菜单
Validates skill quality — preprocessing safety, frontmatter, line counts, references. Use when checking skills, validating SKILL.md, or when skillcheck, lint skill, or validate skill are mentioned.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Patterns for @outfitter/daemon including lifecycle management, IPC communication, health checks, and PID files. Use when building background services, daemons, or when "daemon", "IPC", "health check", "background service", or "@outfitter/daemon" are mentioned.
Creates handlers, CLI commands, MCP tools, and daemon services following Outfitter Dev Kit conventions. Use when adding new components to a project, scaffolding code, or when "create handler", "new command", "add tool", or "daemon service" are mentioned.
Deep patterns for @outfitter/mcp including tool registration, Zod schemas, resources, and server configuration. Use when building MCP servers, registering tools, defining resources, or when "MCP server", "MCP tool", "registerTool", or "@outfitter/mcp" are mentioned.
Generates patterns, templates, and guides for @outfitter/* packages. Covers transport-agnostic handler systems, Result types, error taxonomy, and package APIs. Use when working with @outfitter/*, Result types, Handler contract, error taxonomy, or when Result, Handler, ValidationError, NotFoundError, OutfitterError, or package names like contracts, cli, mcp, schema, tui, daemon, config, logging are mentioned.
Verify Outfitter compliance in a codebase. Scans for anti-patterns (throws, console, hardcoded paths) and produces a severity-ranked compliance report. Use for pre-commit checks, code review, or migration validation.
Submit feedback to the Outfitter team via GitHub issues. Use after discovering bugs, missing features, unclear docs, or improvement opportunities in @outfitter/* packages.
| name | skillcheck |
| description | Validates skill quality — preprocessing safety, frontmatter, line counts, references. Use when checking skills, validating SKILL.md, or when skillcheck, lint skill, or validate skill are mentioned. |
| context | fork |
| metadata | {"version":"1.0.1","author":"outfitter","preprocess":true,"related-skills":["skillcraft","claude-craft"]} |
| allowed-tools | Read, Glob, Grep, Bash, Task |
| argument-hint | [path] |
Validate skill quality across one or more skill directories.
Scan SKILL.md files for <bang>`command` patterns that trigger Claude Code's preprocessor unintentionally:
!bun ${CLAUDE_PLUGIN_ROOT}/skills/skillcheck/scripts/lint-preprocessing.ts ${ARGUMENTS:-${CLAUDE_PLUGIN_ROOT}}
The linter reports:
| Finding | Fix |
|---|---|
Unintentional <bang>`command` in SKILL.md | Replace ! with <bang> |
| Intentional preprocessing | Add metadata.preprocess: true to frontmatter |
<bang> ConventionSKILL.md files are preprocessed by Claude Code — any <bang>`command` syntax executes when the skill loads. To safely document or reference the syntax:
<bang> as a stand-in for !! is fine and encouraged! is required (that's the feature)Skills that intentionally preprocess (running scripts at load time) should declare it:
metadata:
preprocess: true
Beyond preprocessing, verify skill quality with existing tools:
# Frontmatter validation
bun ${CLAUDE_PLUGIN_ROOT}/scripts/validate-skill-frontmatter.ts <path-to-SKILL.md>
# Full plugin validation
bun ${CLAUDE_PLUGIN_ROOT}/scripts/validate-plugin.ts <plugin-directory>
After reviewing linter results, spawn the quartermaster agent to run deeper validation — frontmatter schema, naming conventions, description quality, line counts, and reference integrity. Pass it the same path argument.
<bang>`command` in SKILL.md (this linter)