Evaluate fak guard RSI loop maturity against journal-grounded KPIs.
npx skills add https://github.com/anthony-chaudhary/fak --skill guard-rsi-score
Please help me install this Agent Skill. Skill: guard-rsi-score Source: https://github.com/anthony-chaudhary/fak/tree/main/.claude/skills/guard-rsi-score Command: npx skills add https://github.com/anthony-chaudhary/fak --skill guard-rsi-score
This skill addresses the issue of RSI loops running in plan-mode without ever closing on real-world usage, ensuring that the guard's learning mechanism is grounded in actual decision journals rather than fabricated latency baselines.
Run the guard-rsi-score skill to evaluate the current RSI loop maturity and identify the highest priority debt to retire.
High-intent search queries and answers about installing and using this skill.
RSI loop maturity scoring evaluates decision journal data against established KPIs by enforcing deterministic metrics and journal-grounded honesty gates. This verifies that the loop's learning mechanism is based on actual adjudicated rows rather than fabricated latency baselines.
Transitioning RSI loops from plan-mode simulation requires enforcing deterministic metrics and processing real adjudicated rows from the fak guard decision journal. This structured refinement path facilitates loop closure using non-forgeable honesty gates.
Retire guard RSI debt by implementing required affordances like paired honesty tests and control-pane registration. This provides a structured path to evaluate the loop's realized value and close the simulation gap.
Yes, evaluating RSI scorecards requires integration with the fak guard control-pane and adherence to the scorecard doctrine. This ensures the evaluation relies on actual decision journals rather than fabricated baselines for loop closure.
Your RSI loop stays in plan-mode because it lacks journal-grounded honesty gates and deterministic metrics. Without evaluating actual fak guard decision journal data against KPIs, the loop cannot transition to real-world usage.
anthony-chaudharyCalculate milestone debt from support-maturity grid gaps and roadmap epic progress.
itou-daikiImplement Go testing patterns including table-driven tests, benchmarks, and fuzzing.
alexandervashurinMonitor live web apps for console errors and performance regressions after deployment.
anthony-chaudharyHalve actionable debt on a scorecard surface and re-pin baselines at saturation.
