Automated summary
Audits React components for hardcoded tenant-specific strings, non-semantic colors, and sections that could be gated behind feature flags.
Strengths
- Clearly separates acceptable cases (SEO metadata, data arrays at the top of page files) from genuine violations in reusable components
- Emits a structured three-table markdown report that is immediately usable in PR review
- Defaults to the right directories (src/components/ and src/app/(site)/) while still accepting an explicit target
- Read-only by design — it reports findings without editing files, so it is safe to run before a merge
Limitations
- Tightly coupled to the 'movemental' project: brand name, cited author names, and paths are baked into the skill
- Limited to Read/Grep/Glob, so there is no AST analysis and no reliable detection of hex values outside JSX
- The color rules defer to another skill (tailwind-cleanup) whose content is not included here
Run it before PR review or when preparing the codebase to onboard a new tenant.
On a project that uses neither Tailwind nor a multi-tenant architecture, or when you expect automated fixes instead of a report.
Security analysis
SafeThe skill is a pure read-only audit: it uses only Read, Grep, and Glob to search a codebase for hardcoded strings, non-semantic color classes, and missing feature flags. There is no bash, no network access, no file writes, no auto-fix behavior (explicitly stated), and no handling of secrets or credentials. All referenced paths are ordinary source directories, so execution risk is negligible.
No concerns found
How this analysis is madeExamples
/tenant-check src/components/Lance un tenant-check sur toute la base avant que je soumette la PR de la page pricing./tenant-check src/app/(site)/aboutname: tenant-check description: Audit components for hardcoded tenant strings, non-semantic colors, or missing feature flags. Use before PR review or to check tenant isolation readiness. user-invocable: true allowed-tools: Read, Grep, Glob
Audit the movemental codebase for tenant config violations.
Target: $ARGUMENTS
If no target, scan src/components/ and src/app/(site)/.
What to Check
1. Hardcoded Tenant Strings
Search for strings that should come from a config or CMS, not be hardcoded in components:
- Brand name "Movemental" hardcoded in components (allowed in metadata/SEO, flagged in reusable components)
- Domain references:
movemental.comin component code - Specific leader names (e.g., "Alan Hirsch", "Brad Brisco") in reusable components
- Pricing figures (
$1,000,90%,10%) in reusable components vs data arrays - Contact info, addresses, phone numbers inline
2. Non-Semantic Colors
Run the same checks as tailwind-cleanup §1:
- Any
bg-white,bg-black,text-white,text-blackoutside midnight context - Any Tailwind palette colors:
bg-blue-*,text-gray-*, etc. - Any hardcoded hex values in JSX
3. Feature Flag Readiness
Check whether optional sections could be gated:
- Sections that might not apply to all future tenants
- Content blocks that assume a specific audience (churches, nonprofits, movement leaders)
- Pricing tiers or economics that are tenant-specific
Output Format
## Tenant Check Report
### Hardcoded Strings
| File | Line | String | Recommendation |
|------|------|--------|---------------|
### Color Violations
| File | Line | Class | Fix |
|------|------|-------|-----|
### Feature Flag Opportunities
| File | Section | Suggestion |
|------|---------|-----------|
Rules
- This is an AUDIT skill — report findings, don't auto-fix.
- Hardcoded strings in page-level
metadataexports are acceptable (SEO needs). - Hardcoded strings in data arrays at the top of page files are acceptable for now (will be migrated to CMS/config later).
- Focus on reusable components that would break if used for a different tenant.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/tenant-check-audit-mrwakbnh/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/tenant-check-audit-mrwakbnh' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/tenant-check-audit-mrwakbnh/download' --output '.skill-downloads/tenant-check-audit-mrwakbnh/SKILL.md.part' && mv '.skill-downloads/tenant-check-audit-mrwakbnh/SKILL.md.part' '.skill-downloads/tenant-check-audit-mrwakbnh/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read, Grep, Glob
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/tenant-check-audit-mrwakbnh/SKILL.md' && test -s '.skill-downloads/tenant-check-audit-mrwakbnh/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/tenant-check' && cp -R '.skill-downloads/tenant-check-audit-mrwakbnh' '.claude/skills/tenant-check'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/tenant-check-audit-mrwakbnh'openskills read 'tenant-check-audit-mrwakbnh'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/tenant-check-audit-mrwakbnh/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.