القائمة
Design and package new Claude Code AgentSkills — covers structure, principles (concise, degrees of freedom), and the SKILL.md + resources anatomy
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Analyze financial text sentiment using FinBERT or LLM, returning a scored label (positive/negative/neutral) from -1.0 to 1.0
Search A-Share and HK stock tickers by name or code and retrieve OHLCV historical price data
Time-series market forecasting using the Kronos model with news-aware sentiment adjustment for OHLC price prediction
Fetch real-time hot finance news and unified trend reports from multiple sources (财联社, WallStreetCN, Weibo, Zhihu, etc.) and Polymarket prediction data
Perform finance web searches across multiple engines (Jina, DuckDuckGo, Baidu) and local RAG document retrieval with smart search caching
Generate Draw.io XML diagrams to visualize finance logic flows, investment theses, and signal transmission chains
| name | Skill Creator |
| description | Design and package new Claude Code AgentSkills — covers structure, principles (concise, degrees of freedom), and the SKILL.md + resources anatomy |
| category | tools-and-utilities/report-generators |
| tags | ["skill-authoring","meta","agent-skills"] |
This skill provides guidance for creating effective skills.
Skills are modular, self-contained packages that extend Codex's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Codex 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 Codex needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
Default assumption: Codex is already very smart. Only add context Codex doesn't already have. Challenge each piece of information: "Does Codex 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 Codex 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)
│ └── 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.)