← 返回 Skills 市场
Skill Engineer
作者
Chunhua Liao
· GitHub ↗
· v3.2.0
907
总下载
1
收藏
4
当前安装
4
版本数
在 OpenClaw 中安装
/install skill-engineer
功能描述
Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement. Orchestrates Designer, Reviewer, and Tester suba...
安全使用建议
This skill mostly does what it says, but it asks agents to: (1) query your vector memory (session history/notes), (2) read OpenClaw config and skill files in your home/workspace, and (3) regenerate README and push changes to GitHub. Before installing or enabling autonomous use:
- Review and run the included scripts locally yourself (check-completeness.sh, validate-scorecard.sh, validate-trigger.sh, quality-score.py) to see what they do and to confirm there are no unexpected network calls.
- Restrict or disable autonomous push-to-GitHub behavior: require manual approval for any git commits/pushes or run the README-sync step locally.
- Be deliberate about enabling vector memory access (memory_search) because it exposes session history/notes; if that data is sensitive, keep memory.enabled disabled or limit the skill's permissions.
- Ensure the dependent deepwiki skill is from a trusted source before using it.
If you want higher assurance, run the skill in a sandboxed repo/environment first and require human approval before giving it repository write/push rights or access to session memory.
功能分析
Type: OpenClaw Skill
Name: skill-engineer
Version: 3.2.0
The skill-engineer bundle is a highly structured framework for the iterative development and quality assurance of OpenClaw agent skills. It implements a sophisticated multi-agent orchestration pattern (Designer, Reviewer, Tester) and includes several utility scripts (e.g., quality-score.py, validate-trigger.sh) to provide deterministic validation of skill artifacts. The bundle is notable for its strong emphasis on security and best practices, featuring explicit OPSEC rubrics in reviewer-rubric.md and designer-guide.md designed to prevent the accidental inclusion of secrets or internal organizational data. All high-risk capabilities, such as subagent spawning and file system manipulation, are strictly aligned with the stated purpose of skill engineering and are governed by rigorous quality gates.
能力评估
Purpose & Capability
The name/description (design, review, test skills) align with the included materials: detailed SKILL.md, reviewer/tester/designer guides, and deterministic validation scripts. The declared non-code registry metadata (no env vars/binaries) matches the instruction-only install model; mandatory dependencies listed in SKILL.md (deepwiki skill, vector memory DB) are coherent for an orchestrator that needs current API behavior and session history.
Instruction Scope
SKILL.md instructs querying the agent's vector memory (memory_search), inspecting local OpenClaw files/paths (e.g., ~/.openclaw/skills/deepwiki/ and openclaw.json) and contains a README sync / push-to-GitHub step. Those actions reach beyond the skill's own files and ask for access to session history, local config and repository operations. While plausible for a skill-engineer, they are significant side-effects and broaden the trust surface.
Install Mechanism
No install spec or remote downloads; this is instruction-only with packaged reference docs and local validation scripts. That's low-install risk — nothing is fetched from external URLs or extracted. The provided scripts are local deterministic tools (bash/python) that operate on repository files.
Credentials
Registry metadata requests no environment variables or credentials. However, SKILL.md requires the vector memory feature and the deepwiki skill and tells the agent to inspect openclaw.json and user skill directories. This does not request new secrets, but it implies access to potentially sensitive session history and local configuration; that access is plausible for the role but should be intentionally granted and audited.
Persistence & Privilege
always:false and normal autonomous invocation are set (not elevated). But the workflow explicitly includes a README sync that regenerates README from the implementation and a 'Push to GitHub' step. That implies write/commit and remote push privileges over repositories. The package itself doesn't include automated push code, but the documented workflow expects the orchestrator to perform repo-side changes — a capability that increases impact and should require explicit authorization and careful scoping.
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 skill-engineer - 安装完成后，直接呼叫该 Skill 的名称或使用
/skill-engineer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
v3.2.0
v3.2.0: Skill taxonomy (Capability Uplift vs Encoded Preference), mandatory dependencies (deepwiki + vector memory), new scripts (quality-score.py, validate-trigger.sh), Configuration section
v3.1.0
v3.1.0: Mandatory skill naming step in Designer workflow — present 3-5 candidates to user before writing artifacts. Naming criteria table, step-by-step process, worked example. Removed redundant Separation of Concerns section.
v3.0.1
Version 3.0.1
- No file changes detected for this release.
- No modifications to SKILL.md or other artifacts.
- Functionality and documentation remain unchanged from version 3.0.0.
v3.0.0
Skill-engineer v3.0.0 introduces a comprehensive multi-agent framework for quality-gated skill development, leveraging separation of concerns and iterative refinement.
- Adds a three-role architecture (Designer, Reviewer, Tester) for designing, reviewing, and validating agent skills.
- Clearly defines scope, boundaries, and success criteria for skill lifecycle management.
- Details orchestrator responsibilities and strictly enforces that only subagents create or evaluate skill content.
- Sets a maximum of three development iterations, with explicit failure and user notification protocols if quality gates are not met.
- Provides example requirements gathering templates and outlines both recommended (role-based) and advanced (parallel session) subagent spawning mechanisms.
- Excludes release, deployment, tracking, and infrastructure management from this skill’s responsibilities.
元数据
常见问题
Skill Engineer 是什么？
Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement. Orchestrates Designer, Reviewer, and Tester suba... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 907 次。
如何安装 Skill Engineer？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install skill-engineer」即可一键安装，无需额外配置。
Skill Engineer 是免费的吗？
是的，Skill Engineer 完全免费（开源免费），可自由下载、安装和使用。
Skill Engineer 支持哪些平台？
Skill Engineer 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 Skill Engineer？
由 Chunhua Liao（@chunhualiao）开发并维护，当前版本 v3.2.0。
推荐 Skills