← Back to Skills Marketplace
HPD Pipeline
by
omermesebuken1
· GitHub ↗
· v0.1.0
· MIT-0
122
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install hpd-pipeline
Description
Use when the HPD lab needs a repeatable Planner -> Designer -> conditional Developer -> Tester flow for an approved idea, with Lobster-first and sequential f...
README (SKILL.md)
hpd-pipeline
Follow the stage contract in {baseDir}/references/project-pipeline.md.
Preferred mode
- If the
lobsterCLI is available onPATH, prefer a Lobster workflow. - If
lobsteris unavailable, run the same stages sequentially in one turn and marklobster_ready: false.
Required output sections
briefcost_estimatebomassembly_planrender_promptsoftware_specwhen neededtester_reportartifact_manifestcompletion_summary
Optional artifact fields
Use these when real outputs exist. If they do not exist, say so explicitly instead of implying they were produced.
render_imagecad_step_pathcad_stl_pathsassembly_doc_pathsource_code_pathfirmware_build_path
Rules
- Keep outputs Notion-first.
- Do not claim STEP/STL or validated firmware unless it was actually produced.
Usage Guidance
This skill appears to be a coherent project pipeline, but it relies on external CLIs and APIs (lobster, openclaw image generation, Gemini API) and asks outputs to be 'Notion-first' while declaring no credentials. Before installing: (1) confirm whether your agent environment already has Lobster, OpenClaw, Gemini, or Notion integrations and what credentials they expose; (2) decide whether you are comfortable the agent may call those services and push project artifacts to Notion; (3) if you want to restrict access, run the skill in a sandbox or remove/disable integrations you don't trust; (4) ask the skill author to declare required binaries and environment variables and to provide any fallback scripts (e.g., the 'Gemini API script') so you can review them. If you cannot verify those integrations, treat the skill as capable of sending project data to external services and proceed cautiously.
Capability Analysis
Type: OpenClaw Skill
Name: hpd-pipeline
Version: 0.1.0
The skill bundle defines a structured project development workflow (Planner, Designer, Developer, Tester) for hardware and software design. The instructions in SKILL.md and references/project-pipeline.md focus on generating reports, BOMs, and CAD files (OpenSCAD) while utilizing standard tool-use patterns like image generation. No indicators of malicious intent, data exfiltration, or unauthorized command execution were found.
Capability Assessment
Purpose & Capability
The name/description (HPD pipeline) align with the SKILL.md stage contract and required outputs. Expectation to prefer a 'lobster' CLI and to generate images/CAD/source fits the described pipeline. However, the skill references external tools and outputs (openclaw image generate, Gemini API, Notion-first) that are not declared in the skill's requirements.
Instruction Scope
The instructions tell the agent to run external commands and APIs (try lobster on PATH; run 'openclaw image generate'; fall back to a 'Gemini API script' if image generation fails) and to write OpenSCAD and other artifact files to the workspace. They also require publishing outputs Notion-first. Those actions involve external integrations and writing files, but the skill does not enumerate what credentials or endpoints will be used or provide the fallback scripts — giving the agent broad discretion to call environment-integrated services.
Install Mechanism
This is an instruction-only skill with no install spec and no code files. That minimizes code-install risk.
Credentials
No environment variables, credentials, or config paths are declared, yet the SKILL.md expects use of external services (Gemini API, Notion) and CLIs (lobster, openclaw). Those services typically require API keys/credentials; the absence of declared env vars is a mismatch. If the agent environment already has those integrations, the skill would use them implicitly — which could lead to unintended data sharing.
Persistence & Privilege
always is false and there is no code that requests persistent/system-wide configuration or modifies other skills. The skill writes artifacts to its workspace per the contract, which is normal for this type of workflow.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install hpd-pipeline - After installation, invoke the skill by name or use
/hpd-pipeline - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Initial publish
Metadata
Frequently Asked Questions
What is HPD Pipeline?
Use when the HPD lab needs a repeatable Planner -> Designer -> conditional Developer -> Tester flow for an approved idea, with Lobster-first and sequential f... It is an AI Agent Skill for Claude Code / OpenClaw, with 122 downloads so far.
How do I install HPD Pipeline?
Run "/install hpd-pipeline" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is HPD Pipeline free?
Yes, HPD Pipeline is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does HPD Pipeline support?
HPD Pipeline is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created HPD Pipeline?
It is built and maintained by omermesebuken1 (@omermesebuken1); the current version is v0.1.0.
More Skills