Observed since 20 Oct, 23:24 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
Static quality linter for AI agent skill definitions (SKILL.md files)
Static quality linter for AI agent skill definitions (
SKILL.mdfiles).
agent-skill-lint is the eslint of the agent skill world — pure static analysis, zero LLM calls, zero cloud dependency, pre-commit-friendly, CI-ready.
It catches bad skill definitions at development time, before they reach the agent.
pip install agent-skill-lint
Or from source:
git clone https://github.com/hananel-e/agent-skill-lint
cd agent-skill-lint
pip install -e ".[dev]"
# Lint all skill.md files found recursively under a path
skill-lint roo check .
# Lint a single file
skill-lint roo check .roo/skills-build/coder/skill.md
# Filter by severity
skill-lint roo check . --severity error # errors only
# Output formats
skill-lint roo check . --format json # machine-readable
skill-lint roo check . --format github # GitHub Actions annotations
# Disable specific rules
skill-lint roo check . --ignore ROO012,ROO031
# List all rules
skill-lint roo rules
# Explain a specific rule
skill-lint roo explain ROO013
# Check tool dependencies
skill-lint doctor
# ── v0.2.0 commands ──────────────────────────────────────────────────────────
# Score skills (A-F quality grades)
skill-lint roo score .
skill-lint roo score . --format json
skill-lint roo score . --fail-under 80 # exit 1 if average < 80
# Simulate routing for a query (no ML required)
skill-lint roo simulate "write and fix code" --path .roo/skills/
skill-lint roo simulate "plan architecture" --path . --top 3
skill-lint roo simulate "debug errors" --path . --embeddings # requires [embeddings] extra
# Check framework sync (.roomodes ↔ skills)
skill-lint roo sync .
skill-lint roo sync . --format json
skill-lint roo sync . --roomodes .roomodes # use a specific .roomodes file
# Update the known mode slug cache from GitHub
skill-lint roo update-slugs
| Code | Meaning |
|---|---|
0 | Clean — no violations |
1 | One or more violations found |
2 | Tool error (file not found, parse failure, etc.) |
| Rule ID | Severity | Description |
|---|---|---|
ROO001 | error | name field missing from frontmatter |
ROO002 | error | description field missing from frontmatter |
ROO003 | error | modeSlugs field missing from frontmatter |
ROO004 | error | modeSlugs is an empty list |
ROO005 | warning | modeSlugs contains an unrecognised mode slug |
ROO006 | warning | name value does not match the parent directory name |
ROO007 | error | description is too short (< 50 characters) |
ROO008 | warning | description is too long (> 400 characters) |
| Rule ID | Severity | Description |
|---|---|---|
ROO010 | warning | Description missing a trigger condition keyword |
ROO011 | warning | Description does not start with an action verb or Use |
ROO012 | warning | Description contains vague words |
ROO013 | warning | Description has >75% token overlap with another skill |
ROO014 | warning | Skill name mentioned in description is inconsistent with frontmatter |
| Rule ID | Severity | Description |
|---|---|---|
ROO020 | error | No H1 heading found after frontmatter |
ROO021 | warning | H1 heading text does not match frontmatter name |
ROO022 | warning | Body has no numbered sections — likely a stub |
ROO023 | error | Markdown link target does not exist relative to repo root |
ROO024 | warning | Body references a mode slug not present in .roomodes |
ROO025 | warning | Body after frontmatter is < 100 characters — stub skill |
| Rule ID | Severity | Description |
|---|---|---|
ROO030 | warning | Body references a skill name with no corresponding skill.md |
ROO031 | warning | Handoff file path uses a non-standard pattern |
ROO032 | error | Two or more skills claim the same modeSlugs entry |
ROO034 | warning | Two skills have descriptions with high token overlap — ambiguous routing |
ROO035 | warning | Skill's modeSlugs references a mode not defined in any .roomodes file |
ROO036 | warning | A mode defined in .roomodes has no skill covering it |
Place a .skill-lint.yaml file at your repo root (copy from .skill-lint.yaml.example):
rules:
ROO007:
min_length: 60 # override default (50)
ROO008:
max_length: 300 # override default (400)
ROO013:
similarity_threshold: 0.80 # override default (0.75)
ignore:
- ".roo/skills/legacy/" # skip entire directory
- "ROO031" # globally disable a rule
# Custom vague words (appended to built-in list)
vague_words:
- "facilitates"
# Known mode slugs (appended to built-in list)
extra_mode_slugs:
- "my-custom-mode"
Four rules accept numeric overrides under the rules: key:
| Rule | Config key | Default | Effect |
|---|---|---|---|
ROO007 | rules.ROO007.min_length | 50 | Minimum description length in characters. Raise it if your team requires more detail. |
ROO008 | rules.ROO008.max_length | 400 | Maximum description length in characters. Lower it to enforce tighter descriptions. |
ROO013 | rules.ROO013.similarity_threshold | 0.75 | Token-overlap ratio (0–1) above which two skill descriptions are flagged as too similar. Raise it to allow more overlap; lower it to enforce stricter uniqueness. |
ROO034 | rules.ROO034.overlap_threshold | 0.60 | SequenceMatcher ratio (0–1) above which two skill descriptions are flagged as routing-ambiguous. |
Example — enforce 60-char minimum and flag descriptions that are 80%+ similar:
rules:
ROO007:
min_length: 60
ROO013:
similarity_threshold: 0.80
ignore:
- "ROO031" # disable rule globally
- ".roo/skills/legacy/" # skip all skill.md files under this path prefix
You can also suppress rules for a single run without touching the config:
skill-lint roo check . --ignore ROO012,ROO031
If your Roo setup uses custom modes not in the built-in list, add them so ROO005 does not flag them as unknown:
extra_mode_slugs:
- "my-workflow"
- "data-analyst"
The built-in vague words are: handles, manages, does, performs, processes.
Append your own:
vague_words:
- "facilitates"
- "coordinates"
- "oversees"
.roo/skills-build/coder/skill.md
✗ ROO008 description is 412 chars (max 400) [error]
⚠ ROO012 description uses vague word: "owns" [warning]
.roo/skills/api-schema-generator/skill.md
✗ ROO023 broken link: .roo/skills-build/coder/ui-patterns.md [error]
⚠ ROO022 no numbered sections found [warning]
────────────────────────────────────────────────────────────
2 errors | 2 warnings | 3 files scanned | 1 clean
# .pre-commit-config.yaml
repos:
- repo: https://github.com/hananel-e/agent-skill-lint
rev: v0.2.0
hooks:
- id: skill-lint-roo
name: skill-lint (Roo skills)
language: python
entry: skill-lint roo check
files: skill\.md$
pass_filenames: false
args: ["."]
pip install -e ".[dev]"
pytest
| Concern | Library |
|---|---|
| CLI | typer |
| Terminal output | rich |
| Frontmatter parsing | python-frontmatter |
| Markdown parsing | markdown-it-py |
| Token overlap (ROO013, ROO034) | difflib.SequenceMatcher (stdlib) |
| Config file | pyyaml |
| Slug registry | stdlib urllib, json |
| Routing simulator | stdlib difflib, re |
| Embedding backend (opt-in) | sentence-transformers + numpy |
| Build backend | hatchling |
| Test framework | pytest |
Zero heavy dependencies by default — no scikit-learn, no LLM calls.
Use pip install 'agent-skill-lint[embeddings]' to enable the embedding-based routing simulator.
roo score)Converts lint violations into a numeric score (0–100) and letter grade (A–F) per skill, plus an aggregate average. Use --fail-under N to gate CI on quality.
Scoring: base 100, -15 per ERROR, -5 per WARNING (clamped to 0)
Grades: A ≥90 B ≥80 C ≥70 D ≥60 F <60
roo simulate)Ranks all scanned skills by how well their description matches a natural-language query. Useful for spotting ambiguous descriptions before deploying to a live agent.
--embeddings: cosine similarity via sentence-transformers (more accurate)--top N: show top N matches--fuzzy-threshold: tune fuzzy matching sensitivityroo sync)Compares .roomodes definitions against scanned skill files. Detects:
.roomodes but no skill covers themmodeSlugs references a mode absent from .roomodesroo update-slugs)Fetches the latest known mode slugs from GitHub and caches them at ~/.cache/skill-lint/slugs.json. ROO005 reads from this cache so the known-slug list stays current without a code release.
| Rule | Description |
|---|---|
ROO034 | Two skills have descriptions with high token overlap — ambiguous routing |
ROO035 | Skill's modeSlugs references a mode not defined in any .roomodes file |
ROO036 | A mode defined in .roomodes has no skill covering it |
Heuristic rules are not perfect. ROO010–ROO014 and ROO034 fire on patterns that correlate with poor skill quality — they are not proofs. A description can pass all rules and still be a bad routing signal, or fail ROO011 and still work fine in practice. Treat warnings as prompts to review, not verdicts.
Routing simulator is heuristic by default. The roo simulate command uses keyword overlap, not semantic understanding. Use --embeddings with sentence-transformers for more accurate results.
Sync checker requires .roomodes. roo sync and ROO035/ROO036 are no-ops when no .roomodes files are found in the repo. They are only meaningful for Roo-based agent setups.
Apache 2.0
Download counts and popularity will appear here as the collector receives them.
| Version | Published | Direct dependencies | Open version |
|---|---|---|---|
| 0.2.0 | 26 Jun 2026 | 11 |
This describes our collected data; it is not a security assessment.
Shared repository data · GitHub
Observed since 20 Oct, 23:24 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
package:c7998d9b7814286b4b009900359927279a02b36e579e8c01a10c4a30b3afdf0e