Skill validator

Skill joaquimscosta/arkhe-claude-plugins/.claude/skills/skill-validator

Validate skills against Anthropic best practices for frontmatter, structure, content, file organization, hooks, MCP, and security (62 rules in 8 categories). Use when creating new skills, updating existing skills, before publishing skills, reviewing skill quality, or when user mentions "validate skill", "check skill", "skill best practices", "skill review", or "lint skill".From its SKILL.md

Install

npx -y skills add joaquimscosta/arkhe-claude-plugins --skill skill-validator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

21 stars21 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.9 KB, 615 tokens by cl100k_base, as published. Nobody here has run it

Skill Validator

Run automated checks against 62 rules covering frontmatter, structure, content, files, references, security, hooks, and MCP.

Quick Start

scripts/validate_skill.py /path/to/skill-directory

With severity filter:

scripts/validate_skill.py /path/to/skill --min-severity warning

Validation Categories

Category	Rules	Checks
Frontmatter	FM001-FM018	Required fields, naming, description, context/agent, maxTurns, memory, disable-model-invocation
Structure	SS001-SS006	Line limits, progressive disclosure
Content	CW001-CW009	Writing style, terminology, string substitution, dynamic context injection, ultrathink
Files	FO001-FO007	Naming conventions, forbidden files
References	RI001-RI003	Broken links, orphan files
Security	SC001-SC005	eval/exec, undocumented constants
Hooks	HK001-HK003	Hook structure, handler format, matcher format
MCP	MC001	MCP server configuration format

Severity Levels

Level	Action
CRITICAL	Must fix before publishing
ERROR	Should fix
WARNING	Consider fixing
SUGGESTION	Optional improvement

Output Example

=== Skill Validation Report: my-skill ===

Summary: 0 critical, 1 error, 2 warnings, 1 suggestion

[ERROR] SS002: SKILL.md exceeds 500 lines (523 lines)
  Location: SKILL.md
  Fix: Split content into WORKFLOW.md, EXAMPLES.md, TROUBLESHOOTING.md

[WARNING] CW001: Second-person language detected
  Location: SKILL.md:45
  Found: "You should create..."
  Fix: Use imperative: "Create..."

Command Options

--min-severity {critical,error,warning,suggestion}  # Filter output
--format {text,json}                                # Output format
--ignore RULE1,RULE2                                # Skip specific rules

Common Issues

"False positive on second-person"

Context-appropriate "you" may be acceptable
Use --ignore CW001 to suppress

"Script security warning"

Add inline comment: # skill-validator: ignore SC001

"Hook/MCP validation incomplete"

Install PyYAML for full nested structure validation: pip install pyyaml

See TROUBLESHOOTING.md for complete issue handling.

References

EXAMPLES.md - Real validation outputs
references/RULES_REFERENCE.md - Complete rules documentation

What ships with it: 4 files

80.7 KB alongside SKILL.md, 1 of them executable

references/

RULES_REFERENCE.md10.2 KB

scripts/

validate_skill.pyruns55.5 KB

EXAMPLES.md9.9 KB
TROUBLESHOOTING.md5.1 KB

Gives 0 of the 12 instructions most quality gates skills give in 615 tokens

Counted across 1,524 of the 2,830 authors here whose files we hold, read 2026-09-06

Read full output and check exit codein 45 of 1524, across 40 files
Verify output confirms the claimin 44 of 1524, across 39 files
Identify the command that proves the claimin 43 of 1524, across 39 files
Execute the full verification commandin 36 of 1524, across 30 files
Produce a verification reportin 34 of 1524, across 18 files
Review git diff changesin 30 of 1524, across 16 files
Fix build failures immediatelyin 29 of 1524, across 9 files
Group findings by severityin 28 of 1524
State claim only with evidencein 27 of 1524, across 22 files
Verify regression tests with red-green cyclein 26 of 1524, across 22 files
Run the full test suitein 26 of 1524, across 25 files
Run test suite with coveragein 25 of 1524, across 10 files

Said here and by no other author read

Run automated checks against skill rules
Use imperative language in skill content
Install PyYAML for nested structure validation
Use ignore flags for false positives

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.