메뉴
Deprecated compatibility reference for numerical agent-skill ratings and rubric-based comparisons. Use the active creating-agent-skills workflow for current skill scoring, review, revision, and creation work.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/narumiruna/skills --skill scoring-agent-skills명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Draft, execute, or track lean, verifiable implementation plans for non-trivial migrations, refactors, PR splits, task checklists, and other work with sequencing, tradeoffs, unknowns, or risks, and delete them when complete; use writing-roadmap for strategic direction and skip small obvious tasks.
Create, revise, review, or track concise, outcome-oriented product and system roadmaps with phased milestone checkboxes and evidence-based progress, and delete them when complete; use writing-plans for executable task planning and implementation tracking.
Inspect, launch, configure, validate, and troubleshoot an installed Ghostty terminal, including helper CLI actions, keybind actions, themes, fonts, configuration files, and platform-specific behavior.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | scoring-agent-skills |
| description | Deprecated compatibility reference for numerical agent-skill ratings and rubric-based comparisons. Use the active creating-agent-skills workflow for current skill scoring, review, revision, and creation work. |
| metadata | {"internal":true} |
Use creating-agent-skills for the maintained workflow. Its explicitly requested Score mode preserves the former $scoring-agent-skills behavior and owns the current six-dimension rubric.
Do not score an ordinary review unless the user explicitly asks for ratings, numerical scores, a rubric, or a scored comparison. A scoring request remains read-only unless revisions are also requested.
For compatibility, establish the target-model baseline, inspect the skill and its relevant discovery and resource surfaces, apply the same rubric anchors to every assessed skill, support scores with direct evidence, and separate structural validation from qualitative judgment. Mark materially unavailable dimensions unassessed rather than inventing evidence.
Report the scope, baseline, dimension scores, one-decimal aggregate with coverage, evidence-based notes, validation evidence, and improvement priorities. State that source-and-structure scoring is not a runtime effectiveness benchmark.