---name: gene-panel-design-agent

**Purpose:** Critical analysis and improvement of agent skills

Cross-domain evaluation to estimate generality and detect blind spots. Use when asked to assess broad capability, compare models across domains, or identify missing skills.

從規格目錄的 acceptance.yaml 生成/維護 BDD/ezSpec 測試。使用類似 Gherkin 語法，AI 自動產生 step definition（開發人員不需要手寫），驗收測試規格即為 Executable Specification。

Generate two distinct, creative, and copyright-compliant ad copy variations based on campaign parameters and research insights. Use when creating advertising text content including headlines, body copy, and calls-to-action. Triggers on requests to write ad copy, create ad text, generate headlines, or develop platform-specific ad messaging for A/B testing.

Generate two distinct, AI-powered image variations for advertising campaigns using Google Gemini's image generation capabilities. Use when creating visual assets for ads based on campaign parameters and research insights. Triggers on requests to generate ad images, create visual assets, produce image variations for A/B testing, or develop platform-specific ad visuals.

Create API reference documentation from docstrings. Use when documenting public module interfaces.

Create starter code from templates. Use when setting up new modules or test files.

Generate the comprehensive demo markdown artifacts from the current codebase. Use before UAT to ensure test artifacts reflect the latest code.

Generate an end-to-end test for a given feature or user story. Use when the user asks to create E2E tests, automate workflows, test user flows, or convert manual workflows into Playwright tests. Leverages Playwright MCP to perform the workflow interactively before generating test code.

Auto-generate test data factories from schemas, types, or models. Use when creating test data infrastructure, setting up fixtures, or reducing test setup boilerplate.

Generates features_spec.txt files for use with auto-code extension mode. Analyzes existing codebase and creates structured feature specifications based on user requirements.

Generate Django database migrations for Sentry. Use when creating migrations, adding/removing columns or tables, adding indexes, or resolving migration conflicts.

Homeostatic actuator auto-generating missing tests for requirements with low coverage. Creates unit tests, edge cases, and error cases for REQ-* without sufficient test coverage. Use when validate-test-coverage detects gaps.

Generate high-quality bilingual programming quiz questions for Codle. Use this skill when creating new quiz questions that test deep understanding rather than rote memorization.

generate-spec

Generate job-targeted CV variants with built-in quality gates. Queries knowledge base, customizes content, runs eval/redteam pipeline.

Create a new artifact (text, code, plan, data) under specified constraints. Use when producing content, writing code, designing solutions, or synthesizing outputs.

Generate images using AI models via OpenRouter API. Supports text-to-image and image-based generation with customizable aspect ratios. Use when the user asks to generate, create, or synthesize images based on text descriptions or reference images.

PRIMARY expert for ALL NestJS and @lenne.tech/nest-server tasks. ALWAYS use this skill when working in projects with @lenne.tech/nest-server in package.json dependencies (supports monorepos with projects/*, packages/*, apps/* structure), or when asked about NestJS modules, services, controllers, resolvers, models, objects, tests, server creation, debugging, or any NestJS/nest-server development task. Handles lt server commands, security analysis, test creation, and all backend development. ALWAYS reads CrudService base class before working with Services.

Generates new agent profiles with consistent structure, automatic validation pattern injection, and test-driven protocols

Esta skill te ayuda a determinar y ajustar el nivel de granularidad apropiado para el modelado de historias de dominio, así como a gestionar las perspectivas temporales (proceso actual vs. futuro dese

Extract the most meaningful, engaging clips from YouTube videos. Use when user provides a YouTube URL and wants to find highlights, best moments, controversial takes, or valuable segments. Supports specifying number of clips or topic focus.

Customize plot aesthetics using natural language. Use when the user wants to change colors, fonts, titles, labels, themes, or any visual aspect of a plot before publication.

Search and retrieve plots from history. Use when the user asks about previous plots, wants to find a plot they made earlier, re-display a past visualization, or export a historical plot.

Create terminal data visualizations using Grammar of Graphics. Use when plotting data, creating charts, graphing, visualizing distributions, or when the user mentions plot, chart, graph, histogram, scatter, boxplot, or visualize.

Apply publication-quality style presets to plots. Use when the user wants to style a plot like Wilke, Tufte, Nature, The Economist, or apply minimal/publication styling.

Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.

End-to-end GitHub issue fix workflow using gh, local code changes, builds/tests, and git push. Use when asked to take an issue number, inspect the issue via gh, implement a fix, run XcodeBuildMCP builds/tests, commit with a closing message, and push.

Lists GitHub issues with optional filtering. Use when you need to browse open, closed, or specifically labeled issues in a repository.

Locks or unlocks an issue conversation. Use to manage noise or conclude discussions.

Use to analyze failures in GitHub pipelines or jobs.

Performs advanced searches for issues. Use when looking for duplicates or specific keywords across repositories.

Associates an issue with a milestone. Use for release planning.

Retrieves detailed information about a specific GitHub issue. Use when you need to read the body, comments, or labels of an issue.

Manage GitHub Actions workflows with the gh CLI (list, run, cancel, monitor).

Gherkin acceptance criteria authoring. Use when writing Given/When/Then scenarios, feature files, or BDD-style specifications. Provides syntax reference, best practices, and Reqnroll integration guidance.

Skill for analyzing git changes, grouping them into logical atomic commits, generating conventional commit messages, and guiding through the commit process. Use when committing changes with proper conventional commit format and maintaining atomic commits.

Use when debugging regressions or identifying which commit introduced a bug - provides systematic workflow for git bisect with automated test scripts, manual verification, or hybrid approaches. Can be invoked from systematic-debugging as a debugging technique, or used standalone when you know the issue is historical.

Automated git bisect for bug hunting with test script execution

git

Automate Git workflow with conventional commits, setup GitHub Actions CI/CD, configure Husky hooks, manage PR automation, and handle semantic releases

Create standardized, semantic git commits using the Conventional Commits specification. Analyze the actual diff to determine appropriate type, scope, and message.

Summarizes git commits for specified users over a given time period and generates markdown reports

Plan and create atomic commits ordered by dependencies

Skill for analyzing git changes, grouping them into logical atomic commits, generating conventional commit messages, and guiding through the commit process. Use when committing changes with proper conventional commit format and maintaining atomic commits.

Manage git-tracked directories correctly - never create .gitkeep files in directories that will immediately contain tracked files

git-expert