Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Project Comparison

This table compares skrills against alternative approaches for managing and deploying skills across Claude Code and Codex CLI.

Project TypeKey ComponentsTransport/RuntimeAutomation InterfaceKey StrengthsDistinguishing Gaps (vs. skrills)
skrillsMCP server, CLI, validation/analysis crates, skill synchronization utilitiesMCP over stdio; single binaryCLI, MCP tools, release artifacts per targetUnified MCP layer, cross-agent synchronization, skill validation with autofix, token analysis, TUI/CLI feature parity
Static skill bundlesReady-to-use skill filesNone (static)Manual copyStraightforward, drop-in content deploymentLacks validation, analysis, or synchronization. No MCP server or Codex bridging.
CI doc/render pipelinesBuild-time convertersBuild-time onlyCI (GitHub Actions, custom pipelines)Automates documentation renderingNo runtime server, skill discovery, or synchronization; limited to prompt-only operations.
Shared rules repositoriesCurated collections of rules and skillsNot applicable (static)Manual consumptionProvides common baseline rulesetLacks installer, automation, or MCP bridge.
Local skill sync CLIsCLI or TUI for local skill synchronizationLocal synchronization only; no MCPCLI/TUIAllows effective local curation and mirroringNo MCP server, no validation/analysis, limited to basic file sync.
Tutorials/how-to guidesInstructional content for authoring skillsNot applicableArticle/docsEducationalLacks integrated tooling; relies on manual steps.

Core Differentiators

Validation Engine

Skrills validates skills against two targets with distinct requirements. Claude Code is permissive, accepting any markdown with optional frontmatter. Codex CLI is strict, requiring YAML frontmatter with name and description fields. The --autofix flag automatically derives and adds missing frontmatter from the file path and content.

Token Analysis

Skrills analyzes skills to estimate token usage and track dependencies. It provides optimization suggestions for large skills, helping to maintain an efficient context window.

Bidirectional Sync

Skrills supports full bidirectional sync for skills, commands, MCP servers, and preferences. It uses byte-for-byte command sync to preserve non-UTF-8 content and includes a --skip-existing-commands flag to protect local customizations from being overwritten.

Planned Improvements

Future work includes signed artifacts and version pinning for synced skills to improve security and reproducibility. Additional goals include improved Windows path detection, default configurations, and skill dependency resolution to manage complex skill sets.

Summary

Skrills is a skills support engine focused on quality and portability. It validates skills for cross-CLI compatibility, analyzes token usage, and synchronizes configurations bidirectionally. The MCP server enables integration with both Claude Code and Codex CLI environments.