ワンクリックでManusで任意のスキルを実行

linting-llm-configs

スター0

フォーク0

更新日2026年3月29日 13:54

Validates AI guidance files with claudelint and agnix. Use when checking SKILL.md, CLAUDE.md, prompts, hooks, or MCP config for structural issues.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

Ven0m0

Ven0m0/.github

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Linting LLM Configs

Validation-only companion to ai-tuning. Keep remediation focused on lint findings; use ai-tuning when the task is about condensing, deduplication, or instruction design.

Usage

Use this skill after editing AI config files or when CI reports config-lint failures.

When to use

Situation	Validator
Claude Code structure, hooks, MCP, `CLAUDE.md`	`claudelint`
`SKILL.md`, `AGENTS.md`, cross-tool config checks	`agnix`
Mixed repo or release gate	Run both

Workflow

Identify the changed files and choose claudelint, agnix, or both.
Run the narrowest command that covers the edited surface.
Fix structure, naming, or duplication issues in the source files.
Re-run the same validators until they pass.
If the content is verbose but lint-clean, switch to ai-tuning for condensation work.

Commands

Scope	Command
Full Claude Code lint	`claudelint check-all`
Strict repo validation (matches CI)	`uv tool run "claudelint@0.3.3" --strict .`
Validate skill files	`claudelint validate-skills --path .`
Validate hooks	`claudelint validate-hooks`
Validate MCP config	`claudelint validate-mcp`
Cross-tool lint	`agnix .`
Safe autofix pass	`agnix --fix-safe .`
Claude Code target	`agnix --target claude-code .`
Cursor target	`agnix --target cursor .`

Guardrails

Keep SKILL.md files short, trigger-driven, and repo-relevant.
Remove duplicated rules instead of copying the same guidance into multiple skills.
Preserve valid frontmatter and kebab-case skill names.
Do not invent local commands; prefer repo or tool-native commands already in use.

Examples

"Lint this SKILL.md after edits" -> run agnix . plus targeted claudelint validate-skills --path .
"Why did config lint CI fail?" -> reproduce with uv tool run "claudelint@0.3.3" --strict .
"Make these skill files shorter" -> switch to ai-tuning after validators are green

References

Validation guide

このリポジトリの他の Skills

同じリポジトリ

lint-and-validate

Ven0m0/.github

Automatic quality control, linting, and static analysis procedures. Use when validating code changes for syntax correctness and project standards. Triggers on keywords: lint, format, check, validate, types, static analysis.

2026-06-030

code-maintenance

Ven0m0/.github

Refactoring and cleanup - improving code structure, removing dead code, eliminating duplication, or pre-merge cleanup. Use when code is hard to maintain, has dead code or debug artifacts, or needs pre-merge polishing.

2026-05-030

fix-issue

Ven0m0/.github

Fix a GitHub issue end-to-end - from reading the issue, understanding requirements, implementing the fix, writing tests, and creating a commit. Use when given a GitHub issue number or URL to resolve.

2026-05-030

language-optimization

Ven0m0/.github

Optimize code for readability, performance, maintainability, and security across Bash, Python, and Rust. Use when asked to improve code quality, optimize performance, add type safety, or refactor for idioms.

2026-05-030

workflow-development

Ven0m0/.github

Create, debug, and optimize GitHub Actions workflows with security best practices. Use when asked to "create workflow", "fix workflow", "add CI", or needs help with GitHub Actions.

2026-05-030

code-review

Ven0m0/.github

Review code changes (diffs, PRs, patches) and provide structured, actionable feedback on correctness, maintainability, and test coverage. Use when the user asks for a code review, requests feedback on a patch/PR, or wants an assessment of changes.

2026-05-030

Linting LLM Configs

Validation-only companion to ai-tuning. Keep remediation focused on lint findings; use ai-tuning when the task is about condensing, deduplication, or instruction design.

Usage

Use this skill after editing AI config files or when CI reports config-lint failures.

When to use

Situation

Validator

Claude Code structure, hooks, MCP, CLAUDE.md

claudelint

SKILL.md, AGENTS.md, cross-tool config checks

agnix

Mixed repo or release gate

Run both

Workflow

Identify the changed files and choose claudelint, agnix, or both.

Run the narrowest command that covers the edited surface.

Fix structure, naming, or duplication issues in the source files.

Re-run the same validators until they pass.

If the content is verbose but lint-clean, switch to ai-tuning for condensation work.

Commands

Scope

Command

Full Claude Code lint

claudelint check-all

Strict repo validation (matches CI)

uv tool run "claudelint@0.3.3" --strict .

Validate skill files

claudelint validate-skills --path .

Validate hooks

claudelint validate-hooks

Validate MCP config

claudelint validate-mcp

Cross-tool lint

agnix .

Safe autofix pass

agnix --fix-safe .

Claude Code target

agnix --target claude-code .

Cursor target

agnix --target cursor .

Guardrails

Keep SKILL.md files short, trigger-driven, and repo-relevant.

Remove duplicated rules instead of copying the same guidance into multiple skills.

Preserve valid frontmatter and kebab-case skill names.

Do not invent local commands; prefer repo or tool-native commands already in use.

Examples

"Lint this SKILL.md after edits" -> run agnix . plus targeted claudelint validate-skills --path .

"Why did config lint CI fail?" -> reproduce with uv tool run "claudelint@0.3.3" --strict .

"Make these skill files shorter" -> switch to ai-tuning after validators are green

References

name	linting-llm-configs
description	Validates AI guidance files with claudelint and agnix. Use when checking SKILL.md, CLAUDE.md, prompts, hooks, or MCP config for structural issues.