Skip to content
Agentmart
Submit a tool

evolve

自进化能力:感知生态变化、评估融合方案、驱动版本迭代

Skill by chengxuniucode

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying evolve?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/chengxuniucode-evolve

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

自进化能力:感知生态变化、评估融合方案、驱动版本迭代

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/evolve

What's inside

Skill name
evolve
Description
自进化能力:感知生态变化、评估融合方案、驱动版本迭代
License
MIT
Instructions
170 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Evolve Skill

## 目标

使 ForgeTeam 具备自我进化能力。不依赖对特定项目的跟踪,而是:
1. 持续感知整个 AI 编码生态的技术方向
2. 从自身使用数据中发现改进机会
3. 结构化评估新方向的融合价值
4. 驱动版本迭代决策

## 进化不等于堆功能

进化的核心判断标准:
- 是否让用户**更快**交付?
- 是否**降低**了认知负担?
- 是否保持了"one person, full team"的承诺?
- 是否符合进化红线?

## 执行步骤

### Step 1: 感知 (Sense)

扫描以下信息源,发现值得关注的变化:

| 信息源 | 关注维度 |
|--------|---------|
| GitHub Trending (AI/DevTools) | 新工具、新范式、社区热度 |
| AI 工具 Release Notes | 新能力、新协议、Breaking Changes |
| 社区 Issues / Discussions | 用户痛点、Feature Request、使用模式 |
| 技术博客 / 论文 | 新研究方向、行业趋势 |
| 本地 usage analytics | skill 跳过率、断路器频率、完成时间 |

输出:**变化信号列表**

```markdown
## 感知信号 ({date})

### 信号 1: {描述}
- 来源: {URL / 项目 / 论文}
- 方向: {agent 编排 / 工作流 / 上下文 / 质量 / 协议}
- 时效性: {短期热点 / 中期趋势 / 长期方向}
- 与 ForgeTeam 相关度: {高 / 中 / 低}

### 信号 2: ...
```

### Step 2: 评估 (Evaluate)

对高相关度信号进行深度评估:

```
信号 → 问自己 5 个问题:

1. 这解决了什么真实痛点?(不是"看起来酷")
2. ForgeTeam 用户是否有此需求?(看 Issues / analytics)
3. 融合代价多大?(改核心 vs 加扩展 vs 只改文档)
4. 是否违反进化红线?
5. 投入产出比:这个方向值得现在投入吗?
```

评估矩阵:

| 维度 | 得分标准 |
|------|---------|
| 痛点真实度 | 有用户反馈 > 有行业数据 > 仅有理论支持 |
| 融合代价 | 改文档 < 加 extension < 加 core skill < 改架构 |
| 时效性 | 长期趋势 > 中期方向 > 短期热点 |
| 竞争态势 | 我们不做用户会流失 > 锦上添花 > 可有可无 |

### Step 3: 决策 (Decide)

根据评估结果,给出决策建议:

| 决策 | 条件 | 动作 |
|------|------|------|
| **立即融合** | 痛点真实 + 代价低 + 时效紧 | 生成 EP → 排入下个 minor |
| **规划融合** | 痛点真实 + 代价中等 + 长期趋势 | 生成 EP → 排入 roadmap |
| **持续观察** | 方向对但时机不成熟 | 记录到进化雷达 |
| **明确拒绝** | 违反红线 / ROI 太低 | 记录拒绝原因 |

### Step 4: 产出 (Output)

根据决策生成对应产出:

**进化建议报告(`evolution-report.md`):**

```markdown
# Evolution Report — {date}

## 扫描范围
- 时间窗口: {上次 evolve 到现在}
- 信息源: {扫描了什么}

## 发现信号: {N} 个

## 建议动作

### 立即融合 ({N} 项)
1. {信号} → {建议方案} → EP-{NNN}

### 规划融合 ({N} 项)
1. {信号} → {建议方向} → 排入 v{X.Y}

### 持续观察 ({N} 项)
1. {信号} → {观察理由}

### 明确拒绝 ({N} 项)
1. {信号} → {拒绝理由}

## 本期进化健康度
- 核心 skill 稳定度: {无变更 / 有优化 / 有重构}
- Extension 活跃度: {新增 N / 更新 N / 废弃 N}
- 社区贡献: {PR N / Issues N / EP N}
- 用户反馈趋势: {正面 / 中性 / 需关注}
```

**进化提案(如决策为"融合"):**
- 按 `evolution/EP-000-template.md` 格式生成

From chengxuniucode/ForgeTeam, MIT.

More from chengxuniucode/ForgeTeam

Signals

Stars
2
Forks
1
Open issues
0
Last commit (this folder)
May 24, 2026 (5 months ago)
Last release
Aug 5, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from chengxuniucode

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get evolve running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying evolve?

CallGet help
Cite this page

evolve skill. Agent Mart. https://agentmart.dev/skills/chengxuniucode-evolve (last updated 2026-10-24)