AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Clip Skills

skill-nweii-agent-stuff-clip-skills · by nweii

Save `bunx skills` terminal output (a manifest from `skills add/use <repo> -l`) as a Repos note in the Brain vault under 03-Records/Snippets/Repos/. Use when the user pastes a skills listing and wants it captured. Triggers: '/clip-skills', 'save these skills', 'make a note for this skill repo'.

No reviews yet
0 installs
27 views
0.0% view→install

Install

$ agentstack add skill-nweii-agent-stuff-clip-skills

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-nweii-agent-stuff-clip-skills)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Clip Skills? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Clip skills

Turn a bunx skills manifest (run in the terminal, not the browser) into one note in 03-Records/Snippets/Repos/. This is the CLI-entry twin of the Obsidian Web Clipper "Agent skills" template, which handles the same note when clipping a GitHub/skills.sh page in the browser. Match that template's shape so notes from either path look identical.

Defer first

Vault layout, metadata semantics, and tool-choice rules live in the vault's AGENTS.md / CLAUDE.md. Read those if unsure about a field or which write tool to use. This skill only adds the procedure for this one note type.

Input

The user has run one of these and pasted the output:

bunx skills add  -l   # lists a collection's skills
bunx skills use  --skill 

Derive ` (or the bare URL slug, e.g. https://docs.stripe.com) from what they ran. If the listing is missing or partial, ask them to re-run with -l`.

Note shape

Path: 03-Records/Snippets/Repos/

Filename:

  • Collection of skills → skills - (e.g. Payments skills - stripe, Design engineering skills - Emil Kowalski)
  • Single skill → skill -

No quotes in the filename.

Frontmatter:

aliases:        # 1-2 retrieval-friendly alt titles, sentence case
categories:     # [[Snippets]] and [[Web]] always; add [[Clippings]] ONLY if the source is a clipped web page (e.g. a docs site), not a bare GitHub repo
icon: "LiSparkles"
description:    # what this offers in 1-2 plain sentences — collection focus/breadth, or the single skill's own description lightly compressed
url:           # the source page/repo URL, query string stripped
author:        # repo owner or credited person as a [[wikilink]]; prefer full name over handle
last:          # today's date
tags:          # clippings/skills, plus 1-2 broad lowercase topical tags (hyphens, no spaces)

Body — two sections:

## Use

## Skills

## Use codeblocks

Use `shell fences, one command per block, each preceded by its label line.

Collection (three blocks):

  • Browse the collection:bunx skills add -l
  • Try one without installing:bunx skills use --skill
  • Install one:bunx skills add --skill -a claude-code zed -g -y

Single skill (two blocks):

  • Try without installing:bunx skills use --skill
  • Install:bunx skills add --skill -a claude-code zed -g -y

Leave `` as a literal placeholder for a collection; for a single skill use its actual skill name.

## Skills bullets

One bullet per skill: **skill-name**: . Compress the manifest's full description to a single sentence that keeps the substance — don't paste the whole multi-sentence blurb, don't truncate to a fragment. Include every skill the listing names, in listing order.

When the -l output reports files for a skill, add one nested bullet under it:

- **skill-name**: one-line purpose.
    - Files: `SKILL.md`, `references/a.md`, `b.md`, ...

Omit the Files line for skills that reported none. Keep the source's own groupings as plain subheadings only if it has them.

Write

Use the vault's preferred write path (Obsidian CLI when available, else the environment's equivalent — see CLAUDE.md). Don't leave raw Templater ` fields. After writing, give the note title and its obsidian://open?vault=Brain&file=...` URI.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.