Run a read-only surface-pruning audit against a fleet repo. Combines deadcode whole-program reachability with .ralph/tool_benchmarks.jsonl telemetry into a ranked list of candidates-for-removal (zero-call MCP tools, long-tail tools, unreachable Go functions). Use before a deletion PR; never mutates the target.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "ralphglasses-dead-surface-audit" with this command: npx skills add hairglasses-studio/skillsmp-hairglasses-studio-hairglasses-studio-ralphglasses-dead-surface-audit
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Multi-agent reflective review of pruning candidates from ralphglasses_dead_surface_audit. Spawns three sub-agent reviewers (diff / holistic / test-impact) via `claude --print`, requires ≥2/3 safe-to-delete consensus before forwarding to the auto-revert tool. Use when an audit returns >5 candidates and you want a safety net beyond the single-handler ranking score.
Run end-to-end repo self-development workflows for ralphglasses, including repo surface audit, roadmap analysis, loop or marathon execution, merge verification, and durable docs writeback.
Fleet management and self-improvement tools for ralphglasses
Provides AI-driven portfolio risk analysis for China A-shares with VaR, stress testing, tail risk, factor exposure, and risk attribution for fund managers.