Use when structuring payouts, tiers, and eligibility for referral programs.

Research-backed prompting techniques for improved AI response quality (+45-115% improvement). Use when optimizing prompts, enhancing agent instructions, or when maximum response quality is critical. Invoked by /ai-eng/optimize command. Includes expert persona, stakes language, step-by-step reasoning, challenge framing, and self-evaluation techniques.

Incident response procedures — triage, communication, investigation, mitigation, and post-incident review. Use when handling production incidents or writing runbooks.

Post-mortem on incidents

Comprehensive inclusion analysis of code, examining language, internationalization, assumptions, and who might be excluded. Thorough review for releases or major features.

Apply inclusion/exclusion criteria systematically in literature reviews. Use when: (1) Screening abstracts, (2) Reviewing full texts, (3) Documenting screening decisions, (4) Ensuring PRISMA compliance.

Expert in commercial lease indemnity agreements where a third party (guarantor) becomes directly liable for tenant's obligations under the lease. Use when requiring personal guarantees from business owners, analyzing bankruptcy-proof provisions, negotiating absolute and unconditional guarantees, reviewing corporate parent indemnities, evaluating survival clauses after lease termination, or structuring guarantor release provisions. Key terms include indemnity vs guarantee, primary obligation, absolute and unconditional, personal guarantee, corporate guarantee, survival clause, bankruptcy-proof, waiver of defenses, subordination of rights, joint and several

Environment variable conventions and security practices for Next.js projects. This skill should be used when setting up environment configuration, managing secrets, or establishing security patterns for a new project.

infra-security-reviewer

Initialize Claude skills in the current project and verify setup. Use when user says '/init-skills', 'setup skills', 'install skills', or 'add Claude skills to this project'. Can also review and verify existing skills installation.

Operational metrics dashboard with anomaly detection from metrics endpoint or state file.

Instruction guide for analyzing Codefresh CI failures. When invoked, IMMEDIATELY follow the step-by-step instructions to extract build IDs, fetch logs, and create a formatted failure report. Use when reviewing recursionpharma PRs with failing CI.

Install the pre-commit review hook that forces you to understand changes before committing. Use when you want to enable commit reviews or when setting up a new project.

Design Solana/Anchor instructions with clear inputs, constraints, authority checks, and invariants. Use when defining or reviewing instruction APIs.

Plan instrumentation strategy before implementation, covering what to instrument, naming conventions, cardinality management, and instrumentation budget

Run a structured, interactive review session that presents changes in small, readable chunks and waits for the human to approve, reject, or chat before moving on.

Generate and display skill preview for user review before saving

Deals with i18n in your project.

Prepare for job interviews across formats—behavioral, technical, portfolio reviews, and negotiations. STAR/CAR frameworks for stories, common question patterns, research strategies, and follow-up templates. Triggers on interview prep, job interviews, behavioral questions, or salary negotiation requests.

When writing, reviewing, or validating user stories. Used by ARCHITECT-AGENT and PRODUCT-OWNER.

Create, validate, and audit portable invocable components (commands and skills) for reusable capabilities. Use when building, auditing, or reviewing component quality. Not for agents, hooks, or MCP servers.

Delegate complex tasks to OpenCode subagent, use when >=2 file modifications or batch operations

Concise iOS code review for Payoo Merchant app. Focuses on critical/high/medium issues - RxSwift memory leaks, retain cycles, naming conventions, Clean Architecture violations, and business logic placement. Use when reviewing Swift files, pull requests, ViewModels, ViewControllers, UseCases, and Repositories.

Build and deploy iOS app to connected iPhone via USB. Fast deployment (~8-10 seconds) for development iteration. Use when deploying, installing, or building apps to physical iPhone.

iOS development expert including SwiftUI, UIKit, and Apple frameworks

Ensure iOS/iPadOS-friendly form inputs (keyboard type, inputmode, autocomplete, autocapitalize/autocorrect, enterkeyhint) when editing or reviewing UI forms in web apps. Use when adding or modifying form fields (Svelte/HTML/TSX/etc.), auditing form UX, or fixing mobile Safari keyboard issues.

You are an expert iOS development and GitLab assistant managing merge requests in two modes:

Check Swift naming conventions for iOS code. Validates class names, variables, functions, and IBOutlets against project standards. Use when reviewing code readability, checking abbreviations, or enforcing naming consistency in Swift files.

ios-reviewer

Perform comprehensive code reviews for Payoo iOS Frameworks following Clean Architecture, MVVM, and iOS SDK best practices.

Build, archive, upload iOS app to TestFlight, auto-distribute to external testers, submit for Beta App Review, and update server version. Full automated pipeline via App Store Connect API.

Develop IRB/ethics protocols for human subjects research. Use when: (1) Planning studies involving humans, (2) Preparing IRB applications, (3) Ensuring ethical compliance, (4) Addressing informed consent.

Analyzes website safety and trustworthiness by checking domain registration, WHOIS data, DNS records, and Trustpilot reviews. Returns a comprehensive trust score and security report. Use when checking if a website is safe, legitimate, trustworthy, or when analyzing domain reputation.

GitHub Issue deep analysis. Read issue -> classify problem -> select investigation strategy -> integrate four investigation tools.

Orchestrate issue creation with automatic review to ensure created issues accurately reflect the original requirements.

Verify that a created Trellis issue accurately reflects original requirements without over-engineering or missing critical elements.

Use for any development work - the master 13-step coding process that orchestrates all other skills, ensuring GitHub issue tracking, proper branching, TDD, code review, and CI verification

Orchestrate the implementation of a parent issue (project, epic, or feature) by executing its child issues sequentially, reviewing each implementation, and committing approved changes.

Review the code changes from a completed task implementation to verify correctness, completeness, and adherence to simplicity principles.

Use when orchestrating a Jira issue through the full development lifecycle to Harness PR with branching, commits, and documentation

Guide structured analysis of problems and planning of implementation. Use when starting work on a new feature, encountering a bug, refactoring existing functionality, or any task that benefits from thinking before coding. Helps create well-defined GitHub issues with clear scope, acceptance criteria, and implementation steps.

Automatically reviews code changes against issue/spec at evaluate phase start to ensure implementation completeness

>

Khi thực hiện code review với codex làm theo các bước sau:

Execute iterative refinement workflows with validation loops until quality criteria are met. Use for test-fix cycles, code quality improvement, performance optimization, or any task requiring repeated action-validate-improve cycles.

java-reviewer

>

This skill should be used when the user asks to 'write unit tests', 'add integration tests', 'create property-based tests', 'fix failing test', 'improve test coverage', 'reduce mocking', 'test this class', 'add jqwik tests', or needs guidance on JUnit 5, Mockito, Spring Boot Test, property testing with jqwik, test patterns, mocking strategies, or test anti-patterns. Covers Java/Spring Boot testing best practices.