Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for heavy agent users whose local setup has accumulated too many tools, skills, and prompts and now burns context or slows routing before real work starts.
Who should use it
Who should skip it
Pass on thousandflowers/skillreaper if its scope or audience does not match what your team is building right now.
About this signal
thousandflowers/skillreaper is tracked by RepoRadar as a agent ops tool in the Developer Tools section. It was first seen on 2026-06-27 and last updated on 2026-06-27. The current verdict is 'try now' with a Gold tier and easy setup difficulty. thousandflowers/skillreaper leads on workflow potential (9.6) and setup ease (8.8); its lowest signal is maturity (6.9), so factor that in before investing setup time. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned thousandflowers/skillreaper a composite score of 8.1 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 28.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
The prune, mute, and hook commands write inside your local agent directories, so start with the read-only scan and review the manifest before changing anything; Transcript analysis exposes the names and behavior of tools your sessions used, so keep the report local if your setup includes sensitive internal workflows; Low-usage tools are not always bad tools, so treat the recommendations as evidence for review rather than as automatic truth.