← Back to Skills Marketplace
Resume-to-Tags
by
tuobadaidai
· GitHub ↗
· v1.0.0
· MIT-0
79
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install resume-to-tags
Description
从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签(含近义词扩展) → 创建飞书多维表格(多选标签字段) → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求"生成标签矩阵"、"人才标签库"、"简历转表格"、"候选人打标"时使用。
Usage Guidance
This skill is plausible for parsing resumes and building a tag matrix, but it contains two important ambiguities you should resolve before installing or using it:
1) Feishu integration: SKILL.md instructs creating and modifying a Feishu Bitable but the skill declares no Feishu credentials or required permissions. Confirm whether your agent/platform provides a Feishu connector and what exact permissions (create tables, modify fields, insert records) will be used. If the platform will request a Feishu token, review the scope and where that token is stored.
2) LLM and PII handling: scripts/extract_tags.py extracts phone and email and embeds resume text into a generated prompt that you are instructed to send to an LLM. Decide which model/endpoint will be used, verify its data retention and access policies, and avoid sending sensitive resumes to untrusted endpoints. Test the flow with synthetic or redacted data first.
Additional practical checks:
- Inspect how your agent maps the SKILL.md 'feishu_bitable_app_*' actions to concrete API calls and whether those calls will be audited/logged.
- Ensure the platform's connector prompts you before granting Feishu or LLM access; do not supply broad tokens to unknown code.
- Consider running extract_tags.py locally to see the produced prompt and JSON, and confirm synonyms.json meets your taxonomy needs.
If the author can provide explicit details about Feishu connector requirements and the expected LLM endpoint (or include code to call Feishu/LLM safely), the incoherence would be resolved. Otherwise treat the missing integration/credential details as a red flag and proceed cautiously.
Capability Analysis
Type: OpenClaw Skill
Name: resume-to-tags
Version: 1.0.0
The resume-to-tags skill bundle is a legitimate HR automation tool designed to extract professional attributes from resumes and organize them into a Feishu (Lark) Bitable. The Python script `scripts/extract_tags.py` uses regex for basic contact info extraction and prepares a structured prompt for an LLM, while `SKILL.md` provides clear instructions for the agent to manage the Feishu integration. The code and instructions are well-aligned with the stated purpose and show no signs of malicious intent, unauthorized data exfiltration, or harmful prompt injection.
Capability Assessment
Purpose & Capability
The skill claims to parse resumes into tags and populate a Feishu (飞书) Bitable. The repository contains a tag-extraction script and extensive synonym taxonomy, which aligns with the stated purpose. However, SKILL.md instructs creating/updating Feishu app/tables via actions (feishu_bitable_app_*), yet the skill declares no required credentials, env vars, or config paths for Feishu. That mismatch (expecting an external service but not declaring required access) is an incoherence that could hide assumptions about platform connectors or required permissions.
Instruction Scope
Instructions are focused on extracting tags (via an LLM prompt) and creating/populating a Feishu table. The included script (extract_tags.py) builds a strict JSON prompt and pre-extracts phone/email via regex, so PII (emails/phones and resume text) will appear in the prompt and in the script's JSON output. The script does NOT itself call any LLM or Feishu API; it returns the prompt and basic_info and instructs the operator/agent to send the prompt to an LLM and then perform synonyms expansion and table operations. The open-ended instruction to 'send prompt to LLM' leaves the endpoint, model, and data-handling policy unspecified — a data-flow ambiguity that users should confirm.
Install Mechanism
This is instruction-plus-scripts only with no install spec. Nothing is downloaded or written by an installer, which minimizes supply-chain risk. Files are small and local (a Python script and a JSON synonyms file).
Credentials
No environment variables, secrets, or config paths are declared, yet the workflow expects operations against Feishu (creating apps/tables/fields, batch insert). Either the skill assumes the host agent already has a Feishu connector/token (not disclosed), or the SKILL.md is incomplete. Additionally, the script extracts candidate phone and email (sensitive PII) and embeds resume text into the LLM prompt; users must ensure any LLM or logging endpoint has appropriate access controls. The lack of declared credentials for Feishu/LLM is disproportionate to the stated remote actions.
Persistence & Privilege
The skill does not request 'always: true' and has no install spec that modifies system-wide agent config. It does not appear to persist or escalate privileges beyond performing data extraction and (per instructions) invoking Feishu actions, assuming connector access exists.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install resume-to-tags - After installation, invoke the skill by name or use
/resume-to-tags - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
简历到纯标签矩阵的完整流程,含近义词扩展
Metadata
Frequently Asked Questions
What is Resume-to-Tags?
从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签(含近义词扩展) → 创建飞书多维表格(多选标签字段) → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求"生成标签矩阵"、"人才标签库"、"简历转表格"、"候选人打标"时使用。 It is an AI Agent Skill for Claude Code / OpenClaw, with 79 downloads so far.
How do I install Resume-to-Tags?
Run "/install resume-to-tags" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Resume-to-Tags free?
Yes, Resume-to-Tags is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Resume-to-Tags support?
Resume-to-Tags is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Resume-to-Tags?
It is built and maintained by tuobadaidai (@tuobadaidai); the current version is v1.0.0.
More Skills