Skill Entries

Skills define what Warden analyzes and when.

Fields

Field	Purpose
name	Skill name or path.
paths	Files to include as glob patterns.
ignorePaths	Files to exclude as glob patterns.
failOn	Minimum severity to fail: critical, high, medium, low, info, off.
reportOn	Minimum severity to report.
remote	GitHub repository for remote skills: owner/repo or owner/repo@sha.
model	Override the main agent model for this skill. See Models and Runtimes.
maxTurns	Optional max agentic turns per hunk.

Filters

Use paths and ignorePaths to scope a skill:

warden.toml

[[skills]]
name = "api-review"
paths = ["src/api/**/*.ts"]
ignorePaths = ["**/*.test.ts"]

[[skills.triggers]]
type = "pull_request"
actions = ["opened", "synchronize"]

Skill References

warden.toml

# Built-in skill
[[skills]]
name = "security-review"

# Relative path
[[skills]]
name = "./custom-skills/my-review"

# Remote skill
[[skills]]
name = "api-review"
remote = "your-org/warden-skills"

# Pinned remote skill
[[skills]]
name = "api-review"
remote = "your-org/warden-skills@abc123def"

See skill discovery for resolution order.