Research a topic deeply, plan a blog step by step, and write a long-form article with structured Markdown outputs in the current working directory. Supports multilingual writing, source tracking, metadata generation, and optional image insertion via available image tools.
Generate complete, production-ready Agent Skill packages via a 7-step pipeline. Each step has defined inputs, outputs, and quality constraints.
空投项目评估 — 基于 v3 门槛+加权模型（发币意愿/风险 门槛检查 → 筹码/链上/竞争/成本 加权评分） 百分制 × 系数，输出档位判定（Sprint/中等维护/低保维护）。 输出格式对齐 P-xxx 空投评估模板。Triggers on "空投评估", "airdrop evaluation", "项目评分", "airdrop scoring", "空投分析", "evaluate airdrop", or "P-xxx". --- # Airdrop Evaluation (v3) 基于门槛+加权评分框架对空投项目进行综合评估，输出 P-xxx 格式报告。 ## Data Source Priority ### Layer 1: MCP - **coingecko** — 代币信息（如已发币） - **dune** — 链上数据（交易指标、用户增长、手续费、供需分析、KPI 汇总） ### Layer 2: Chrome CDP - `defillama.com/protocol/{protocol}` — TVL 趋势、协议数据 - 官网、文档、Discord ### Layer 3: Web Search - 融资背景、团队信息、社区规模、积分机制、官方公告、竞品信息 ## Workflow ### Step 1: Project Identification + Document Collection - 解析项目名称 - 查找官网、文档、社交媒体链接 - 确认项目状态（是否已发币、是否有积分系统） - **主动询问用户是否有项目相关文档**（白皮书、tokenomics、积分规则等） - 用户提供 → 优先作为评分依据，按文档性质标注置信度 - 官方公告/白皮书/合约文档 → ◆ - 多源交叉验证的分析 → ◇ - 单一来源未验证 → ○ - 用户没有 → 继续自动拉取 ### Step 2: Auto-Fetch Data 自动拉取可获取的数据： - coingecko: 代币信息（如已发币） - dune: 链上数据 - 日度交易指标（交易次数、交易量 USD、手续费 USD、Unique Takers/Makers） - 用户增长（新增用户、7日均值、累计用户） - 协议收入/手续费趋势 - 供需背离分析（供给侧 vs 需求侧指标趋势对比） - 汇总 KPI（总交易量、总交易数、总手续费、总用户数、峰值日、WoW 变化） - defillama: TVL 趋势（Chrome CDP） - Web Search: 融资轮次、估值、团队背景、积分机制细节、社区规模、竞品信息 （URL 未知时先 Web Search 取 URL 再 Chrome CDP 访问，Web Search 无法找到 URL 则直接 Web Search 摘要兜底） ### Step 3: Gate Check (门槛检查) 预填"发币意愿"和"风险等级"评分 + 依据 + 置信度标注： | 门槛维度 | 建议分数 | 系数 | 依据 | 置信度 | |---------|---------|------|------|-------| | 发币意愿 | X | ×Y | [data] | ◆/◇/○ | | 风险等级 | X | ×Y | [data] | ◆/◇/○ | **明确标注为建议评分，等待用户确认或调整。** - 用户确认后： - 任一维度 < 3 → 输出"放弃"精简报告，**流程终止** - 两项都 ≥ 3 → 记录系数，进入 Step 4 ### Step 4: Weighted Scoring (加权评分预填 + 用户确认) 预填四个加权维度评分建议： | 维度 | 权重 | 建议分数 | 依据 | 不确定性 | 置信度 | |------|------|---------|------|---------|-------| | 筹码获取 | 30% | X | [data] | [unknowns] | ◆/◇/○ | | 链上健康度 | 25% | X | [data] | [unknowns] | ◆/◇/○ | | 竞争定位 | 25% | X | [data] | [unknowns] | ◆/◇/○ | | 单位成本 | 20% | X | [data] | [unknowns] | ◆/◇/○ | **明确标注为建议评分，等待用户确认或调整。** 用户可以补充自己的判断依据。 ### Step 5: Calculate + Report (计算 + 生成报告) - 计算最终分 - 档位判定（含降档规则） - 催化剂表格（如有） - 按模板输出报告 ## Output Template — Gate
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
