Perform integrity checks on version numbers and file consistency across the repository.
Install
mkdir -p .claude/skills/check-forever-healthy && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17511" && unzip -o skill.zip -d .claude/skills/check-forever-healthy && rm skill.zipInstalls to .claude/skills/check-forever-healthy
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Project Verification & Consistency CheckingKey capabilities
- →Check version numbers across project files
- →Verify consistency of item numbering in documentation
- →Report inconsistencies found in project files
- →Check overall consistency across various files
- →Use a root VERSION file as reference
- →Offer to fix detected inconsistencies
How it works
This skill scans specified project files to check for consistency in version numbers, item numbering, and overall content. It uses the `VERSION` file in the project root as a reference.
Inputs & outputs
When to use check
- →Check project version consistency
- →Verify documentation numbering
- →Validate file integrity
About this skill
AI4L - Project Verification & Consistency Checking
Handles consistency checking for all major files in the repo, including version numbers, item numbering, and overall consistency across files
[project_files]
-
.claude/skills/er/SKILL.md -
.claude/skills/check/SKILL.md -
.claude/agents/er-auditor.md -
.claude/agents/er-creator.md -
.claude/agents/er-fixer.md -
.claude/agents/er-combiner.md -
AGENTS.md -
CLAUDE.md -
README.md -
CONTRIBUTING.md -
prompts/ER.md -
prompts/PERSONA.md -
.grok/rules/rules.md -
docs/Using-Chat-UI.md -
docs/Using-Claude-Desktop.md -
docs/Using-CLI-Environments.md -
docs/Lessons-Learned.md -
docs/Limitations.md -
docs/Examples.md
Version
- Check all [project_files] version numbers
- Use the version stated in the
VERSIONfile in the project root as a reference. - Make sure that all targets are consistent with it, including the version in the badges.
- Some files do not have badges, just the version in the text. Make sure those are consistent as well.
- If a file has no version, leave it as it is
Consistency Checking
- Check all target files for consistency and completeness
- Check the numbering of all items and the item count in ER.md
- Also check numbered step lists (
1.,2.,3.…) in ER.md, not justx.yitems - Test each sequence for gaps and duplicates explicitly — a gap paired with a duplicate passes a count/min/max test
Environment Configs
.mcp.json is the source for MCP servers; .codex/config.toml, .grok/config.toml and the Claude settings files are hand-maintained. The servers in scope are those AGENTS.md prescribes for the agents; other servers in .mcp.json are out of scope.
- For each server in scope, compare command and args in
.codex/config.tomland.grok/config.tomlwith.mcp.json; report a server missing from a TOML and any argument that differs - Compare the
mcp__*entries in the allow lists of.claude/settings.jsonand, where present,.public/.claude/settings.jsonwith the servers in scope; report a prescribed server that is not allowed - Run
/syncinto a temporary directory and diff against the committed generated files; report any drift
Reporting
- If there are any inconsistencies, report them and ask the user if you should fix them.
- Report what was fixed (if anything).
When not to use it
- →When the project does not have a `VERSION` file in the root directory
Limitations
- →Relies on a `VERSION` file in the project root for version reference
- →Consistency checks are limited to the specified project files
How it compares
This skill automates the verification of project consistency against a central version reference, which is more reliable and faster than manual checks across many files.
Compared to similar skills
check side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| check (this skill) | 0 | 3mo | No flags | Beginner |
| browser-use | 64 | 5mo | Review | Intermediate |
| tmux-terminal | 3 | 7mo | Review | Advanced |
| vibe-check | 1 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by forever-healthy
View all by forever-healthy →You might also like
browser-use
browser-use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
tmux-terminal
mikeyobrien
Interactive terminal control via tmux for TUI apps, prompts, and long-running CLI workflows.
vibe-check
VibiumDev
Browser automation for AI agents. Use when the user needs to navigate websites, read page content, fill forms, click elements, take screenshots, or manage browser tabs.
windsurf-flows-automation
jeremylongshore
Create and manage Windsurf Flows for repetitive tasks. Activate when users mention "windsurf flows", "task automation", "workflow automation", "repetitive tasks", or "process automation". Handles Flow creation and management. Use when working with windsurf flows automation functionality. Trigger with phrases like "windsurf flows automation", "windsurf automation", "windsurf".
proof-of-work
MadAppGang
Proof artifact generation patterns for task validation. Covers screenshots, test results, deployments, and confidence scoring.
manage-skills
junnv93
Analyzes session changes to detect missing verification skills. Dynamically discovers existing skills, creates new skills or updates existing ones, and manages CLAUDE.md skill references. Use when adding new patterns/modules that may need verification coverage, or when maintaining skill consistency.