lineMay 15, 2026

ODW #6: The Pros and Cons of MCP and Agent Skills from a Git Automation Perspective (opens in new tab)

The post presents agent skills as a simpler, more practical alternative to building MCP servers for many AI-agent workflows. It demonstrates how to use Anthropic’s `skill-creator` to build a Git release automation skill that analyzes commits, updates a changelog, bumps versions, commits, tags, and pushes releases. The author emphasizes that precise requirements and explicit constraints are essential for preventing unintended agent behavior. ## Why Agent Skills Are Practical - Agent skills can simplify both implementation and architecture compared with custom MCP servers. - Although online examples explain the concept, the post focuses on a practical, work-oriented use case. - The tutorial assumes familiarity with the basic concept of skills and concentrates on building and applying one. ## Git Smart Release Automation The example skill automates releases for a Git project in the current working directory. - Reads the Git history after the most recent tag. - Summarizes changes and adds them to the top of `CHANGELOG.md`. - Creates `CHANGELOG.md` if it does not exist. - Updates the version in `pyproject.toml`. - Commits the changelog and version changes. - Creates a corresponding Git tag. - Operates based on the terminal’s current `pwd`. ## Using `skill-creator` - Anthropic’s official `skill-creator` skill is used to generate the new automation skill. - The user provides a detailed requirements specification rather than implementing everything manually. - Explicit workflow steps and constraints help keep the agent focused on the correct directory and avoid unnecessary complexity. - The development process is demonstrated with Claude Code. ## Clarifying Requirements Before generating the skill, the agent asks questions to resolve ambiguous behavior. - Support patch, minor, and major version bumps. - Use `v0.1.0` for the first release when no prior tag exists. - Follow a structured changelog format. - Push both commits and tags to the remote repository. - Abort with an explanation if the working directory contains uncommitted changes. ## Generated Skill Structure The completed skill contains: - `SKILL.md` — instructions and metadata for the agent. - `scripts/smart_release.py` — a local Python script that performs Git operations and file modifications. - `evals/evals.json` — evaluation cases for testing the skill. The skill also includes: - Keep a Changelog-style updates. - Dirty working-directory checks. - Automatic remote pushing. - Commit categorization such as `feat`, `fix`, and `docs`. ## `SKILL.md` and the Python Script - The frontmatter in `SKILL.md` acts as a concise discovery description that helps the agent decide when to load the skill. - The Markdown body provides the detailed execution workflow. - `smart_release.py` handles operations requiring deterministic file and Git manipulation, reducing the need for the language model to process raw data directly. - The post then begins testing the skill with a simple Python calculator project. A practical approach is to define release behavior, edge cases, and safety constraints before asking an agent to generate the skill, while delegating file and Git operations to a local script.

semantic-versioningpythonmcpclaude-code+3

gitlabJan 14, 2026

AI Catalog: Discover, create, and share agents and flows (opens in new tab)

The GitLab AI Catalog serves as a centralized repository designed to streamline the discovery, creation, and distribution of AI agents and automated flows across an organization. By providing a structured environment for managing foundational and custom AI assets, it fosters team collaboration and ensures consistency throughout the development lifecycle. Ultimately, the catalog enables developers to scale AI-driven automation from experimental private prototypes to production-ready, instance-wide solutions. ## Discovering and Enabling AI Assets * The catalog acts as a central hub for two distinct asset types: Agents, which handle on-demand or context-specific tasks, and Flows, which are multi-step automations that orchestrate multiple agents. * Users can browse assets via the Explore menu, inspecting titles, descriptions, and visibility statuses before implementation. * To utilize an asset, it must first be added to a top-level group via the "Enable in group" button and then activated within specific projects. * The duplication feature allows teams to copy existing agents or flows to serve as templates for further customization. ## Development and Configuration * Custom agents are built by defining specialized system prompts and configuring specific tool access, such as granting read-only permissions for code and merge requests. * Custom flows utilize a YAML-based structure to define complex behaviors, incorporating components like prompts, routers, and agent hierarchies. * New assets are typically assigned a unique display name (e.g., `ci-cd-optimizer`) and initially set to private visibility to allow for safe experimentation. * Effective creation requires thorough documentation of prerequisites, dependencies, and specific use cases to ensure the asset is maintainable by other team members. ## Managing Visibility and Sharing * Private visibility restricts access to project members with at least a Developer role or top-level group Owners, making it ideal for sensitive or team-specific workflows. * Public visibility allows anyone on the GitLab instance to view and enable the asset in their own projects. * Best practices for sharing include using descriptive, purpose-driven names like `security-code-review` rather than generic identifiers. * Organizations are encouraged to validate and test assets privately before moving them to public status to ensure they solve real problems and handle edge cases. ## Versioning and Lifecycle Management * GitLab employs automated semantic versioning (e.g., 1.1.0) where any change to a prompt or configuration triggers an immutable version update. * The platform uses "version pinning" to ensure stability; when an asset is enabled, projects remain on a fixed version rather than updating automatically. * Updates are strictly opt-in, requiring users to manually review changes and click an "Update" button to adopt the latest version. * Version history and current status can be monitored through the "About" section in the Automate menu for both agents and flows. To maximize the benefits of the AI Catalog, organizations should establish a clear transition path from private experimentation to public sharing. By leveraging version pinning and granular tool access, teams can safely integrate powerful AI automations into their development workflows while maintaining full control over environment stability and security.

semantic-versioningdatabase-designgitlabagents+4