Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/DjangoPeng/agentic-ainpx agentmods add skills/djangopeng/agentic-ai/crm-assistantWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/djangopeng/agentic-ai/crm-assistant)<a href="https://agentmods.dev/skills/djangopeng/agentic-ai/crm-assistant"><img src="https://agentmods.dev/badge/skills/djangopeng/agentic-ai/crm-assistant/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/djangopeng/agentic-ai/crm-assistant"><img src="https://agentmods.dev/badge/skills/djangopeng/agentic-ai/crm-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.01186 |
| Opus 5.5 | $0.00046 | $0.00474 |
| Sonnet 5.5 | $0.00023 | $0.00237 |
| Haiku 4.5 | $0.00011 | $0.00119 |
Grade A, and why
crm-assistant scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.jsoncustomer_profile_update.jsonopportunity_update.jsonfollow_up_task.jsonpre_meeting_brief.jsoncustomer_table_rows.jsonopportunity_snapshot_row.jsoncrm_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
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
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
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）
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.mdreferences/output_schemas.mdreferences/feishu-bitable-mapping.mdreferences/llm_prompt_template.mdreferences/llm_output_schema.mdreferences/openclaw_user_side_write_prompt.mdreferences/user_side_feishu_prompt.md
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 119 lines · 114 tokens per session scan A 345d5891af76
crm-assistant is a skill published in the GitHub repository DjangoPeng/agentic-ai (153 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session and 1,186 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
horizon
Install, configure, run, customize, schedule, and extend Horizon, the profile-driven news radar. Use for first-time Horizon installation, source selection and onboarding, generating or reading daily digests, tuning processing profiles and digest limits, setting up delivery and scheduled runs, diagnosing pipeline…
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
agent-initialization
Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt, before tool calls, or after a task). For an Agent with an in-app workbench, pair with penguin-plugin; for a standalone…
pptagent
Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.
awm-rsi-toolkit
Run AWM (Agent Workflow Memory, Wang et al. 2024) on an agent - induce reusable workflows from its successful trajectories, online over a training stream or offline from supplied experiences, then freeze the workflow memory and measure it on a published Benchmark.
update-setup
A one-time setup wizard for creating a personalised upgrade guide for a workspace. It checks for an existing guide, identifies the current version and installation clues, and requires confirmation of the installation method before writing a new guide.