Agent skill

CRM Assistant

by DjangoPeng in DjangoPeng/agentic-ai

将销售会议 transcript、飞书会议原始 JSON、飞书云文档正文或 Word/DOCX 会议纪要,转换成 CRM 结构化结果,并按客户信息表 + 商机推进快照表两表模型生成/同步飞书多维表格记录时使用。适用于多轮客户推进、客户画像增量更新、商机阶段判断、Lead Score 计算,以及“弱值不覆盖旧值、沟通风格/风险顾虑合并”的客户字段更新规则。

MITAuto-check passedSales & Support

Install CRM Assistant

skills CLI
$ npx skills add DjangoPeng/agentic-ai --skill crm-assistant -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install DjangoPeng/agentic-ai crm-assistant --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/DjangoPeng/agentic-ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/CRM-Assistant/skills/crm-assistant .claude/skills/crm-assistant && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
crm-assistant
GitHub stars
152
Token cost
~681 tokens
SKILL.md length
121 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

将销售会议 transcript、飞书会议原始 JSON、飞书云文档正文或 Word/DOCX 会议纪要,转换成 CRM 结构化结果,并按客户信息表 + 商机推进快照表两表模型生成/同步飞书多维表格记录时使用。适用于多轮客户推进、客户画像增量更新、商机阶段判断、Lead Score 计算,以及“弱值不覆盖旧值、沟通风格/风险顾虑合并”的客户字段更新规则。

  • Works in 3 steps: 固定两表模型 → 客户信息更新规则 → 当前已知注意点
  • Tasks that involve Word documents
  • SKILL.md covers 这个 skill 负责什么, 当前项目的关键业务规则, 优先命令 and 需要写回飞书时, plus 3 more sections
  • Calls python

What it does

CRM Assistant is an agent skill from DjangoPeng/agentic-ai. 将销售会议 transcript、飞书会议原始 JSON、飞书云文档正文或 Word/DOCX 会议纪要,转换成 CRM 结构化结果,并按客户信息表 + 商机推进快照表两表模型生成/同步飞书多维表格记录时使用。适用于多轮客户推进、客户画像增量更新、商机阶段判断、Lead Score 计算,以及“弱值不覆盖旧值、沟通风格/风险顾虑合并”的客户字段更新规则。

Its SKILL.md is about 680 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Sales & Support, covering Word documents. It works with Microsoft Word and Feishu (Lark). The repository describes itself as: 一套经过生产验证的 OpenClaw + Claude Code 实战知识库:涵盖生产部署、IM 接入、模型配置、安全加固,以及一系列可落地的 AI Agent 业务流项目(小红书发布 / 财务票据 / 智能早报 / CRM / 量化投研 / 密钥巡检自愈)。 The licence is MIT.

When your agent uses it

  • Tasks that involve Word documents

Example prompts

  • “弱值不覆盖旧值、沟通风格/风险顾虑合并”
  • “/crm-assistant”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. 固定两表模型
  2. 客户信息更新规则
  3. 当前已知注意点

What it can do on your machine

Read from SKILL.md and the folder at commit c8bc8f1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

CRM Assistant loads about 681 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 121 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~681

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from DjangoPeng/agentic-ai at commit c8bc8f1, republished under its MIT licence (© DjangoPeng). 121 words, ~681 tokens.

Download SKILL.mdSave it as .claude/skills/crm-assistant/SKILL.md (or your agent's skills folder).
name
crm-assistant
description
将销售会议 transcript、飞书会议原始 JSON、飞书云文档正文或 Word/DOCX 会议纪要,转换成 CRM 结构化结果,并按客户信息表 + 商机推进快照表两表模型生成/同步飞书多维表格记录时使用。适用于多轮客户推进、客户画像增量更新、商机阶段判断、Lead Score 计算,以及“弱值不覆盖旧值、沟通风格/风险顾虑合并”的客户字段更新规则。

CRM Assistant

在销售会议已经有可读文本后使用本 Skill。当前项目已经收敛为一个 Python CLI:scripts/crm_assistant.py。

这个 skill 负责什么

把以下任一输入:

  • transcript.txt + context.json
  • 飞书会议原始 JSON
  • 飞书云文档导出的会议正文
  • Word / DOCX 会议纪要

转换成:

  • meeting_record.json
  • customer_profile_update.json
  • opportunity_update.json
  • follow_up_task.json
  • pre_meeting_brief.json
  • customer_table_rows.json
  • opportunity_snapshot_row.json
  • crm_packet.json
  • 在具备凭据时,进一步写回飞书多维表格

当前项目的关键业务规则

1. 固定两表模型
  • 客户信息(长期客户画像,按客户身份 upsert)
  • 商机快照(每次会议一条快照,保留推进轨迹)
2. 客户信息更新规则

对 客户信息的所有字段统一执行:

  • 如果本轮值是弱值(如 未明确 / 未知 / 待确认 / 空值),不要覆盖旧的明确值
  • 如果本轮值是新的明确判断,允许更新旧值
  • 沟通风格、风险顾虑 采用合并策略:保留旧值并追加新值,去重后写回
3. 当前已知注意点
  • 项目已经支持 DOCX 直连入口与飞书多维表格同步
  • 同一客户多轮推进时,客户信息做增量更新,商机快照表持续追加
  • 同一项目不同阶段应优先沿用同一个商机ID,不要每轮都新建商机
  • 机会名称 应优先采用 客户公司 - 项目主题,不要把联系人姓名列表拼到最前面

优先命令

A. 直接处理 Word / DOCX 并写 CRM 结果
bash
python ./scripts/crm_assistant.py ingest-docx-to-bitable \
  --docx-path ./meeting.docx \
  --output-dir ./runtime/your_case
B. 从飞书会议原始 JSON 提取并落 CRM
bash
python ./scripts/crm_assistant.py ingest-feishu-raw-to-bitable \
  --raw-input-path ./raw.json \
  --output-dir ./runtime/your_case
C. 从飞书云文档正文落 CRM
bash
python ./scripts/crm_assistant.py ingest-feishu-doc-to-bitable \
  --doc-markdown-path ./source_doc.md \
  --output-dir ./runtime/your_case
D. 仅做规则处理(已有 transcript + context)
bash
python ./scripts/crm_assistant.py process-transcript \
  --transcript-path ./transcript.txt \
  --context-path ./context.json \
  --output-dir ./runtime/your_case/process

需要写回飞书时

如果当前环境具备飞书 app 凭据,可在 ingest 命令上追加同步参数,例如:

  • --sync-feishu
  • --app-token-or-url
  • --customer-table-id
  • --opportunity-table-id
  • 以及 app 凭据来源(显式参数、配置文件或环境变量)

若当前环境没有凭据:

  • 先完成 CRM 结构化产物生成
  • 再返回待写入内容,或由具备飞书工具能力的一侧执行写表

按需读取的参考资料

仅在需要时再读:

  • references/input_schemas.md
  • references/output_schemas.md
  • references/feishu-bitable-mapping.md
  • references/llm_prompt_template.md
  • references/llm_output_schema.md
  • references/openclaw_user_side_write_prompt.md
  • references/user_side_feishu_prompt.md

自检建议

在修改脚本或规则后,至少做一项:

bash
python ./scripts/crm_assistant.py --help
python ./scripts/crm_assistant.py run-sample-tests
python ./scripts/crm_assistant.py run-feishu-pipeline-tests

补充:

  • 当前仓库默认不保留 assets/samples/,因此 run-sample-tests 无样本时会直接跳过
  • 如果要跑真实样本回归,请先补回脱敏样本与断言文件

输出要求

优先保证:

  • 中文业务摘要短而准
  • 阶段判断、Lead Score、下次动作可解释
  • 飞书字段名和当前表结构一致
  • 不要让弱值覆盖长期客户已知信息
  • 沟通风格 / 风险顾虑按合并策略处理

© DjangoPeng, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in CRM-Assistant/skills/crm-assistant of DjangoPeng/agentic-ai.

Open the folder on GitHubat commit c8bc8f1

Compare with similar skills

CRM Assistant next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

CRM Assistant compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CRM Assistant this skillDjangoPeng/agentic-ai152—~681Automated safety check: PassMIT
Feishu Docraucvr/Group-Goki1123 repos~592Automated safety check: PassMIT
Feishu DocCatCatUncle/openworkbuddy282—~750Automated safety check: PassCustom licence
Rfp Response Content Generationpnp/sharepoint-skills133—~4.8kAutomated safety check: PassMIT
Rfp Response Proposal Reviewpnp/sharepoint-skills133—~3.5kAutomated safety check: PassMIT
Feishu Docopenclaw/openclaw392k—~516Automated safety check: PassMIT

Similar skills

  • Feishu Doc

    raucvr/Group-Goki

    Feishu document read/write operations. An agent skill from raucvr/Group-Goki.

    112 GitHub starsUsed in 3 repos~592 tokens
    Productivity & AutomationAuto-check passed
  • Feishu Doc

    CatCatUncle/openworkbuddy

    创建/写入飞书云文档的完整 API 姿势(含插图)。要"发到飞书/建飞书文档"优先用 feishudoccreate 工具;需要手写 API(插图片/表格/自定义凭证)或排查权限、块结构报错时加载本技能。

    282 GitHub stars~750 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Rfp Response Content Generation

    pnp/sharepoint-skills

    Section-by-section proposal drafting agent. An agent skill from pnp/sharepoint-skills.

    133 GitHub stars~4.8k tokensUpdated today
    Sales & SupportAuto-check passed
  • Rfp Response Proposal Review

    pnp/sharepoint-skills

    Post-generation audit agent for proposal drafts. An agent skill from pnp/sharepoint-skills.

    133 GitHub stars~3.5k tokensUpdated today
    Sales & SupportAuto-check passed
  • Feishu Doc

    openclaw/openclaw

    Feishu document read/write workflows. An agent skill from openclaw/openclaw.

    392k GitHub stars~516 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Minimax DOCX

    poco-ai/poco-claw

    Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET).

    1.4k GitHub starsUsed in 7 repos~3.9k tokens
    Documents & OfficeAuto-check passed

More from DjangoPeng/agentic-ai

  • 当用户希望生成 AI 早报、运行晨报链路、查看今日资讯摘要,或消息中包含”早报””晨报””今日资讯””新闻摘要”等关键词时触发。

    152 GitHub stars~974 tokensUpdated 3 mo ago
    Auto-check: notes
  • Xhs Auto Publisher

    DjangoPeng/agentic-ai

    面向云服务器的小红书图文自动发布 Skill。适用于需要在 Linux 云服务器上,通过 Playwright/CDP、二维码人工接管、登录缓存、龙虾代发飞书群图片消息、截图留痕与审计日志来完成小红书草稿或发布流程的场景。

    152 GitHub stars~570 tokensUpdated 3 mo ago
    Auto-check passed
  • Financial Expense Automation

    DjangoPeng/agentic-ai

    当用户上传 PDF、JPG、JPEG、PNG 附件,或消息中包含"报销""发票""票据""录入""火车票""机票"等关键词时触发。对附件内容进行识别,若确认为报销票据则提取结构化字段并写入飞书多维表格;若识别后内容不是报销票据,告知用户并终止流程。

    152 GitHub stars~816 tokensUpdated 3 mo ago
    Auto-check passed
  • GitHub Secret Auditor

    DjangoPeng/agentic-ai

    当用户希望让 OpenClaw 通过 ACP 调度 Claude Code,对 GitHub 仓库进行 API Key、Token、密码、私钥、Webhook URL 等敏感信息泄露巡检、自动修复、验收、推送修复 commit,并通过飞书发送巡检报告时使用。

    152 GitHub stars~2.8k tokensUpdated 3 mo ago
    Auto-check: notes

Questions about CRM Assistant

What does CRM Assistant do?

将销售会议 transcript、飞书会议原始 JSON、飞书云文档正文或 Word/DOCX 会议纪要,转换成 CRM 结构化结果,并按客户信息表 + 商机推进快照表两表模型生成/同步飞书多维表格记录时使用。适用于多轮客户推进、客户画像增量更新、商机阶段判断、Lead Score 计算,以及“弱值不覆盖旧值、沟通风格/风险顾虑合并”的客户字段更新规则。. CRM Assistant is an agent skill from DjangoPeng/agentic-ai.

When should I use CRM Assistant?

CRM Assistant fits situations like: tasks that involve Word documents.

How do I install CRM Assistant in Claude Code?

Run `npx skills add DjangoPeng/agentic-ai --skill crm-assistant -a claude-code`. Or copy the skill folder (CRM-Assistant/skills/crm-assistant in DjangoPeng/agentic-ai) into .claude/skills/crm-assistant in your project. Claude Code loads it when a task matches its description.

How do I install CRM Assistant in Codex?

Run `npx skills add DjangoPeng/agentic-ai --skill crm-assistant -a codex`. Or copy the skill folder (CRM-Assistant/skills/crm-assistant in DjangoPeng/agentic-ai) into .agents/skills/crm-assistant in your project. Codex loads it when a task matches its description.

Can I use CRM Assistant in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DjangoPeng/agentic-ai --skill crm-assistant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/crm-assistant, .gemini/skills/crm-assistant, .github/skills/crm-assistant and .opencode/skills/crm-assistant in your project.

What does CRM Assistant need to run?

Going by SKILL.md and its folder, CRM Assistant needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does CRM Assistant access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is CRM Assistant safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does CRM Assistant use?

CRM Assistant is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does CRM Assistant use?

About 681 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to CRM Assistant?

Skills that share tags, products or a category with CRM Assistant: Feishu Doc (raucvr/Group-Goki, 112 stars), Feishu Doc (CatCatUncle/openworkbuddy, 282 stars), Rfp Response Content Generation (pnp/sharepoint-skills, 133 stars) and Rfp Response Proposal Review (pnp/sharepoint-skills, 133 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CRM Assistant?

DjangoPeng (a GitHub user) maintains it in DjangoPeng/agentic-ai, which has 152 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on July 8, 2026.

Source: DjangoPeng/agentic-ai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.