Menu
SkillsMP a collecté 16 skills depuis tedivm/opencode-config. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 16 skills collectés sur 16.
Use when creating, configuring, or modifying opencode agents. Covers Markdown agent definitions, frontmatter options (description, mode, hidden, color), primary vs subagent types, and detailed prompt structure. Don't use for skills, commands, or general…
Langue du texte source : anglais
Use when rendering mermaid diagrams to PNG, SVG, or PDF images. Handles both .mmd files and inline mermaid code blocks in markdown files. Don't use for creating mermaid syntax or GraphViz/DOT diagrams.
Langue du texte source : anglais
Use when converting files to Markdown format for LLM consumption, document analysis, or text extraction. Supports PDF, Office documents, images, audio, HTML, and more via Microsoft's markitdown. Don't use for simple text file reads, existing Markdown files,…
Langue du texte source : anglais
Use when creating or modifying custom opencode commands in the `commands/` directory. Covers markdown command files, frontmatter options (description, agent, model, subtask), prompt templates with $ARGUMENTS, shell output injection, and file references.
Langue du texte source : anglais
Use to do a thorough exploration of an existing codebase. Always use this when asked to explore a codebase/repo/project. Always use it when starting a task that requires deep knowledge of the codebase. Don't use for quick lookups or single-file questions.
Langue du texte source : anglais
You MUST use when creating, modifying, or reviewing GitHub Actions workflow files. For security reasons it is VITAL that you use this skill when working with third party actions (including `actions/checkout` and other official actions).
Langue du texte source : anglais
Use when parsing, querying, transforming, or extracting data from JSON files, API responses, or JSON streams. Always use the `jq` CLI for all JSON operations. Do not use for YAML, XML, CSV, or plain-text parsing. Never build JSON from scratch in Python, Node,…
Langue du texte source : anglais
Use when designing software architecture or new features: producing technical design documents with model definitions, service code, API contracts, migration strategies, and testing plans. Works alongside OpenSpec proposals or stands alone for feature design.…
Langue du texte source : anglais
Use when implementing, extending, or adapting Rob's Style Guide design system in any framework (vanilla HTML, Svelte, React, etc.). Covers theming, colors, typography, components, Prism.js syntax highlighting, and Tabler Icons. Don't use for generic styling,…
Langue du texte source : anglais
Use when bootstrapping the design of a brand new project — producing a plan.md through iterative exploration. Don't use for modifying existing plans, implementing features, or working with established codebases.
Langue du texte source : anglais
Use when creating a new Python project from Rob's Awesome Python Template (cookiecutter). Don't use for adding Python to existing projects, installing packages, or working with established codebases.
Langue du texte source : anglais
Use when asked to create, generate, or scaffold a new Agent Skill. Don't use for modifying existing skills or writing general documentation.
Langue du texte source : anglais
All actions on GitHub must use this skill. Covers pull requests, issues, repositories, releases, GitHub Actions, searches, and API requests via the `gh` CLI.
Langue du texte source : anglais
Use when initializing or setting up OpenSpec in a project that doesn't have it yet. Don't use for creating, applying, exploring, or tinkering with OpenSpec proposals.
Langue du texte source : anglais
Use when creating a pull request, preparing changes for review, or pushing work to GitHub. Handles quality checks, branch management, conventional commits, openspec archival, and PR creation end-to-end.
Langue du texte source : anglais
Use when asked to "fix things", "qa", "run tests and fix things", "test until clean", or similar requests to iteratively run quality checks and fix failures until everything passes. Don't use for single-purpose tasks like running only tests or only linting…
Langue du texte source : anglais