Pipeline

by agenticnotetaking

Pipeline is an Automation skill for Claude Code, published by agenticnotetaking in arscontexta.

3.5K stars219 forkson agenticnotetaking/arscontextaAdded 2026/08/16Repository updated 2026/02/24

View source on GitHub Download repo ZIP

claude-codeclaude-code-pluginknowledge-baseknowledge-managementmarkdownsecond-brain

Install in seconds

Install Pipeline

Copy Pipeline into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/agenticnotetaking/arscontexta/tree/main/skill-sources/pipeline ~/.claude/skills/pipeline

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/agenticnotetaking/arscontexta.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skill-sources/pipeline/SKILL.md in agenticnotetaking/arscontexta
Installs to: ~/.claude/skills/pipeline
Collection: One of 25 skills cataloged from this repository
Category: Automation — 1523 skills

What Pipeline does

Pipeline processes source files end-to-end: seeding, extracting claims, reflecting, reweaving, verifying, and archiving them into a knowledge base. Use it when you want to run the full processing workflow on a file or batch of files in one command.

Pipeline is cataloged under Automation on DirSkills. Pipeline comes from a repository tagged claude-code, claude-code-plugin, knowledge-base, knowledge-management and markdown.

Documentation

README

Excerpt

EXECUTE NOW

Target: $ARGUMENTS

Parse immediately:

Source file path: the file to process (required)
--handoff: output RALPH HANDOFF block at end (for chaining)
If target is empty: list files in {DOMAIN:inbox}/ and ask which to process

Step 0: Read Vocabulary

Read ops/derivation-manifest.md (or fall back to ops/derivation.md) for domain vocabulary mapping. All output must use domain-native terms. If neither file exists, use universal terms.

START NOW. Run the full pipeline.

Pipeline Overview

The pipeline chains four phases. Each phase uses skill invocation or /ralph for subagent-based processing. State lives in the queue file — the pipeline is stateless orchestration on top of stateful queue entries.

This is the opening of the README. Read the full README on GitHub.

Commands Pipeline provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/ralph
/seed
/reduce
/archive-batch
/pipeline

Frequently asked about Pipeline

What else does agenticnotetaking publish alongside Pipeline?
Pipeline is one of 25 skills that DirSkills catalogs from agenticnotetaking/arscontexta, the repository it ships in. Its siblings there include Add Domain, Ars Contexta Setup and Ars Contexta Tutorial. Each one is a separate skill with its own page in this directory, installs the same way Pipeline does, and is maintained by agenticnotetaking in that same repository. The rest of the collection is listed on the agenticnotetaking/arscontexta page.
How does Pipeline compare to other Automation skills?
Pipeline ranks #346 by stars among the 1523 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Pipeline against them. Open each page to compare what they document and how they install.