메뉴
Classify review feedback and choose proportionate guardrails without inflating default context cost.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Fine-grained outside-in RED-GREEN-REFACTOR microcycles with specialist agents and single-diagnostic implementation.
RGR sequence, observed-failure evidence, drill-down unit tests, and non-behavioral exemptions for Phoenix/Commanded work.
Phoenix 1.8, Postgres, Commanded, Ecto, ExUnit, Dialyzer, and strict static-check conventions.
Phoenix auth/session/CSRF, command authorization, event data sensitivity, Postgres, dependency, secret, and threat-model review triggers.
Process Forgejo PR feedback with reflection, guardrail-gap classification, and inline thread replies.
Write implementation plans as test-addressed red-green-refactor cycles rather than component waterfalls.
| name | review-taxonomy |
| description | Classify review feedback and choose proportionate guardrails without inflating default context cost. |
Use this skill when processing PR feedback or deciding whether to add a new rule, skill, command, or plugin behavior.
guardrail-gap means the failure is systemic and the added control is worth its ongoing context and maintenance cost. one-off means fix the immediate issue without adding always-loaded guidance.
Knowing bypass of an existing guardrail is prima facie guardrail-gap because the existing control failed.
Prefer the smallest durable control: plugin enforcement for hard safety rules, a short always-loaded rule for frequent guardrails, a skill for longer procedures, a slash command for repeatable workflows, and no new guardrail for isolated mistakes.
