ytreenova
ytreenova contém 18 skills coletadas de robkam, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
Prevent and remove high-impact code-quality issues with principle-driven, risk-ranked recommendations and optional implementation.
Plan ytnova changes from behavior to implementation tasks with files, risks, invariants, and acceptance criteria. Use for design and technical-approach questions.
Implement approved ytnova tasks in C with minimal coherent edits, architectural safety, and terminal-verified proof.
Perform adversarial ytnova code review with severity-ranked findings, concrete fixes, and pass-fail gate decision.
Enforce strict ytnova bugfix loop: failing regression first, implementation second, passing proof third.
Run ytnova C quality gate for feature-sized changes using build, static analysis, valgrind, and pytest per docs/AUDIT.md.
Provide practical conventions and process guidance for ytnova and OSS C/TUI workflows, including personas, skills, review standards, and developer expectations.
Validate ytnova keybinding changes for ASCII/control-key collisions and keep menus/help/tests synchronized.
Keep ytnova manpage and usage docs synchronized by editing etc/ytnova.1.md as source and regenerating derived outputs.
Apply safe ncurses rendering patterns in ytnova to prevent flicker, color bleed, and redraw regressions.
Debug flaky PTY/pexpect tests in ytnova with deterministic synchronization and minimal timeout use.
Design deterministic pytest/pexpect regression tests for ytnova behavior, including fail-first evidence and clear diagnostics.
Defensive protocols to prevent excessive usage allowance, quota, token, and context window burn-up.
Design ytnova interactions to minimize menu depth and cognitive load using shallow, high-signal choice flows.
Detect prompt-chain offenders in ytnova UI flows and produce ranked compression plans that enforce the UX economy gate.
Scan prose for AI writing tells, report numbered findings by category with line references, wait for user approval before editing, and rescan after approved fixes.
Enforce structured PR scrutiny with risk-focused findings, plain-language summaries, and conflict triage outputs.
Enforce root-cause remediation for QA failures; no pass-by-patch, no test-to-green hacks, and no local suppressions without explicit approval.