atlas
atlas is a Codebase mapping & onboarding skill for AI agents, published by LordCasser in the atlas repository on GitHub. Skillspace rates atlas D (69/100) and it passed the safety scan; the rating is based on static analysis only.
MCP-first deterministic local code-facts engine (tree-sitter → SQLite) for scoped symbol search, callers/callees, paths, impact, variable/call tracing, and C/C++ lifecycle via Focus-driven on-demand extraction. Use for structure, data/call flow, change impact, or agent context on a local checkout—prefer Atlas over filename guesses or blind text search. Always project(open) then scoped MCP tools; do not run atlas index from the agent (blocks large repos).
- Grade
- D
- Quality
- 69 / 100
- Safety
- Passed
- GitHub stars
- 32
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 79 / 100
- Maturity
- Packaged: licensed, with a version or references
- 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.