skill-writer
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
Discover Tools skills, compare source repositories and read the instructions for each workflow.
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
Use when building web components, pages, or applications that need distinctive, production-grade interfaces. Helps avoid generic AI aesthetics with bold, intentional design choices.
Use when creating, editing, or reviewing OpenCode plugins. Covers plugin structure, event hooks, TypeScript typing, custom tools, dependency management, and common patterns like notifications and compaction hoo...
Use when creating, editing, or reviewing implementation plans. Covers plan structure, version headers, task phases, acceptance criteria, and checkpoint format.
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt temp...
Use when creating, editing, or reviewing custom OpenCode tools. Covers tool definition structure, argument schemas with Zod, context access, multi-tool files, and invoking scripts in other languages.
Use when creating, editing, or reviewing agent configuration files (AGENT.md or opencode.json agents). Covers frontmatter options, mode selection, tool permissions, and common patterns.
Use when creating, editing, or reviewing custom OpenCode commands. Covers frontmatter options, prompt templating with arguments and shell output, file references, and agent/model configuration.
Use when creating, editing, or reviewing SKILL.md files for AI agents. Covers frontmatter requirements, naming conventions, structure patterns, and common mistakes.
Use when cleaning up Git history, applying commits across branches, finding bug introductions, or recovering from mistakes. Covers rebase, cherry-pick, bisect, worktrees, and reflog.
Use ni (@antfu/ni) for package manager operations. Use this skill when installing dependencies, running scripts, or executing packages in JavaScript/TypeScript projects.
Use `a gh check-pr-review` to fetch and address PR review comments. Use this skill when checking PR review feedback, viewing unresolved threads, or addressing reviewer comments.
Use renovate-dryrun to test Renovate configuration locally. Use this skill when debugging or validating renovate.json5 changes.
Use this skill when committing changes. This skill enforces writing meaningful commit messages with both Why and What sections, and provides Git workflow guidelines.
Use `a gh issue-agent` to view and edit GitHub Issues. Use this skill when working with GitHub Issues - viewing issue content, editing issue body/title/labels, or adding/editing comments.
Use this skill when creating a Pull Request. This skill provides the workflow for drafting, reviewing, and submitting PRs using a ai pr-draft command.
別の worktree で別の Claude Code インスタンスにタスクを委任する。現在のセッションをブロックせずに並列で作業を進めたいときに使用する。
Shared skill entrypoint for Claude Code. See the canonical skill file at: wandb-plot/SKILL.md
Download and generate plots from Weights & Biases runs. Use when you need to: - List projects you have access to - List runs in a W&B project - Inspect available metrics for a run - Download existing plot image...
MagicBlock Ephemeral Rollups development patterns for Solana. Covers delegation/undelegation flows, dual-connection architecture (base layer + ER), cranks for scheduled tasks, VRF for verifiable randomness, and...
Get your personalized trend briefing based on profile domains.
Install hookify rule to auto-suggest diagrams during design discussions
Create a custom source adapter for pattern-radar
Automatically use Perplexity search for personalized context enrichment. Use when facing unfamiliar technologies, decision points, learning questions, or preference-dependent choices.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.