill by name.

Smoke test for aliyun-devops-manage. Validate script compilation and one bounded DevOps metadata query path.

Smoke test for aliyun-pts-manage. Validate script compilation and one bounded read-only PTS metadata query path.

This skill MUST be invoked when the user says "review spec", "find gaps", "what's missing", or "clarify requirements". SHOULD also invoke when reviewing spec.md for completeness. Focuses on product decisions and generates clarifying questions with concrete options.

Enable the auto permissions review hook for this session. Auto-approves read-only operations, sends ambiguous Bash to Haiku, and reviews edits only in accept-edits mode. Other terminal sessions are not affected.

Test shell scripts with BATS (Bash Automated Testing System). Write, run, and debug tests for bash scripts.

Automatically builds and tests code changes. Use whenever code is modified, tests fail, before creating pull requests, or when verifying code quality.

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

Use when completing tasks, requesting review, or receiving code review feedback — covers both requesting and responding to reviews with technical rigor

Code review guidance.

Review, stage, commit, and push all current changes to remote.

Review data constraints and referential integrity in Rails models and migrations.

Internal documentation-index generation workflow for direct invocation from context maintenance tasks.

Continue working on an existing diagram. Load, review, and modify persistent diagrams across sessions.

Triage and prioritize CVE findings from INFYNON package scans. Use when the user has scan results and needs to decide what to fix, defer, or handle — covers severity matrix, fix strategies, and safe version selection.

Scaffold an aggregate root with entity, value objects, repository interface, domain events, and test stubs

Systematic debugging workflow. Use for "debug", "fix bug", "not working", "error", "broken".

Use when debugging a failing test or runtime error with hypothesis-driven investigation, autonomous command validation, and systematic root cause elimination.

Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.

Analyser et résoudre une erreur (message simple ou stack trace)

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

Test-only skill for verifying sibling file access in Copilot CLI

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches

[deprecated alias] Renamed to flow-next-spec-completion-review in flow-next 1.0 — invoke the new skill. Removed in 2.0.

Create, list, and delete GitLab work items (tasks, OKRs, key results, epics, incidents, test cases). Use when working with GitLab's work item types beyond standard issues. Triggers on work items, work-items, tasks, OKRs, key results, epics, work item create, work item delete.

Browse and review open learning PRs in the configured groovebook repo. Use to participate in the shared groove commons.

Evaluate output, identify lessons, decide accept/rework. Use after implementation.

Interacts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files and hunks, reloads session contents, and adds inline review comments. Use when the user has a Hunk session running or wants to review diffs interactively.

Iterative self-improvement pipeline -- review-fix loop with adversarial sentinels until all issues (info severity and above) are resolved or max iterations reached

Create a structured customer interview script with JTBD probing questions, warm-up, core exploration, and wrap-up sections. Follows The Mom Test principles — no leading questions, no pitching, focus on past behavior. Use when preparing for user interviews, creating interview guides, or planning discovery research.

Store a lesson learned from the current conversation. Triggered by /lesson command. Use when Master signals that the recent conversation contains a pitfall, fix, or key insight that should be persisted to long-term memory.

Test message variants on synthetic audiences. Use when: predicting response rates, sentiment, or objections before live tests.

Ultra-fast feature implementation using Explore → Code → Test workflow. Use when implementing focused features, single tasks, or when speed over completeness is priority.

Ultra-fast feature implementation using Explore → Code → Test workflow. Use when implementing focused features, single tasks, or when speed over completeness is priority.

Create a pull request with Problem/Solution format. Can optionally commit first. Use when opening PRs or when branch changes are ready for review.

Create a pull request based on a GitHub issue with analysis, implementation, QA, and PR creation

Post a comment on a pull request. Use when the user wants to add a comment to a PR, respond to feedback, request review, or document decisions.

Address PR review comments by implementing reviewer feedback and suggestions.

View pull request diff and code changes. Use when the user wants to see what changed in a PR, review code changes, understand the scope of modifications, or examine specific file changes.

Use when reviewing a GitHub PR for quality, scope correctness, trust tier compliance, or generating user-friendly review feedback.

File Linear tickets from PR review feedback and notify the PR author. Use when asked to file a ticket from PR comments, create a ticket from PR feedback, ticket PR concerns, or create a Linear ticket from a PR review. Triggers on phrases like "file ticket from PR", "ticket the PR concerns", "linear ticket for PR", "create ticket from PR feedback", or "ticket this review".

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.

Detect new or modified skills in .agents/skills/ by comparing git hashes against ai-skills, snapshot for rollback, review, publish to ai-skills, install locally, and cherry-pick lockfile to TARGET. Replaces /elevate-skill.

Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.

Screenshot capture, organization, and comparison for QA testing. Use when taking screenshots during test execution to ensure proper naming, organization, and traceability back to test cases.

Prepare a Quarterly Business Review. Use when: building QBR presentations, client performance reviews, or strategy updates.