원클릭으로
corpus-shared-c
Use when verifying duplicate-block detection across a fixture trio.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when verifying duplicate-block detection across a fixture trio.
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
| name | corpus-shared-c |
| description | Use when verifying duplicate-block detection across a fixture trio. |
| version | 0.1.0 |
Serves as the gamma member of the shared-block fixture trio.
The corpus root path handed to the gamma assertions.
The gamma member of the fixture tree is unchanged.
Shared corpus preamble line one. Shared corpus preamble line two. Shared corpus preamble line three. Shared corpus preamble line four. Shared corpus preamble line five. Shared corpus preamble line six. Shared corpus preamble line seven. Shared corpus preamble line eight. Shared corpus preamble line nine. Shared corpus preamble line ten. Shared corpus preamble line eleven. Shared corpus preamble line twelve. Shared corpus preamble line thirteen. Shared corpus preamble line fourteen. Shared corpus preamble line fifteen. Shared corpus preamble line sixteen.
An empty findings list for the gamma member.
Given the input gamma, the expected output is gamma-trio-clean.
Diverging from the shared preamble in the gamma copy.
I help with tidying up messy notes whenever it seems useful.
Use when the user asks to create, write, compose, or design a new agent skill — turning an idea, notes, requirement, or repeated workflow into a SKILL.md with eval cases and a trigger set through an interview → draft → critique → refine loop.
Use when the user asks to lint, audit, test, benchmark, validate, or fix an agent skill — from a single SKILL.md frontmatter check to trigger-accuracy measurement or a corpus-wide audit of installed skills for duplication — driving the shakespii CLI (init, lint --json, test --run, bench) to resolve findings until clean.
A tiny practice skill that summarizes shell command output into one line.
Use when the user asks for a one-word acknowledgement drill — replies with exactly the word the drill names.
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"