Skill

downstream

Assess downstream effects of editing a chapter. Use when the user has edited a chapter and wants to know what breaks in later chapters.

Install

npx claudepluginhub jdpedrie/critic --plugin critic

Tool Access

This skill uses the workspace's default tool permissions.

Preview

The vault path for all tool calls is: ${user_config.vault_path}

SKILL.md

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

139.2k

mcp-builder

9 files

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

anthropics-skills-13

124.2k

canvas-design

20 files

Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.

anthropics-skills-13

124.2k

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitMar 28, 2026

Actions

View Source View Plugin View on GitHub View README

Downstream Assessment

The vault path for all tool calls is: ${user_config.vault_path}

Assess what breaks in later chapters after editing a chapter.

Arguments

$ARGUMENTS should be a chapter name (e.g., "chapter-03").

Workflow

Call the assess-downstream tool with the vault path (current working directory) and chapter name.

Present results as readable text:

Summary: The overall assessment.

Downstream Issues (grouped by severity): For each issue:

Which chapter is affected
What breaks and why (referencing the edit that caused it)
Quote from the affected chapter
Suggested fix

Safe Chapters: List chapters that appear unaffected.

After presenting, offer:

"Want to look at any specific affected chapter?"
"Should I run a full review on any of the affected chapters?"

Important Notes

This tool reads from the edited chapter through the END of the manuscript. For long manuscripts this is a large context call.

Present issues in severity order: critical first.

Quote the downstream evidence so the user can verify.

Downstream Assessment

The vault path for all tool calls is: ${user_config.vault_path}

Assess what breaks in later chapters after editing a chapter.

Arguments

$ARGUMENTS should be a chapter name (e.g., "chapter-03").

Workflow

Call the assess-downstream tool with the vault path (current working directory) and chapter name.
Present results as readable text:

Summary: The overall assessment.

Downstream Issues (grouped by severity): For each issue:
- Which chapter is affected
- What breaks and why (referencing the edit that caused it)
- Quote from the affected chapter
- Suggested fix
Safe Chapters: List chapters that appear unaffected.
After presenting, offer:
- "Want to look at any specific affected chapter?"
- "Should I run a full review on any of the affected chapters?"

Important Notes

This tool reads from the edited chapter through the END of the manuscript. For long manuscripts this is a large context call.
Present issues in severity order: critical first.
Quote the downstream evidence so the user can verify.