How to Build a Reusable AI Agent Skill Using SKILL.md and Python

·2 views

Developers can create structured AI agent skills by combining a SKILL.md specification file with small Python validation scripts, keeping workflow logic testable and predictable. The tutorial uses a 'commit-crafter' skill as a working example, sourced from a public MIT-licensed repository that documents the open Agent Skills specification. The skill guides an agent to draft Conventional Commit messages from staged Git changes, then validates them using a standalone Python script before any commit is made. The folder structure requires only SKILL.md at minimum, with optional scripts/ and references/ directories for maintainability. No API key, hosted model, or third-party Python package is needed to follow the minimal setup path.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

How to Fix Docker 'Code Exited (1)' Error on Raspberry Pi

The 'Exited (1)' error in Docker indicates the container's main process terminated with a non-zero exit code, often caused by architecture incompatibility. On Raspberry Pi, this commonly occurs when running Docker images built for x86/x64 systems on ARM-based hardware, resulting in errors like 'Exec format error' or 'Illegal instruction'. Developers can diagnose the issue by checking the device architecture with 'uname -m' and verifying whether the Docker image supports ARM. The recommended fix is to use Docker Buildx to build multi-architecture images targeting linux/arm/v7 or linux/arm64 platforms natively. Additionally, a common syntax mistake — using spaces in '--net=host' — can silently cause network failures and should be corrected.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

How a Zero-Budget MCP Server Reached #7 on ModelScope's Hot List

RollingGo Hotel MCP, a travel-focused AI tool, climbed to #7 on ModelScope's hot-list rankings without any advertising spend or large social media campaigns. A developer building a travel AI agent analyzed the tool's growth trajectory by studying its README history, comment activity, and marketplace positioning. The strategy centered on optimizing a single high-intent platform — ModelScope's MCP marketplace — rather than spreading efforts across multiple channels. Key tactics included rewriting the README to lead with the problem it solves, expanding integration examples from one to four, and prominently highlighting a free tier with no enterprise credentials required. Actively responding to user comments also helped sustain engagement and signaled ongoing developer support, reinforcing the tool's ranking through install velocity and community interaction.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Locale Collation Differences Can Silently Break CI Builds Using Glob Patterns

A subtle but critical build issue arises when shell glob patterns like 'fragments/*.json' expand files in collation order, which varies across locales such as en_US.UTF-8 and C. This means a concatenation script written on a Linux machine may produce a different file order — and a different checksum — than the same script run on macOS or a CI runner. The discrepancy causes checksum validation failures even when all files are present, making the bug appear like a flaky test when it is actually a deterministic environment mismatch. AI-generated scripts worsen the problem by defaulting to short, unquoted globs without documenting the locale dependency. The recommended fix is to use an explicit file manifest and pin LC_ALL=C in any script that relies on file ordering, rather than assuming the runtime environment will match the development machine.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

opencodex lets ChatGPT Desktop run local and third-party LLMs via local proxy

A open-source tool called opencodex enables the ChatGPT Desktop app to communicate with non-OpenAI language models, including locally hosted ones like Qwen and GLM, by acting as a local proxy. It works by redirecting the app's API requests through a locally running server at 127.0.0.1:10100, without modifying or forking the ChatGPT Desktop application itself. The tool supports over 40 providers, including Anthropic, Google Gemini, Ollama, vLLM, and LM Studio, as well as any endpoint compatible with the OpenAI or Anthropic API. Installation requires only two npm commands and Node.js 18 or higher, with the Bun runtime bundled automatically. Because opencodex operates as a proxy rather than a fork, it remains functional across ChatGPT Desktop updates, making it resilient to upstream changes.

0 comments Read more at DEV Community