Unified shipping + TRACE self-review protocol (beads, proof, PR). Explicit-only.

impact-analysis

Implements new TCL builtin commands or subcommands in feather. Use when adding new TCL commands like lrepeat, or new subcommands to existing commands like namespace.

'Single-agent implementation: executes plans in-place without subagents. Use /implement (default) for complex features; use this for simpler tasks or when subagent overhead is unwanted.'

Add comprehensive type hints to Python/TypeScript code to improve IDE support, catch errors early, and enable better AI code understanding

implementation-loop

Use when preparing to implement instructions by reviewing documentation and TODO.md so the actual work starts with a shared plan.

Implement a feature using the written implementation plan. Use when you have a fully-formed written implementation plan to execute in a separate session with review checkpoints

Use after implementing a plan to verify completeness, correctness, and merge safety - the post-implementation gate

Loads plan, reviews critically, executes each batch, and reports for review between batches. Use when implementing a plan from a plan file.

<objective>

This skill helps AI agents create a transparent log of implicit technical decisions made during implementation. The goal is to capture specific, non-obvious choices that could be valuable for later re

CSV and OFX transaction import parsing. Use when working on files in src/lib/import/.

Improve UI copy using proven frameworks (JTBD, benefit-first, error patterns). Use when a designer wants to improve button text, error messages, empty states, or audit copy in a component. Supports interactive walkthrough mode for reviewing changes one-by-one, or batch mode for quick fixes.

Complete continuous improvement cycle orchestrating review, analysis, learning extraction, systematic updates, and validation. Sequential workflow from comprehensive review through pattern analysis and learning extraction to improvement application and re-validation. Use when continuously improving skills, applying review findings, implementing systematic enhancements, or executing complete improvement cycles.

Refactor and improve code quality. Use for code refactoring, performance optimization, and quality improvements. Includes Context7 refactoring patterns lookup.

Apply IN10 Red Teaming to organize adversarial review to find vulnerabilities through simulated attack.

Use when checking what PRs are waiting for your review, or when starting your day to see what needs attention

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

Review web interface implementations across Interactivity, Typography, Motion, Touch, Optimizations, Accessibility, and Design/UX. Based on industry best practices and UX psychology principles. Use for UI component and page implementation reviews.

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

When the user wants to submit an iOS app to the App Store. Use when the user mentions 'App Store,' 'App Store Connect,' 'TestFlight,' 'iOS submission,' 'app review,' 'EAS build,' 'eas submit,' 'Apple review,' 'app rejection,' or 'iOS release.' This skill covers the entire process from setup to App Store review approval.

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:

Build, review, and refactor iOS mobile apps (Swift) using modern iOS patterns. Use for tasks like SwiftUI UI, navigation, state management, networking (URLSession), persistence (Core Data/SwiftData/Keychain), dependency injection, modularization (SPM), testing, performance, accessibility, and App Store release readiness.