ways-settings
ways-settings is a Claude Code configuration skill for AI agents, published by aaronsb in the agent-ways repository on GitHub. Skillspace rates ways-settings D (68/100) and it passed the safety scan; the rating is based on static analysis only.
Manage Claude Code's settings.json as a composable, versioned store of interviewed config fragments — scaffold from the schema, lint, compile, and project into ~/.claude, with rationale and provenance. Synthesizes Claude Code's own config knowledge and its /insights usage report with the operator's history. Use when the operator wants to build up, review, or reason about their configuration as a documented fragment store. Not for a one-off settings.json change (Claude Code's built-in update-config handles those), editing individual ways (the ways skill), CLAUDE.md memory, or updating the agent-ways install (ways-update).
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 20
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.