suite-name
TRIGGER_DESCRIPTION. Use when USER_CONTEXT. Routes to specialists for CAPABILITIES.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
TRIGGER_DESCRIPTION. Use when USER_CONTEXT. Routes to specialists for CAPABILITIES.
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 | SUITE_NAME |
| description | TRIGGER_DESCRIPTION. Use when USER_CONTEXT. Routes to specialists for CAPABILITIES. |
One-sentence description of what this skill suite does.
skills/specialist-a/SKILL.mdskills/specialist-b/SKILL.mdskills/specialist-a/SKILL.md| Skill | Path | Purpose | Model Tier |
|---|---|---|---|
| specialist-a | skills/specialist-a/SKILL.md | Does X | analytical |
| specialist-b | skills/specialist-b/SKILL.md | Does Y | reasoning |
Read ONLY the relevant specialist SKILL.md based on classification above. Do not pre-load multiple specialists.
Cross-skill composition: Skills may reference other installed skills by name in procedures. These references are runtime-resolved (not context-loaded) and degrade gracefully if the referenced skill is not installed. This is distinct from the cross-specialist isolation rule (§2.5), which blocks file path references between siblings.
Pass between skills as structured JSON:
{
"source_skill": "specialist-a",
"findings": [],
"confidence": "high|medium|low"
}
Use when a user asks to read, analyze, summarize, or extract from a heavyweight file (PDF, DOCX, PPTX, XLSX, CSV, TSV). Converts the file into markdown or CSV first, generates a lightweight index, and only spends model tokens on the compressed artifact. Trigger on "read this PDF", "look through this spreadsheet", "summarize this deck", or any time raw file ingestion would waste tokens. Do NOT trigger for plain text, markdown, JSON, YAML, or source code files — those are cheap to read directly.
TRIGGER_DESCRIPTION. Use when USER_CONTEXT. Covers CAPABILITIES.