Help us improve
Share bugs, ideas, or general feedback.
From aria-knowledge
Saves a URL or text snippet to the knowledge intake clippings folder for later review and promotion. Quick capture without leaving the session; items are audited on next /audit-knowledge run.
npx claudepluginhub mikeprasad/aria-knowledge --plugin aria-knowledgeHow this skill is triggered — by the user, by Claude, or both
Slash command
/aria-knowledge:clip <url or text> [tags]<url or text> [tags]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Save a URL or text snippet to `intake/clippings/` for later review and promotion.
Ingests sources like URLs, YouTube videos, GitHub repos/PRs/issues, PDFs, or text into a vault, creating SHA-256 hashed raw files and Markdown summaries with key claims.
Bulk imports knowledge from files, directories, or URLs into structured backlogs, or captures a single document with a 5-section template (claims, worth-keeping, contested, action, reaction).
Share bugs, ideas, or general feedback.
Save a URL or text snippet to intake/clippings/ for later review and promotion.
Canonical resolution: This is the Claude Code variant. When both plugin-claude-code and plugin-claude-cowork are loaded in the same session (most common in Claude Desktop), bare /clip resolves to this skill — aria-knowledge (Code) is the canonical owner of all 24 dual-port skills per ADR-094 §Part 1. The Cowork variant is namespaced-only: /aria-cowork:clip.
Before Step 0: Check that the Bash tool is available in this session. If Bash is NOT available (you are running in Claude Cowork or another non-Code runtime), surface the following notification and wait for explicit user confirmation:
⚠️ Runtime mismatch — you invoked aria-knowledge's
/clipfrom a non-Code runtime.Behavior is largely the same in both runtimes; for the Cowork-native variant (writes to
intake/clippings/in the attached knowledge folder via persistent-grant), use/aria-cowork:clip.Use
/aria-cowork:clipinstead? (y/n)
Wait for an explicit reply:
y / yes — Use the Skill tool to invoke aria-cowork:clip with the same arguments the user provided to this invocation. Do not proceed with this skill's steps; the cowork variant takes over and runs to completion. This is the default-yes path — auto-redirect is the helpful action.n / no — Proceed with this (aria-knowledge) variant anyway despite the runtime mismatch. The user has explicitly opted in.This gate applies even when mode = auto per ADR-094 §Part 3. Auto mode's "implicit-yes on all gates" rule is suspended for the runtime-mismatch check — auto trusts that the user invoked the correct variant, and this gate enforces that precondition. All other auto-mode gates remain bypassed. The friction cost is now low: on y, the auto-redirect runs the correct variant with the original args.
If Bash is available, proceed to Step 0.
Read ~/.claude/aria-knowledge.local.md and extract knowledge_folder. If the file doesn't exist, stop: "aria-knowledge is not configured. Run /setup to get started."
Verify {knowledge_folder}/intake/clippings/ exists. If not, stop: "Clippings directory not found. Run /setup to repair the knowledge folder structure."
The user provides one of:
http:// or https://If no input is provided, ask: "What would you like to clip? Paste a URL or text snippet."
If the input is a URL:
If WebFetch fails, save the URL itself as the content with a note that the page could not be fetched.
Create a kebab-case slug from:
Filename format: {YYYY-MM-DD}-{slug}.md
Check if the file already exists in intake/clippings/. If so, append a numeric suffix: {date}-{slug}-2.md.
Write to {knowledge_folder}/intake/clippings/{filename}:
---
source: [URL or "manual"]
date: YYYY-MM-DD
tags: [user-provided tags, or auto-detected from content, or empty array]
---
# [Title or first line of text]
[Content — summary for URLs, full text for snippets]
Tag detection: If the user didn't provide tags, check if any words in the title or content match known tags from {knowledge_folder}/index.md (if it exists). Only suggest tags with high confidence — don't guess.
Output:
Clipped to intake/clippings/{filename}
Tags: [tags or "none"]
Will be reviewed at next /audit-knowledge run.