bake-claude-md-files

Converts CLAUDE.md rules into automated checks (eslint, phpstan, pint, CI, etc.), removes the automated rules from CLAUDE.md, and verifies everything passes. Frees up agent context by replacing prose with tooling.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "bake-claude-md-files" with this command: npx skills add publicala/bake-claude-md-files/publicala-bake-claude-md-files-bake-claude-md-files

Read all CLAUDE.md files in the project, along with the existing tool configurations (eslint, phpstan, pint, package.json scripts, lefthook, git hooks, GitLab CI or GitHub Actions and everything else relevant).

Identify rules in the CLAUDE.md files that can be turned into automated checks. Every rule we can remove is context freed up for the agent.

Before modifying any CLAUDE.md file, present a summary of:

  • Which rules will be automated (and by which tool)
  • Which rules will be kept (and why - e.g. requires human judgment, context-dependent)

Only proceed after the user approves. Then implement the automated checks, verify everything passes, and only remove a rule from CLAUDE.md after its corresponding check passes.

Implementation priority

  1. Discover existing tooling first - inventory linters, test frameworks, static analyzers, CI pipelines, and git hooks before implementing anything
  2. Use native capabilities - express checks through tools already in the project:
    • Linter/formatter rules (ESLint, Biome, Prettier, Pint, Ruff, gofmt)
    • Static analysis (TypeScript strict, PHPStan, mypy, Rector)
    • Architecture tests (Pest arch, ArchUnit, dependency-cruiser)
    • Git hooks (Lefthook, Husky, pre-commit)
    • CI pipeline steps
  3. Custom scripts only as last resort - only when no existing tool can express the check
  4. Wire into existing runners - new checks must run via existing test/lint commands, not new entrypoints

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

clinic-visit-prep

帮助患者整理就诊前问题、既往记录、检查清单与时间线,不提供诊断。;use for healthcare, intake, prep workflows;do not use for 给诊断结论, 替代医生意见.

Archived SourceRecently Updated
Automation

changelog-curator

从变更记录、提交摘要或发布说明中整理对外 changelog,并区分用户价值与内部改动。;use for changelog, release-notes, docs workflows;do not use for 捏造未发布功能, 替代正式合规审批.

Archived SourceRecently Updated
Automation

klaviyo

Klaviyo API integration with managed OAuth. Access profiles, lists, segments, campaigns, flows, events, metrics, templates, catalogs, and webhooks. Use this skill when users want to manage email marketing, customer data, or integrate with Klaviyo workflows. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).

Archived SourceRecently Updated
Automation

lifelog

生活记录自动化系统。自动识别消息中的日期(今天/昨天/前天/具体日期),使用 SubAgent 智能判断,记录到 Notion 对应日期,支持补录标记。 适用于:(1) 用户分享日常生活点滴时自动记录;(2) 定时自动汇总分析并填充情绪、事件、位置、人员字段

Archived SourceRecently Updated