roebi

Defines the git-based lifecycle for agent chat sessions: CREATE for new projects (git init with explicit main branch) and RESUME for continuing work from a delivered tar.gz containing a .git folder. Use this skill whenever an agent starts a new software project from scratch, or whenever a user provides a versioned tar.gz to continue work in a new or resumed session. Also covers the handover tag namespace convention (handover/vN) that keeps session delivery tags safely separated from software version tags (vX.Y.Z) used by GitHub Actions release workflows. Trigger phrases: "start new project", "new session", "resume project", "continue from tar", "here is myproject_vN.tar.gz", "untar and continue", "pick up where we left off", "add github actions release workflow".

Scaffold a complete, modern Python project from scratch - from mkdir to first PyPI publish. Use this skill whenever the user wants to create a new Python package, library, CLI tool, or PyPI module, start a new Python open-source project, set up GitHub Actions CI/CD for Python, or asks how to structure a modern Python project with packaging, testing, and devcontainer. Also triggers for "new pypi module", "python project template", "python package from scratch", "hatch", "uv init", or any request to bootstrap a Python repo with best practices.

Creates a topic-specific directory and file tree scaffold (Gerüst) as a starting point for a software solution or skill collection. Generates empty files, adds placeholder.txt in every empty directory so git tracks it, and writes a README.md in the root with metadata: topic, version, description, create timestamp (YYYYMMDD_HHMISS), creator, and license. Activate for phrases like: "create a file tree for", "scaffold a project for", "create directory structure for", "bootstrap a file scaffold", "Gerüst für", "starting point for", "create folder structure", or "new project skeleton".

Applies the Test-Driven Development (TDD) cycle as an agentic loop of RED -> GREEN -> REFACTOR iterations until all requirements are covered or all existing code paths are tested. Use when a user or agent wants to write code strictly test-first, add missing tests to existing code, or drive a full TDD session for a module, class, or function. Activate for trigger phrases like: "apply TDD", "write this test-first", "do a TDD loop", "TDD cycle for", "drive TDD on", "red green refactor", or "add tests then implement".

Acts as a knowledgeable Teacher that guides a learner through any topic using a structured 5-level learning plan, tracked in a living <topic>-learning-process.md file. Activate when the user says "teach me", "I want to learn", "explain step by step", "learning session", or asks to start a tutoring or teaching loop on any subject. The skill runs an interactive teach-ask-answer loop, evolving the progress file every iteration, until the learner types "learned".

Runs an interactive brainstorming dialog between a creative mentor (the agent) and a brainstormer (the user). The mentor guides deep topic exploration through a growing idea-tree: the brainstormer defines 4 root perspectives (SWOT-style), then mentor and brainstormer alternately add creative branches each round until the brainstormer says "brainstormed". The session concludes with a downloadable <topic>-brainstorming-summary.md. Activate for phrases like: "brainstorm X", "help me brainstorm", "creative brainstorming session", "explore topic X with me", "brainstorming dialog", "mentor-led brainstorm", or "idea tree for X".

For a given software project goal, recommend the best local LLM model and the skills needed to start implementation. Covers CLI tools, Python libraries, and similar projects.

Creates a Swiss-law-compliant Datenschutzerklärung (Privacy Policy) for websites operated from Switzerland or targeting Swiss users. Guides the user through an interactive data-inventory phase covering all processing activities (hosting, fonts, analytics, contact forms, cookies, external embeds, etc.), then generates a ready-to-publish Privacy Policy in German and/or English. Covers obligations under nDSG (in force 01.09.2023), DSG Art. 19, and where relevant DSGVO (for EU visitors). Activate for phrases like: "create a privacy policy", "Datenschutzerklärung erstellen", "I need a privacy policy for my Swiss website", "nDSG privacy policy", "DSGVO Datenschutz", or "create privacy policy switzerland".

Applies the Test-Driven Development (TDD) cycle as an agentic loop of RED -> GREEN -> REFACTOR iterations until all requirements are covered or all existing code paths are tested. Use when a user or agent wants to write code strictly test-first, add missing tests to existing code, or drive a full TDD session for a module, class, or function. Activate for trigger phrases like: "apply TDD", "write this test-first", "do a TDD loop", "TDD cycle for", "drive TDD on", "red green refactor", or "add tests then implement".

Performs a structured code review against requirements and architecture docs. Checks correctness, test coverage, security, KISS/SOLID principles, and code style. Produces a review-checklist.md with pass/fail per criterion and a list of required fixes. Use after the implement phase and before release. Activate for trigger phrases like: "code review", "review this code", "review phase", "check the implementation", "audit the code", "does the code meet requirements", or "pre-release review".

Produces an architecture design for a software project from a structured requirements list. Outputs architecture.md covering module structure, data flow, technology choices, and testability constraints. Use when requirements are complete and the next step is planning the structure before writing any code. Activate for trigger phrases like: "design the architecture", "architecture phase", "plan the module structure", "create an architecture doc", "design this system", or "how should we structure this project".

Transforms a vague goal or feature request into a structured, testable requirements list. Produces a requirements.md with numbered functional and non-functional requirements. Use when a user or agent starts a new software project and needs to turn an idea into concrete, implementable requirements before any code or design work begins. Activate for trigger phrases like: "gather requirements", "write requirements for", "what are the requirements", "define the requirements", "requirements phase", or "turn this goal into requirements".

Orchestrates the full software development lifecycle as an agentic pipeline. Delegates each phase to a focused sub-skill in order: gather requirements, design architecture, implement with TDD, review code, and release. Use when a user or agent wants to build a software project from a goal statement to a released artifact using a structured, test-driven process. Activate for trigger phrases like: "build a software project", "develop this from scratch", "orchestrate sw development", "run the full dev pipeline", or "implement this end to end".

Performs the release phase of a software project: bumps version, generates changelog, creates a git tag, and publishes the artifact (PyPI, npm, or GitHub Release). Uses semver, conventional commits, and PyPI Trusted Publishing (OIDC) for Python packages. Use after code review passes with zero critical or major findings. Activate for trigger phrases like: "release the project", "release phase", "publish to PyPI", "create a release", "bump version and tag", "cut a release", or "ship it".

Guides a user and a chat agent through a structured monthly review focused on the benefits gained from using the agent. Use this skill at the end of each month when the user wants to reflect on value created, time saved, friction reduced, knowledge gained, or next improvements. Activate for phrases like: "monthly review", "agent benefit review", "did this help me", "value of the agent this month", "retrospective with the agent", or "end of month review".

Documents the Skill Class Model — the OO-based taxonomy that classifies every Agent Skill as one of: Role, Topic, Process, or OneStepProcess, each extending the base Skill class. Defines the v1 metadata extension fields for skill-class, crud-verb, topic, requires-role, subprocess-of, subtopic-of, and subrole-of. Use when an agent or author needs to classify a skill, assign metadata, understand the class hierarchy, or check naming conventions. Activate for phrases like: "what class is this skill", "how do I classify a skill", "skill taxonomy", "skill-class metadata", "is-a or has-a for skills", "what metadata does a Role need", or "naming convention for process skills".

Teaches the new thinking of how to do new work with Agent Skills. Use this skill when the user wants to understand how to organize work using skills, how to save sessions as skills, how to use skill trees, how to continuously improve skills, how to use skills as roles, how to use evolving state with skills, or how to apply test-driven thinking to skill workflows. Trigger when the user asks about new work methods, agent skills workflows, skill organization, session capture, evolving state, or skill-based role patterns.

Creates the "What is this about?" section and frontmatter description field for a blog entry about a GitHub repository. Use this skill when an agent needs to generate a blog post introduction from a repository README and description. Activate for phrases like: "create blog entry", "write blog post for repo", "generate what is this about section", "blog from readme", or "summarize repo for blog".