{"id":"massimodeluisa-recursive-decomposition-skill","name":"recursive-decomposition-skill","af_score":37.8,"security_score":17.5,"reliability_score":17.5,"what_it_does":"A Claude Code skill/plugin that applies recursive decomposition strategies (filtering, chunking, parallel sub-agenting, verification, and synthesis) to improve handling of long-context tasks such as multi-file codebase analysis and multi-document aggregation.","best_when":"When Claude Code needs broader coverage than the context window can comfortably handle, especially for 10+ files / large token sets requiring synthesis and verification.","avoid_when":"When tasks are small/specific (e.g., grep-like lookups) or latency/cost must be minimized over completeness.","last_evaluated":"2026-03-30T15:31:58.075297+00:00","has_mcp":false,"has_api":false,"auth_methods":[],"has_free_tier":false,"known_gotchas":["This skill is triggered by intent/phrasing patterns (e.g., 'analyze all files', 'search across the codebase'); unexpected trigger wording may prevent it from activating.","The workflow adds decomposition/parallelization overhead; for small tasks it may reduce efficiency versus direct answers.","The provided README discusses strategies at a conceptual level but does not describe deterministic output schemas or tool-level contracts that an agent could rely on."],"error_quality":0.0}