← ClaudeAtlas

library-evaluationlisted

Use when adding new packages, choosing between dependency alternatives, or auditing existing libraries. Covers popularity metrics, maintenance health, bundle impact, API quality, and license compatibility with weighted scoring. Do not use for evaluating frameworks or platforms (use technology-radar) or comparing competing products (use competitive-analysis).
dtsong/agentic-council · ★ 0 · AI & Automation · score 78
Install: claude install-skill dtsong/agentic-council
# Library Evaluation ## Purpose Produce a structured, weighted comparison of candidate libraries to make dependency decisions based on evidence rather than familiarity or hype. ## Scope Constraints - Evaluates individual libraries and packages, not full frameworks or platforms. - Focuses on technical fitness for the project, not market positioning or competitive landscape. - Does not perform security audits; flag security concerns for handoff to the appropriate skill. ## Inputs - The need or problem the library should solve - Any known candidates (or let the process discover them) - Project constraints (bundle size budget, license requirements, framework compatibility) - Current tech stack and existing dependencies ## Input Sanitization No user-provided values are used in commands or file paths. All inputs are treated as read-only analysis targets. ## Procedure ### Step 1: Identify Candidate Libraries - Search npm, GitHub, and community recommendations for the problem space - Include the most popular option, the most recently trending option, and at least one lightweight alternative - Note any candidates already in use in the codebase's dependency tree ### Step 2: Evaluate Popularity Metrics For each candidate: - npm weekly downloads (absolute number and trend direction) - GitHub stars and recent star velocity - Community size (Discord, Stack Overflow tags, GitHub Discussions activity) - Notable adopters (large companies or well-known projects using it) ### Step