validate-agent-files
Skill75 starsChanged 13 days agoMITView on GitHub
Validates AI coding assistant customization files (agents, skills, prompts, instructions) for correct format and structure. Works with GitHub Copilot, Claude Code, Codex, OpenCode, and other providers. Use when checking if agent files are properly configured, troubleshooting agent issues, or before committing new customization files.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- JBurlison/MetaPromptsedited, first seen Feb 19, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- JBurlison/MetaPrompts★ 7694% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository42 other files it gives its agents.
- skills/agent-file-specs/references/AGENTS.mdAGENTS.md
- agent-file-specsSkill
- analyze-agent-overlapSkill
- generate-agent-docsSkill
- wow-addon-developmentSkill
- wow-addon-structureSkill
- wow-api-achievementsSkill
- wow-api-calendar-eventsSkill
- wow-api-collectionsSkill
- wow-api-combatSkill
- wow-api-currency-economySkill
- wow-api-encountersSkill
- wow-api-escape-sequencesSkill
- wow-api-eventsSkill
- wow-api-framexmlSkill
- wow-api-group-lfgSkill
- wow-api-guildSkill
- wow-api-housingSkill
- wow-api-indexSkill
- wow-api-items-inventorySkill
- wow-api-lua-environmentSkill
- wow-api-map-navigationSkill
- wow-api-misc-systemsSkill
- wow-api-professionsSkill
- wow-api-pvpSkill
- wow-api-questsSkill
- wow-api-reputationSkill
- wow-api-settings-systemSkill
- wow-api-social-chatSkill
- wow-api-spells-abilitiesSkill
- wow-api-talentsSkill
- wow-api-transmogSkill
- wow-api-unit-playerSkill
- wow-api-weekly-rewardsSkill
- wow-api-widgetSkill
- wow-api-xml-schemaSkill
- wow-client-targetsSkill
- wow-controller-supportSkill
- wow-lua-apiSkill
- wow-macro-commandsSkill
- wow-native-uiSkill
- wow-ui-skinningSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Before committing new agents, skills, prompts, or instructions
- Distinctive: line 17
When an agent isn't behaving as expected
- Very specific: line 19
After modifying any .github customization files
- Distinctive: line 70
No usage examples in description
- Distinctive: line 181
When validating all files, provide summary:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Validate Agent Files
Validates that agent, skill, prompt, and instruction files follow the correct format and structure.
Host-specific packaging
This is a repository maintenance skill, excluded from the WoW plugin. Maintain canonical WoW skills under skills and generate the package with npm run build. Agent metadata, rules, commands, and discovery paths differ by host; do not copy Copilot conventions into Codex or Claude mechanically. See file locations. Examples using <provider>/ below describe Copilot-style source files and must be adapted using host specifications.
When to Use
- Before committing new agents, skills, prompts, or instructions
- When an agent isn't behaving as expected
- To audit existing customization files for issues
- After modifying any
.githubcustomization files
Validation Process
Step 1: Identify File Type
Determine the type based on location and extension:
<provider>/agents/*.md→ Agent file (user-invokable)<provider>/agents/*.subagent.agent.md→ Sub-agent file (workflow component)<provider>/skills/*/SKILL.md→ Skill file<provider>/prompts/*.prompt.md→ Prompt file<provider>/instructions/*.instructions.md→ Instruction file
Step 2: Apply Type-Specific Validation
Agent File Validation (<provider>/agents/*.md)
Required Structure:
---
name: agent-name
description: When to use this agent (should include examples)
user-invokable: true # Optional, defaults to true
---
[System prompt body]Supported Frontmatter Attributes:
name(required) - Agent identifierdescription(required) - When/how to use, with examplesuser-invokable(optional) - Set tofalsefor sub-agents (default:true)tools- List of allowed toolsmodel- Specific model to usehandoffs- Other agents this can delegate to
Checks:
- ✓ YAML frontmatter present with
---delimiters - ✓
namefield exists and is non-empty - ✓
descriptionfield exists (recommend 50+ characters with examples) - ✓ Body content exists after frontmatter
- ✓ If
toolsspecified, they are valid tool names - ✓ If filename contains
.subagent.agent.md, verifyuser-invokable: falseis set
Naming Convention Checks:
- User-facing agents:
<name>.agent.mdor<name>.md - Sub-agents:
<name>.subagent.agent.mdwithuser-invokable: false
Common Issues:
- Missing
---delimiters - Empty or minimal description
- No usage examples in description
- Body content missing or too brief
- Sub-agent missing
user-invokable: false - Sub-agent not using
.subagent.agent.mdnaming convention
Skill File Validation (<provider>/skills/*/SKILL.md)
Required Structure:
---
name: skill-name
description: What this skill does and when to use it.
---
[Skill instructions body]Supported Frontmatter Attributes:
name(required) - Must match parent directory name, lowercase with hyphensdescription(required) - Max 1024 chars, describes function and triggerslicense(optional) - License informationcompatibility(optional) - Environment requirementsmetadata(optional) - Key-value pairs for additional infoallowed-tools(optional) - Space-delimited pre-approved tools
Checks:
- ✓ File is named
SKILL.mdinside a directory - ✓
namematches parent directory name exactly - ✓
nameis lowercase, alphanumeric with hyphens only - ✓
namedoesn't start/end with hyphen or have consecutive hyphens - ✓
descriptionis 1-1024 characters - ✓ Body content provides clear instructions
Common Issues:
namedoesn't match directory name- Uppercase characters in name
- Description too vague (should include trigger keywords)
- Missing instructions in body
Prompt File Validation (<provider>/prompts/*.prompt.md)
Required Structure:
---
mode: agent
description: What this prompt does
---
[Prompt template with {{variables}}]Supported Frontmatter Attributes:
mode(optional) - One of:agent(default),ask,edit,generatetools(optional) - Available tools for this promptdescription(optional but recommended) - What the prompt accomplishes
Checks:
- ✓ File has
.prompt.mdextension - ✓ If
modepresent, it's a valid value - ✓ Variables use
{{variableName}}syntax - ✓ Body content exists (the prompt itself)
Common Issues:
- Wrong extension (
.mdinstead of.prompt.md) - Invalid
modevalue - Undefined variables in template
Instruction File Validation (<provider>/instructions/*.instructions.md)
Required Structure:
---
applyTo: "**/*.ts"
---
[Contextual instructions]Supported Frontmatter Attributes:
applyTo(required) - Glob pattern(s) for when instructions apply
Checks:
- ✓ File has
.instructions.mdextension - ✓
applyTofield exists - ✓
applyTocontains valid glob pattern(s) - ✓ Body content provides meaningful guidance
Common Issues:
- Wrong extension
- Missing
applyTofield - Invalid glob syntax
- Empty or minimal instructions
Output Format
## Validation: [filename]
**Type:** [Agent|Skill|Prompt|Instruction]
**Status:** ✅ Valid | ⚠️ Warnings | ❌ Invalid
### Issues
- [Issue 1 with line number if applicable]
- [Issue 2]
### Recommendations
- [Suggestion for improvement]Batch Validation
When validating all files, provide summary:
## Validation Summary
| Type | Total | Valid | Warnings | Invalid |
|------|-------|-------|----------|---------|
| Agents | X | X | X | X || Sub-Agents | X | X | X | X || Skills | X | X | X | X |
| Prompts | X | X | X | X |
| Instructions | X | X | X | X |
### Files Requiring Attention
- [List files with issues]Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

