skills

skills is a command for Claude Code from bl1nk-bot/agent-library. It costs 8 tokens per session (453 once invoked), scanned A, original, CC0-1.0.

A command for searching Agent Skills, which are reusable task guides that extend an AI coding assistant. Results can be filtered by category or tag, then viewed or installed.

In plain words
What is it for?
Use it to find skills for jobs such as code review, testing, documentation, automation, API integration, or data analysis, and install selected skills in the workspace.
Why use it?
It avoids manually browsing for task guides and helps narrow results to a particular type of work.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the prompts.chat plugin — 2 skills, 2 commands, 2 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/bl1nk-bot/agent-library/skills
Clone the repo
git clone --depth 1 https://github.com/bl1nk-bot/agent-library

Made for: Claude Code.

Or install prompts.chat, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 2 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skills

README.md
[![agentmods](https://agentmods.dev/badge/commands/bl1nk-bot/agent-library/skills.svg)](https://agentmods.dev/commands/bl1nk-bot/agent-library/skills)
Your own site
<a href="https://agentmods.dev/commands/bl1nk-bot/agent-library/skills"><img src="https://agentmods.dev/badge/commands/bl1nk-bot/agent-library/skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00008 $0.00453
Opus 5 $0.00004 $0.00227
Sonnet 5 $0.00002 $0.00091
Haiku 4.5 $0.00001 $0.00045

Measured 6d ago against content hash 9f5fc1aa27d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/claude/prompts.chat/commands/skills.md · 76 lines

What it actually says

/prompts.chat:skills

Search for Agent Skills on prompts.chat to extend Claude's capabilities.

Usage

/prompts.chat:skills <query>
/prompts.chat:skills <query> --category coding
/prompts.chat:skills <query> --tag automation
  • query: Keywords to search for (required)
  • --category: Filter by category slug
  • --tag: Filter by tag slug

Examples

/prompts.chat:skills code review
/prompts.chat:skills documentation --category coding
/prompts.chat:skills testing --tag automation
/prompts.chat:skills api integration
/prompts.chat:skills data analysis

How It Works

  1. Calls search_skills with your query and optional filters
  2. Returns matching skills with title, description, author, files, and tags
  3. Each result includes a link to view the skill on prompts.chat

Getting a Specific Skill

After finding a skill you want, use its ID to get all files:

/prompts.chat:skills get <skill-id>

This retrieves the skill with all its files (SKILL.md, reference docs, scripts, etc.)

Installing a Skill

To download and install a skill to your workspace:

/prompts.chat:skills install <skill-id>

This saves the skill files to .claude/prompts.chat:skills/{slug}/ structure.

Creating a Skill

To create a new skill on prompts.chat (requires API key):

/prompts.chat:skills create "My Skill Title" --description "What this skill does"

You'll be prompted to provide the SKILL.md content and any additional files.

Skill Structure

Skills can contain multiple files:

  • SKILL.md (required) - Main instructions with frontmatter
  • Reference docs - Additional documentation
  • Scripts - Helper scripts (Python, shell, etc.)
  • Config files - JSON, YAML configurations
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 76 lines · 8 tokens per session scan A 9f5fc1aa27d7

Subscribe to this mod's changes

skills is a command published in the GitHub repository bl1nk-bot/agent-library (2 stars, last pushed yesterday), licensed CC0-1.0. It adds 8 tokens to every session and 453 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.