Pitfall Experience logo

Pitfall Experience

Community
BENZEMA216
pitfall-experience

踩坑经验库 - 遇到问题时自动查阅 GitHub 上的历史踩坑记录(Capsule),解决后自动提交新经验回 GitHub Issue。激活条件:(1) 遇到报错/异常/失败时 (2) 配置不生效或行为异常时 (3) 成功解决一个非显而易见的问题后 (4) 用户要求查阅或记录经验时。关键词:踩坑、经验、报错、failed、error、不生效、为什么、pitfall、experience

Overview

PublisherBENZEMA216
Repositoryai-ecommerce-agent-skills
Skill namepitfall-experience
Stars
82
Forks
11
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by BENZEMA216 on GitHub. Read the source before you install it.

Installation

Install the Pitfall Experience AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/BENZEMA216/ai-ecommerce-agent-skills/tree/main/pitfall-experience
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/BENZEMA216/ai-ecommerce-agent-skills.git /tmp/ai-ecommerce-agent-skills
mkdir -p .claude/skills
cp -r /tmp/ai-ecommerce-agent-skills/pitfall-experience .claude/skills/pitfall-experience
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pitfall Experience in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pitfall Experience on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pitfall Experience is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

踩坑经验库 (Pitfall Experience)

遇到问题时查阅 GitHub 上的历史经验,解决问题后将新经验提交回去。

核心规则

  1. 遇到任何报错或异常时,先查阅经验库再尝试修复
  2. 成功解决非显而易见的问题后,必须提交新 Capsule 回 GitHub
  3. 所有操作通过 GitHub API 完成,不需要 git clone

经验仓库

工作流

Phase 1: 查阅经验(遇到问题时)

当遭遇错误/异常/配置不生效时,立即执行:

步骤 1 — 获取 Capsule 索引

bash
curl -s https://api.github.com/repos/BENZEMA216/openclaw-pitfalls/contents/capsules | python3 -c "import sys,json; [print(f['name'], f['download_url']) for f in sorted(json.load(sys.stdin), key=lambda x: x['name'])]"

步骤 2 — 读取相关 Capsule

bash
curl -s https://raw.githubusercontent.com/BENZEMA216/openclaw-pitfalls/main/capsules/PIT-XXX.yaml

步骤 3 — 批量搜索关键词

bash
GITHUB_TOKEN=$(cat /root/.openclaw-claw2/credentials/github_token)
curl -s -H "Authorization: token $GITHUB_TOKEN" "https://api.github.com/search/code?q=关键词+repo:BENZEMA216/openclaw-pitfalls+path:capsules"

步骤 4 — 读取 README 索引表

bash
curl -s https://raw.githubusercontent.com/BENZEMA216/openclaw-pitfalls/main/README.md

Phase 2: 应用经验

  1. 读取 Capsule 的 correct_process 字段
  2. 严格按照 correct_process 的步骤执行,不要自行发挥
  3. 执行完后验证修复结果

Phase 3: 提交新经验(成功解决问题后)

当成功解决了一个非显而易见的问题后,必须将经验提交回 GitHub。

步骤 1 — 确定新 Capsule 编号

bash
LAST_ID=$(curl -s https://api.github.com/repos/BENZEMA216/openclaw-pitfalls/contents/capsules | python3 -c "import sys,json; files=json.load(sys.stdin); ids=[int(f['name'].replace('PIT-','').replace('.yaml','')) for f in files if f['name'].startswith('PIT-')]; print(max(ids) if ids else 0)")
NEW_ID=$((LAST_ID + 1))
NEW_PIT=$(printf 'PIT-%03d' $NEW_ID)
echo "New capsule: $NEW_PIT"

步骤 2 — 用 Python 脚本提交 Issue

bash
python3 /root/.openclaw-claw2/skills/pitfall-experience/scripts/submit_capsule.py \
  --id "$NEW_PIT" \
  --title "简短问题描述" \
  --severity "high" \
  --category "config" \
  --yaml-file /tmp/capsule.yaml

Capsule YAML 格式

yaml
id: PIT-XXX
trigger_time: "YYYY-MM-DD HH:MM"
category: repair | config | env
severity: critical | high | medium | low

problem:
  signal: "具体的错误信号/日志"
  description: "问题的本质是什么"
  env_fingerprint:
    platform: linux
    openclaw: "2026.2.9"
    profile: "claw2"

error_process:
  - step: "做了什么"
    result: "得到了什么错误结果"

correct_process:
  - step: "应该怎么做"
    detail: "具体操作"
  - step: "验证"
    detail: "如何确认修复成功"

root_cause: "根因分析"
confidence: 0.9
blast_radius:
  files: ["affected_files"]
  scope: "影响范围"

判断标准

提交新经验:

  • 配置修改后重启不生效,发现需要额外步骤
  • 命令报错但错误信息有误导性
  • 文档没提到的隐含依赖或前置条件
  • 不同环境/profile 下行为不一致

不需要提交:

  • 简单拼写错误
  • 文档已明确说明的已知限制

严重度判断

级别标准
critical服务完全不可用,或数据丢失风险
high核心功能受损但有 workaround
medium非核心功能受影响,或需要较多时间排查
low体验问题,不影响核心功能

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Pitfall Experience AI skill do?

踩坑经验库 - 遇到问题时自动查阅 GitHub 上的历史踩坑记录(Capsule),解决后自动提交新经验回 GitHub Issue。激活条件:(1) 遇到报错/异常/失败时 (2) 配置不生效或行为异常时 (3) 成功解决一个非显而易见的问题后 (4) 用户要求查阅或记录经验时。关键词:踩坑、经验、报错、failed、error、不生效、为什么、pitfall、experience

Why use Pitfall Experience on TypingMind?

Because you install it once and use it with any model. Pitfall Experience is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pitfall Experience in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/BENZEMA216/ai-ecommerce-agent-skills/tree/main/pitfall-experience. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Pitfall Experience?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pitfall Experience?

As many as you like. As long as a model supports skills, you can use Pitfall Experience with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pitfall Experience AI skill free?

It is published on GitHub by BENZEMA216. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇