claude-skill-check
A small Python linter for Claude Code SKILL.md files. It checks:
- YAML frontmatter is present and parses cleanly
nameanddescriptionare presentnameis lowercase kebab-case, 1-64 chars, starts with a letterdescriptionlength is reasonable (20-1024 chars after trimming)allowed-toolsis either a string or a list of strings- Common secret patterns (Anthropic/OpenAI keys, AWS access keys, GitHub tokens, PEM blocks) are not leaked in the file
- Unknown frontmatter fields get a warning
- Empty body gets a warning
Install
pip install claude-skill-check
Usage
Lint a single file:
claude-skill-check path/to/SKILL.md
Lint every SKILL.md under a directory:
claude-skill-check path/to/skills-dir/
Exit status: 0 on no errors, 1 on any errors, 2 when no skill files were found.
Only show errors
claude-skill-check --quiet path/to/skills-dir/
Use as a library
from claude_skill_check import validate_skill_file
result = validate_skill_file("path/to/SKILL.md")
if not result.ok:
for issue in result.errors:
print(issue.code, issue.message)
Issue codes
| Code | Severity | Meaning |
|---|---|---|
| E000 | error | file not found or not a regular file |
| E001 | error | file is empty or not valid UTF-8 |
| E002 | error | missing YAML frontmatter |
| E003 | error | frontmatter is not valid YAML |
| E004 | error | frontmatter is empty |
| E005 | error | frontmatter is not a mapping |
| E100 | error | missing required field (name or description) |
| E101 | error | name is not a string |
| E102 | error | name is not a valid kebab-case identifier |
| E110 | error | description is not a string |
| E112 | error | description exceeds 1024 chars |
| E120 | error | allowed-tools is not a string or list |
| E121 | error | allowed-tools list contains a non-string item |
| E200 | error | possible secret detected in the skill file |
| W111 | warning | description is shorter than 20 chars |
| W300 | warning | skill body is empty after frontmatter |
| W900 | warning | unknown frontmatter field |
Development
pip install -e '.[dev]'
pytest
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for claude-skill-check 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| claude_skill_check-0.1.0.tar.gz | 6.9 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| claude_skill_check-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 14.3 kB
Release files / claude_skill_check-0.1.0.tar.gz
| Download URL | claude_skill_check-0.1.0.tar.gz |
|---|---|
| Size | 6.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
87452792787c8cec86260e64b1657dd1c2a2ca290cc460b6509364d77595ab1f
|
|
BLAKE2b-256 checksum How to use checksums |
7d0d022cb92bcc37d765feeab05483cb23e46628d08c2bebbddbbe0e65f119b8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Release files / claude_skill_check-0.1.0-py3-none-any.whl
| Download URL | claude_skill_check-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
76d6c572d6da3e165a891eb837f0433f9004c7a3fe68a9166dbb2eacb6bd4743
|
|
BLAKE2b-256 checksum How to use checksums |
108467dc146d19a2cb92c6f3133b75fb1b1f7b454f065a93f803c95a767279d3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Security for claude-skill-check 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
