메뉴
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
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 | skill-creator |
| description | Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. |
| license | Complete terms in LICENSE.txt |
This skill provides guidance for creating effective skills.
Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.
The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
Default assumption: Claude is already very smart. Only add context Claude doesn't already have. Challenge each piece of information: "Does Claude really need this explanation?" and "Does this paragraph justify its token cost?"
Prefer concise examples over verbose explanations.
Match the level of specificity to the task's fragility and variability:
High freedom (text-based instructions): Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.
Medium freedom (pseudocode or scripts with parameters): Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.
Low freedom (specific scripts, few parameters): Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.
Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).
Every skill consists of a required SKILL.md file and optional bundled resources:
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter metadata (required)
│ │ ├── name: (required)
│ │ ├── description: (required)
│ │ └── compatibility: (optional, rarely needed)
│ └── Markdown instructions (required)
└── Bundled Resources (optional)
├── scripts/ - Executable code (Python/Bash/etc.)
├── references/ - Documentation intended to be loaded into context as needed
└── assets/ - Files used in output (templates, icons, fonts, etc.)
Every SKILL.md consists of:
name and description fields (required), plus optional fields like license, metadata, and compatibility. Only name and description are read by Claude to determine when the skill triggers, so be clear and comprehensive about what the skill is and when it should be used. The compatibility field is for noting environment requirements (target product, system packages, etc.) but most skills don't need it.scripts/)Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.
references/)Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.
assets/)Files not intended to be loaded into context, but rather used within the output Claude produces.
Skills use a three-level loading system to manage context efficiently:
Keep SKILL.md body to the essentials and under 500 lines. Split content into separate files when approaching this limit. When splitting out content, reference them from SKILL.md and describe clearly when to read them.
Clearly understand concrete examples of how the skill will be used. Ask questions like:
Analyze each example by considering how to execute it from scratch, then identify what scripts, references, and assets would be helpful for repeated execution.
Run the init script to create the template:
scripts/init_skill.py <skill-name> --path <output-directory>
Remember: the skill is being created for another instance of Claude to use. Include information that would be beneficial and non-obvious.
Consult these guides based on your skill's needs:
name: The skill namedescription: Primary triggering mechanism. Include both what the skill does AND when to use it. All "when to use" information goes here, not in the body.Write instructions for using the skill and its bundled resources.
scripts/package_skill.py <path/to/skill-folder> [output-directory]
The script validates and then creates a .skill file (zip format) for distribution.
自主 CEO 模式。代替使用者監管整個 Agent Team，自主決策研發方向、派工、監控、處理異常。支援 2+ 小時 headless 運行，跨 context window 自動接力。Use when 'supervise', '監管', '自主運行', 'autopilot', '代替我管', 'run team', '幫我盯', '工作幾小時'.
創新 Phase 2：跨域映射 + 數據源評估。分析技術遷移可行性與新數據源 alpha 潛力。Use when 'cross-domain mapping', '跨域映射', 'data source evaluation', '數據源評估'.
創新 Phase 3：POC 原型實作。產出可執行的 proof-of-concept 程式碼。Use when 'build POC', 'prototype', '做原型', 'proof of concept'.
創新 Phase 1：方向偵測 + 前沿掃描。搜論文、GitHub、社群找最新方法。Use when 'frontier scan', '搜論文', 'explore new tech', '前沿掃描'.
創新 Pipeline 指揮官。前沿探索 → 跨域映射 → 數據源評估 → POC 原型 → 可行性裁定。可一鍵跑完或逐步執行。Use when 'innovate', '創新', '新方法', '探索', 'what if we try', '新數據源', '新想法'.
創新 Phase 4：可行性裁定、評分、記錄到 innovation_log、銜接後續。Use when 'innovation verdict', '裁定', 'feasibility score', '可行性評估'.