← 返回 Skills 市场
303
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install skills-orchestrator
功能描述
Orchestrate growth loops across the skill portfolio by connecting usage, feedback, improvement, and adoption into self-reinforcing cycles. Use when designing...
安全使用建议
What to consider before installing or running this skill:
- Functionality: The files and scripts implement growth-loop design/analysis and generate simulated metrics; that matches the skill description.
- Operational dependencies: The scripts use utilities not declared in the metadata (shuf, bc, and optionally jq). Ensure these are available or modify the scripts before running.
- Disk writes & execution: Scripts create files under the skill's data/ folder. test.sh will mark scripts executable and run them; run tests in a sandbox or review/modify test.sh first if you don't want files created or permissions changed.
- Privacy/publishing recommendation: The 'content' design templates recommend making outputs public by default. That is a policy choice and could leak user-generated content if you plug in real data. By default the tool simulates data, but do NOT run these scripts on real user data unless you control where outputs are published and have consent.
- No credentials requested: The skill does not request keys or system credentials — good. Still inspect any real data you feed into it since the scripts will write and (per templates) may suggest public sharing.
- Best practice: Review the scripts locally, run test.sh only in an isolated environment, or remove/adjust the public-by-default lines before using with real user data. If you want to use live analytics, prefer to sanitize or supply only aggregated/simulated inputs.
Confidence note: Medium — the package is straightforward and mostly coherent, but the undeclared CLI dependencies and the public-by-default recommendation introduce practical and privacy concerns that prevented a 'benign' rating.
功能分析
Type: OpenClaw Skill
Name: skills-orchestrator
Version: 1.0.1
The skills-orchestrator bundle is a template-based tool for designing and simulating growth strategies. The included shell scripts (design-loop.sh, analyze-loops.sh, track-metrics.sh) are simple generators that produce markdown reports and JSON metrics using hardcoded templates and random number generation (shuf). There is no evidence of network activity, sensitive data access, or malicious prompt injection; the skill explicitly states it uses simulated data for prototyping purposes.
能力评估
Purpose & Capability
Name/description match the included scripts and data: the repo provides design, analysis, and metrics-simulation scripts and markdown/templates that implement growth-loop orchestration. This is coherent with the stated purpose. However the skill metadata declares no required binaries while the scripts rely on several command-line utilities (shuf, bc, jq optionally), which is an operational mismatch worth noting.
Instruction Scope
SKILL.md repeatedly emphasizes simulated outputs and says it does not ingest live user analytics unless you provide data, which is good. But some design templates (content loop) recommend 'Default: Public (opt-out)' for outputs — an instruction that has privacy and data-publishing implications if followed. The scripts themselves write files under the skill's data directory and test.sh will make scripts executable and run them; none of the scripts read system secrets or network endpoints, but the public-by-default recommendation is scope-creep relative to the earlier privacy note and should be considered before using on real user data.
Install Mechanism
There is no install spec (instruction-only), so nothing is downloaded or installed automatically — lowest installation risk. But the package includes executable scripts that will be written to disk when the skill is installed, and test.sh will change script permissions if run. That disk-write/execution behavior is expected for an instruction+script bundle but worth noting.
Credentials
The skill declares no required env vars or credentials (appropriate for a design/simulation tool). It does accept an optional GROWTH_DATA_DIR env var to control where data is stored. However, the scripts depend on command-line utilities (shuf, bc, jq) that are not declared in the metadata — an omission that can cause runtime surprises. No secrets/credentials are requested or used.
Persistence & Privilege
always is false and the skill does not request permanent platform-level privileges. The scripts write reports under the skill's data directory and may change script executability when you run test.sh, but they do not modify other skills or system config. Autonomous invocation is allowed by default (normal) but not combined with broad access here.
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 skills-orchestrator - 安装完成后，直接呼叫该 Skill 的名称或使用
/skills-orchestrator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
v1.0.1
Fix SKILL.md: remove non-existent scripts, clarify simulated data only
v1.0.0
Rename from growth-loop-orchestrator to skills-orchestrator.
元数据
常见问题
Skills Orchestrator 是什么？
Orchestrate growth loops across the skill portfolio by connecting usage, feedback, improvement, and adoption into self-reinforcing cycles. Use when designing... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 303 次。
如何安装 Skills Orchestrator？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install skills-orchestrator」即可一键安装，无需额外配置。
Skills Orchestrator 是免费的吗？
是的，Skills Orchestrator 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Skills Orchestrator 支持哪些平台？
Skills Orchestrator 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 Skills Orchestrator？
由 haidong（@harrylabsj）开发并维护，当前版本 v1.0.1。
推荐 Skills