Pipeline Init — Data skill for Claude Code
Initialize a project for the agentic pipeline.
How to install Pipeline Init
Installs to ~/.claude/skills/scottconverse-agent-pipeline-codex-pipeline-init/SKILL.md
mkdir -p ~/.claude/skills/scottconverse-agent-pipeline-codex-pipeline-init && curl -fsSL https://raw.githubusercontent.com/scottconverse/agent-pipeline-codex/HEAD/commands/pipeline-init.md -o ~/.claude/skills/scottconverse-agent-pipeline-codex-pipeline-init/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Pipeline Init does
description: Initialize a project for the agentic pipeline. Onboards new projects from a PRD, an existing repo URL, or a description paragraph. argument-hint: (none - interactive)
pipeline-init - onboard a project for agentic pipeline runs
You are onboarding a project for use with the agentic pipeline plugin. The user has one of three things and you need to figure out which, then act on it. **You do not skip the orientation step. You do not silently scaffold based on assumptions.**
Alternatives in Data
- Portaljs Add Dataset — Add a dataset (CSV, TSV, JSON, or GeoJSON) to an existing PortalJS portal 2.3k ★
- Figma UI MCP — AI can draw UI directly on the Figma canvas via JavaScript, and read existing designs back as structured data 232 ★
- Generate More Training Data — This command analyzes patterns in existing data files (CSV, JSONL) and generates additional synthetic training 201 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
New Run
Initialize a new pipeline run (creates manifest and scope-lock skeletons). Run pipeline-init first if the proj
Rlm Init
Initialize the RLM database for storing buffers and state
Init Gitlfs
Initialize Git LFS in the current oryxflow project - check the binary is installed and hooked into git, ensure
PRD Generation
Stage 5: PRD Generation (Non-Interactive Pipeline Mode)
Athena
Run as Athena (PM specialist for PRD creation) inline in the main session — pipeline Stage 1
Hera
Run as Hera (PRD alignment verifier — confirms the implementation covers all acceptance criteria) inline in th
Related Agents
Repo Intel Summarizer
Produce a 3-depth narrative description of a repository (1-line, 1-paragraph, 1-page) for AI agents and humans
Initialize Engagement At The Start
findings.sh init " " --client " " --type " " --scope " " findings.sh stats bash db/handoff.sh handoff_report.m
Sdd Init.Agent
Initialize SDD project context, OpenSpec persistence, testing capabilities, and skill registry.