Adversarial PRD review using 5 specialized subagent personas. Probes for ambiguities, hidden complexity, and untestable requirements before execution begins. Use when: user says 'review this PRD', 'critique this spec', 'is this PRD ready', 'adversarial review', or when /prd-writer invokes it at Step 7. Also trigger when user shares an existing PRD and asks if it's implementation-ready.

Generate images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via inference.sh CLI. Capabilities: text-to-image, image editing, multi-image input (up to 14 images), Google Search grounding. Triggers: nano banana 2, nanobanana 2, gemini 3.1 flash image, gemini 3 1 flash image preview, google image generation

A disciplined workflow for working a queue of bug reports. One bug at a time. No skipping steps. No batching.

license-compliance

트리거: Main 스레드에서 라운드 승인/보류 판단, 다음 handoff 1건 확정, Main->Executor 릴레이 생성이 필요할 때 사용. 비트리거: 코드 구현/테스트 실행이 필요한 실행 작업에는 사용하지 않는다.

'Python programmer specialising in functional programming, clean code, documentation, and code quality using ruff and uv.'

Enforce Repo A DDC policy and acceptance gates before PRs. Use when changing policy files, node runtime behavior, guardrail-sensitive config, or validation tooling that must satisfy AGENTS.md acceptance commands.

Code review local changes

Weekly health review — sleep trends, workout adherence across wger/Fitbod/Peloton, nutrition averages, and recovery analysis.

Code review from a fresh context. Run in a separate session — no knowledge of implementation decisions.

Review a GitLab MR or GitHub PR

Performs comprehensive security and performance audits of codebases, identifying vulnerabilities, unsafe patterns, security weaknesses, and performance bottlenecks. Use this skill when the user requests a security assessment, penetration testing analysis, vulnerability scan, or performance review of their code. Generates detailed, actionable reports with severity classifications and remediation guidance.

Reviews an existing AI agent (or agent design) against all 22 patterns from "Patterns for Building AI Agents" (Bhagwat & Gienow, 2025). Produces a scored checklist with specific recommendations for im

Conventional commits, PR creation, and quality gate verification

Check for license compliance, PII, and IP risks

Create a draft pull request for the current branch. Summarises the diff, fills in any PR templates, and opens the PR via the gh CLI.

Generate SVG logo alternatives with side-by-side comparison. Use when creating logos, branding, or project icons.

Analyze codebase for code smells and refactor to drastically improve code quality. Expert in clean code, SOLID principles, Ruby patterns, service objects, and refactoring. Use for code quality audits, refactoring sessions, and cleaning up technical debt.

Code review panel for current branch changes. Use for reviewing PR changes, code review, or getting feedback on branch changes.

Create a versioned release with changelog generation, git tag, and GitHub release. Use for creating releases, tagging versions, or publishing changelogs.

Implements advanced AI patterns like Reflection, ReAct, Planning, and Tool Use.

Perform static application security testing with tools like Semgrep, CodeQL, and SonarQube. Identify security vulnerabilities in source code before deployment. Use when implementing secure SDLC, code review automation, or security gates in CI/CD pipelines.

Use when asked to add or modify hooks for Claude Code specifically. Or, if the user is asking to automate an action, for example run a formatter after edits, or running a script right before git commits, those are hooks and you should use this skill to implement them.

Durable software engineering agent for reusable code and artifacts.

Autonomous optimization loop that improves any measurable thing. Point it at files to change, a command to check, and a number to improve — then walk away. Works with any AI agent. Use when the user wants to autonomously optimize code performance, ML training, Docker images, SQL queries, prompts, CI speed, bundle size, Kubernetes configs, or any domain with a measurable score. Triggers include requests like 'optimize this', 'improve performance', 'make this faster', 'reduce allocations', 'autoimprove', 'run the optimization loop', 'let it run overnight', or when the user has an improve.md file.

Generate a code review with atomic views and remediation requirements for the current branch vs a base branch. Use this skill when the user wants a code review, branch review, diff review, change analysis, pre-merge review, or quality pass on their current work. Also use when the user asks to understand what changed on a branch, wants a narrative explanation of their changes, or needs a review document before merging.

> CI/CD pipeline analysis, deployment strategy design, and environment management. From commit to production with confidence.

Express shell-command safety as declarative flag maps so tooling knows exactly what passes.

> Organizations that conduct blameless post-incident reviews after every significant security

Deploy ServiceNow configuration changes safely — either via Update Sets (classic instances) or now-sdk install (Fluent SDK projects). Covers Update Set naming, parent/child batching, preview validation, and SDK build/install workflows. Use when managing releases, migrating between instances, promoting changes from dev to test to prod, or orchestrating complex deployments with multiple Update Sets. Trigger this skill whenever the user mentions deployment, Update Sets, moving changes between environments, release management, or now-sdk install.

Audit AI-generated or AI-shaped backend/general code diffs for duplicate helpers, over-defensive control flow, broad exception wrappers, speculative scaffolding, comment/docstring boilerplate, local style drift, hallucinated APIs/dependencies, fixture-shaped test hacks, and obvious safety/performance gaps. Use when reviewing or safely cleaning up Python, TypeScript, or other implementation code after a feature, bugfix, or prototype pass.

Wrap up current work: review + test + gates + commit in one operation. Use when user says 'ship', 'ship it', 'wrap up', 'done', 'finish', 'готово', 'отправляй', 'заверши', 'закрывай'.

Systematic review of existing architecture using ATAM-lite methodology. Evaluates architectural fitness against quality attribute scenarios, identifies risks, sensitivity points, tradeoffs, and anti-patterns. Produces structured review report with findings and recommendations.

Repository management through Git CLI and GitHub API with branch protection, commit conventions, and security controls

Ensures .NET/C# code follows modern best practices, SOLID principles, and industry standards for production-ready applications

Use when the user asks to implement a plan end-to-end, test it, run codex review against the base branch in a loop until no P0/P1 issues remain, and make sure CI/CD is green before finishing.

> Deep soundness analysis of specs and plans. Auto-fixes inferrable issues, surfaces design decisions to you. Runs automatically before sign-off.

<!-- Generated by harness generate-slash-commands. Do not edit. -->

>-

Main Gatorbots FRC orchestrator policy for deterministic worker routing and honest answer modes.

skill_id: skill-quality-review

GitHub-based system design and code review agent.

Assess whether a deprecated CLI tool should be used or rejected. Maintains the deprecation registry, enforces migration paths to canonical alternatives, and evaluates exception criteria.

Multi-LLM parallel code review with specialized agent personas.

Lazily extract referenced files for bundled skills so large prompts stay offline until needed.

> Lightweight orchestrator — dispatches isolated phase-agents, tracks state, chains artifacts between phases. Delegates all planning/execution/verification/review to dedicated persona agents.

> Aesthetic direction workflow. Capture design intent, generate DESIGN.md with anti-patterns and platform notes, review components against aesthetic guidelines, and enforce design constraints at confi

> Detect documentation that has drifted from code. Find stale docs before they mislead developers and AI agents.