← 返回 Skills 市场

HH OpenClaw Agent

Name: HH OpenClaw Agent
Author: zack-dev-cm

作者 Zakhar Pashkin · GitHub ↗ · v1.0.6 · MIT-0

cross-platform ✓ 安全检测通过

159

总下载

当前安装

版本数

在 OpenClaw 中安装

/install hh-openclaw-agent

功能描述

HH OpenClaw Agent is a public ClawHub hh.ru application skill. Use it when the user says "hh openclaw agent", "hh job apply automation", "hh.ru browser appli...

使用说明 (SKILL.md)

HH OpenClaw Agent

Search intent: hh openclaw agent, hh.ru apply, job application browser automation, career submission bundle

Goal

Turn one hh.ru application run into a reusable submission bundle:

one machine-readable application packet
one ordered execution log with evidence
one structural bundle check
one shareable markdown report

This skill is for reviewed hh.ru browser execution through OpenClaw. It assumes the browser profile is already authenticated.

Use This Skill When

the user wants to prepare and submit an hh.ru application through OpenClaw
a vacancy-specific packet should be reviewed before the live browser write
the same hh.ru response flow needs an auditable run log instead of chat memory
a blocked or failed submission needs screenshots, exact steps, and a handoff report
the operator wants one record of approved content and live browser outcome

Quick Start

Initialize the application packet.
- Use python3 {baseDir}/scripts/init_hh_application_packet.py --out \x3Cjson> --packet-id \x3Cid> --vacancy-id \x3Cid> --vacancy-title \x3Ctitle> --company-name \x3Ccompany> --resume-title \x3Cresume> --vacancy-url \x3Curl> --apply-url \x3Curl> --cover-letter \x3Ctext>.
- Add --browser-profile, --review-status, --reviewer, and repeatable --blocked-action fields when needed.
Execute the browser flow through OpenClaw.
- Open the apply URL in a logged-in profile.
- Record each meaningful browser action with append_hh_execution_step.py.
- Capture screenshots and outcome notes as the run progresses.
Keep operator-owned auth and approval gates explicit.
- If hh.ru shows login, CAPTCHA, 2FA, or another auth challenge, stop and let the operator complete it in the same browser profile.
- Do not live-send a packet that is still pending or rejected.
Check the bundle before sharing or counting it as complete.
- Use python3 {baseDir}/scripts/check_hh_submission_bundle.py --manifest \x3Cjson> --repo-root \x3Crepo> --out \x3Cjson>.
- Fix approval-gate issues, missing screenshots, or incomplete failed-step notes before final handoff.
Render the report.
- Use python3 {baseDir}/scripts/render_hh_submission_report.py --manifest \x3Cjson> --out \x3Cmd>.
- The default report redacts the cover letter body, keeps only public https://*.hh.ru/... URLs, and redacts private artifact paths.
- Add --include-sensitive only when you intentionally need a full-content export.
- Share the report instead of loose screenshots and manual notes.

Operating Rules

Packet rules

Keep one packet per vacancy response flow.
The cover letter should stay vacancy-specific.
Record vacancy URL, apply URL, resume title, and approval state before opening the live form.

Execution rules

Use a logged-in OpenClaw browser profile for the live hh.ru session.
Record expected result and actual result for every meaningful step.
Capture a screenshot for failed or blocked steps and for the final submitted state when possible.
Keep artifact paths relative so the bundle can move between machines.

Safety rules

Do not claim undocumented hh.ru write APIs.
Do not store cookies, secrets, or tokens in notes or artifacts.
Do not send a live application unless the packet review state is approved.
Treat login, CAPTCHA, passkey, and 2FA as operator-owned interruptions, not background automation.

Bundled Scripts

scripts/init_hh_application_packet.py
- Create a machine-readable application packet for one hh.ru response flow.
scripts/append_hh_execution_step.py
- Append one evidence-backed browser execution step to the packet.
scripts/check_hh_submission_bundle.py
- Validate approval state, execution evidence, and bundle safety before handoff.
scripts/render_hh_submission_report.py
- Render a concise markdown report from the packet and execution log.

安全使用建议

This skill appears to do what it says: manage local hh.ru application packets and render audited reports. Before installing/using it: (1) review the included scripts yourself (they operate on local files and are easy to inspect); (2) ensure you run them in an environment where artifact paths and screenshots live under the intended repo_root so the bundle checks are meaningful; (3) do not pass secrets, cookies, or absolute file paths into the packet (the README already warns against this); and (4) be cautious when using the --include-sensitive flag since it will un-redact cover letters and apply/outcome URLs. If you want extra assurance, confirm the GitHub homepage and repository commit history match the published package.

功能分析

Type: OpenClaw Skill Name: hh-openclaw-agent Version: 1.0.6 The skill bundle provides a structured and auditable workflow for automating job applications on hh.ru. The included Python scripts (init_hh_application_packet.py, append_hh_execution_step.py, etc.) are limited to local JSON manifest manipulation and report generation using standard libraries. The bundle includes several security-conscious features, such as mandatory human-in-the-loop approval gates, redaction of private file paths and non-target URLs in reports (render_hh_submission_report.py), and validation checks to ensure artifacts use relative rather than absolute paths (check_hh_submission_bundle.py).

能力评估

✓ Purpose & Capability

Name/description match the included behavior: scripts create a packet, append execution steps, validate the bundle, and render a report. The required binaries (python/python3) are appropriate and no unrelated credentials or tools are requested.

✓ Instruction Scope

SKILL.md confines actions to creating and managing local artifacts and instructs the operator to use an already-authenticated browser profile for live actions. The instructions explicitly forbid storing cookies/secrets in artifacts and treat login/2FA as operator-owned interruptions. The bundled scripts operate only on local files and do not make network calls.

✓ Install Mechanism

No install spec; the skill is instruction-only with included Python scripts. Nothing is downloaded or extracted from external URLs, so there is no install-time code injection risk.

✓ Credentials

The skill requests no environment variables or credentials. The scripts only read/write local JSON/markdown files and expect a repo_root for artifact checks; this is proportional to the described functionality.

✓ Persistence & Privilege

always is false and the skill does not request persistent system-wide changes or modify other skills. It does not attempt to enable itself or store tokens; its scope is limited to local file operations.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install hh-openclaw-agent
安装完成后，直接呼叫该 Skill 的名称或使用 /hh-openclaw-agent 触发
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

v1.0.6

Refresh discovery metadata and skill version for ClawHub.

v1.0.5

Align repo and packaged skill licenses to MIT-0.

v1.0.4

Declare MIT license metadata to match the repo license.

v1.0.3

Hardened shareable report redaction, added CI, and clarified public docs.

v1.0.2

Security and privacy hardening.

v1.0.1

Security and public-surface hardening.

v1.0.0

Initial public release.

元数据

Slug hh-openclaw-agent

版本 1.0.6

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 7

常见问题