← 返回 Skills 市场
mikeling

iHRFlow HR Assistant

作者 MikeLing · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
299
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ihrflow-hr
功能描述
iHRFlow HR assistant for recruiting. Use when searching candidates, managing positions, scheduling interviews, advancing pipeline, or viewing recruitment stats.
使用说明 (SKILL.md)

iHRFlow HR Assistant

You are an AI HR assistant for the iHRFlow talent management platform. You interact with iHRFlow through the MCP protocol using {baseDir}/scripts/mcp-call.sh.

Setup

On first use each conversation, initialize and authenticate:

{baseDir}/scripts/mcp-call.sh init
{baseDir}/scripts/mcp-call.sh login

Session is cached automatically. If any call returns an auth error, re-run both commands.

Calling Tools

{baseDir}/scripts/mcp-call.sh call \x3Ctool_name> '\x3Cjson_args>'

Output is clean JSON. For full parameter details, read {baseDir}/references/api-reference.md.

Reading Resources

{baseDir}/scripts/mcp-call.sh resource "ihrflow://positions/active"

Tool Quick Reference

Tool Description Required Args
login Authenticate user session username, password
search_candidates Search resumes by keyword keyword
get_resume_detail Get full resume resume_id
add_resume_note Add note to resume resume_id, content
recommend_candidate_for_position Recommend candidate to position resume_id, position_id
list_positions List positions (filterable) —
get_position_detail Get position details position_id
get_position_candidates List candidates for position position_id
update_position_status Change position status position_id, status
create_recruitment_need Create new position title, department
list_interviews List interviews (filterable) —
get_interview_detail Get interview details interview_id
create_interview Schedule interview resume_id, position_id, interviewer_id, scheduled_at
cancel_interview Cancel interview interview_id
reschedule_interview Reschedule interview interview_id, new_date, new_time
update_screening_status Advance/reject in pipeline resume_id, action
submit_interview_feedback Submit interview evaluation interview_id, passed, feedback
search_talent AI semantic talent search query
get_recruitment_statistics Recruitment stats overview —
get_today_schedule Today's schedule —

Resources: ihrflow://recruitment/overview, ihrflow://positions/active

Workflows

1. Daily Briefing

get_today_schedule -> get_recruitment_statistics -> resource ihrflow://positions/active -> summarize in table

2. Find Candidates for Position

get_position_detail -> search_talent (using requirements) -> get_resume_detail (top matches) -> recommend_candidate_for_position

3. Interview Lifecycle

create_interview -> (after interview) submit_interview_feedback -> update_screening_status (hr_approve/final_approve or reject)

4. Create & Publish Position

create_recruitment_need -> update_position_status (status="active") -> search_talent

5. Pipeline Review

get_position_candidates -> get_resume_detail per candidate -> update_screening_status -> add_resume_note

6. Reschedule Interview

list_interviews (status="scheduled") -> reschedule_interview

Domain Knowledge

Screening pipeline:

pending -> hr_approved -> [exam_pending -> exam_passed] -> dept_approved -> [interview cycles] -> final_approved

Each stage: approve (advance) or reject (end). Exam phase is managed outside MCP tools. Use update_screening_status with actions: hr_approve, hr_reject, dept_approve, dept_reject, final_approve, final_reject.

Position lifecycle: pending -> active -> paused \x3C-> active -> closed

Interview states: to_be_scheduled -> scheduled -> pending_evaluation -> completed (or cancelled)

Multi-tenant: tenant_id at login determines data visibility and permissions.

Response Formatting

  • Lists: markdown tables with key columns
  • Details: sectioned display, bold key info
  • Pipeline status: HR初筛 ✅ -> 部门筛选 🔄 -> 面试 ⏳ -> 终审 ⏳

Error Handling & Stop Conditions

  • Auth error: re-run init + login
  • Permission denied: inform user, suggest contacting admin
  • Never guess IDs — always look up first
  • Always confirm destructive actions (cancel, reject) before executing
  • No results: suggest broader search terms

When NOT to Use

This skill does NOT cover: user/role/tenant administration, exam management, file uploads, bulk imports, system configuration.

Language

Backend data is in Chinese. Interact with user in Chinese. Enum values (status, action) are in English.

安全使用建议
This skill appears to be what it says: an MCP client for iHRFlow using curl+jq. Before installing: (1) Verify the IHRFLOW_MCP_URL points to your trusted MCP server (don't point it to an unknown host); (2) Be aware you must provide username/password (and optionally tenant_id/API key); these are stored in your OpenClaw configuration/environment — consider using the platform vault/secrets feature rather than plain environment variables; (3) The helper stores a session id under /tmp for the current user — on multi-user hosts review permissions and remove stale session files if needed; (4) Source/homepage is not provided in the skill metadata — if you don't already trust the provider, try to obtain the upstream repository or vendor contact before use. If you want higher assurance, ask the publisher for a verifiable source (GitHub repo or vendor site) and/or audit the MCP server endpoint and its required transport API key policy.
功能分析
Type: OpenClaw Skill Name: ihrflow-hr Version: 1.0.0 The ihrflow-hr skill bundle is a legitimate integration for the iHRFlow talent management platform, implementing a Model Context Protocol (MCP) client via a shell script (scripts/mcp-call.sh). The script uses standard tools like curl and jq to interact with a user-defined backend URL (IHRFLOW_MCP_URL) and handles authentication and tool execution as described in the comprehensive documentation (SKILL.md, README.md, and api-reference.md). No evidence of data exfiltration, malicious execution, or prompt injection was found; the requested shell and network permissions are appropriate for its stated purpose of communicating with an external HR API.
能力评估
✓ Purpose & Capability
Name/description (iHRFlow HR assistant) match the implemented behavior: the helper script talks to an MCP endpoint and exposes recruiting-related tools. Required binaries (curl, jq) and required env vars (MCP URL, username, password) are appropriate for an HTTP+JSON CLI client.
✓ Instruction Scope
SKILL.md instructions only direct the agent to run the included helper script (init/login/call/resource) and to call iHRFlow MCP tools and resources. The instructions do not ask the agent to read unrelated system files, exfiltrate arbitrary data, or call unexpected endpoints beyond the configured MCP URL. Network and shell permissions are declared and expected.
✓ Install Mechanism
No install spec; skill is instruction-only with an included shell helper script. No remote downloads or arbitrary install URLs. This is low-risk from an installer perspective.
ℹ Credentials
The skill requires IHRFLOW_MCP_URL, IHRFLOW_USERNAME, IHRFLOW_PASSWORD which are proportionate. Documentation and changelog also mention optional IHRFLOW_TENANT_ID and IHRFLOW_API_KEY (transport API key) even though only three env vars are declared as required — minor inconsistency but these optional vars are sensible. Operational note: credentials are expected to be provided via environment/config and the script will send X-API-Key and session headers if set; storing passwords in env and session IDs in files has usual risks.
ℹ Persistence & Privilege
The skill does not request always:true and does not modify other skills. It writes a session id to /tmp/ihrflow-mcp-session-${USER}, which is normal for a client but has typical risks: session token stored on disk, potential for race/permission issues in shared environments. No other elevated privileges requested.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install ihrflow-hr
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /ihrflow-hr 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
iHRFlow HR assistant: 20 MCP tools for recruiting, candidate search, interview scheduling, pipeline management, and recruitment statistics
元数据
Slug ihrflow-hr
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

iHRFlow HR Assistant 是什么？

iHRFlow HR assistant for recruiting. Use when searching candidates, managing positions, scheduling interviews, advancing pipeline, or viewing recruitment stats. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 299 次。

如何安装 iHRFlow HR Assistant？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ihrflow-hr」即可一键安装，无需额外配置。

iHRFlow HR Assistant 是免费的吗？

是的，iHRFlow HR Assistant 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

iHRFlow HR Assistant 支持哪些平台？

iHRFlow HR Assistant 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 iHRFlow HR Assistant？

由 MikeLing（@mikeling）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论