new-skills

new-skills is a skill for Claude Code, Codex from Unique-Divine/jiyuu. It costs 111 tokens per session (1,408 once invoked), scanned A, original, MIT.

A guide for creating, testing, and improving coding-agent skills. A skill is a reusable set of instructions that changes how an agent handles a particular kind of task.

In plain words
What is it for?
Use it to create a skill from scratch, revise an existing one, write realistic test prompts, review results, and refine the instructions based on those tests.
Why use it?
It provides a repeatable way to turn an idea into a usable skill and check whether the skill triggers and behaves correctly. This helps expose unclear instructions before relying on the skill in real work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/realu/ki/boku/jiyuu/ai-skills/<name>.

Good fit Use it to create a skill from scratch, revise an existing one, write realistic test prompts, review results, and refine the instructions based on those tests.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

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 new-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/unique-divine/jiyuu/new-skills/github.svg)](https://agentmods.dev/skills/unique-divine/jiyuu/new-skills)
Your own site
<a href="https://agentmods.dev/skills/unique-divine/jiyuu/new-skills"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/new-skills/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for new-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/unique-divine/jiyuu/new-skills"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/new-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,408 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00111 $0.01408
Opus 5 $0.00056 $0.00704
Sonnet 5 $0.00022 $0.00282
Haiku 4.5 $0.00011 $0.00141

Measured 3d ago against content hash 7dd696d6463f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

new-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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/quick_validate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

ai-skills/new-skills/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New skills

Create and revise agent skills as concise operational references. Start from the user's actual workflow, preserve useful existing material, and validate the result without introducing an evaluation process the user did not request.

Understand the intended skill

Use the conversation and existing files to establish:

  1. What work the skill should enable.
  2. Which requests should and should not trigger it.
  3. What tools, inputs, outputs, and repository conventions it depends on.
  4. Whether it is public or private.

Inspect relevant skills and source documentation before asking questions that the environment can answer. Ask the user only about unresolved intent or tradeoffs that materially change the skill.

When revising an existing skill, read its complete SKILL.md and each bundled resource needed for the requested change. Preserve its directory name and frontmatter field name unless the user explicitly requests a rename.

Choose the canonical location

Repository Unique-Divine/jiyuu is the public skill distribution location. Write public skills here:

/home/realu/ki/boku/jiyuu/ai-skills/<name>

A public skill stays in jiyuu/ai-skills even when its CLI or library lives in a jiyuu package. Do not create jiyuu/<package>/ai-skills/<name>. Example: command gh-rev lives in jiyuu/gh-rev; agent skill gh-rev lives in jiyuu/ai-skills/gh-rev.

Classify ownership from the resolved path, not from the runtime view. Directories ~/.agents/skills and ~/.cursor/skills both link to boku/priv-skills, which is the flat union. Public skills appear there as symlinks into jiyuu/ai-skills. Editing through the union still writes the jiyuu file. A union or $HOME skill path is not proof that the skill is private.

  • Resolved under jiyuu/ai-skills → public. Omit metadata.private.
  • Real directory under boku/priv-skills → private. Require:
metadata:
  private: true

Use a private skill for personal data, private operations, credentials-adjacent workflows, or instructions that should not be published. Do not set metadata.private to false on a public skill, and do not replace a public union symlink with a real directory in priv-skills.

Read the full file on GitHub · 162 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago Changed · -211 lines · +60 tokens per session scan C → A 7dd696d6463f
  2. 11d ago First seen · 373 lines · 51 tokens per session scan C b03efafe8d9f

Subscribe to this mod's changes

new-skills is a skill published in the GitHub repository Unique-Divine/jiyuu (6 stars, last pushed 4d ago), licensed MIT. It adds 111 tokens to every session and 1,408 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

use-modern-go

Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.

JetBrains/go-modern-guidelines · 32 tokens

migrate-goldmark-extension-v1-to-v2

Migrate goldmark extension from goldmark v1 to v2.

yuin/goldmark · 26 tokens

readme-generate

A tool that analyzes source code to generate English and Chinese README files and related project documentation.

agenvoy/Agenvoy · 67 tokens

gograph

Go repository intelligence for Claude Code. Use when reading, navigating, editing, reviewing, or refactoring a Go codebase. Exposes 64 query, analysis, and workflow capabilities through the local gograph MCP server, including bounded first-call exploration, AST-aware call graphs, blast-radius analysis, impact, and…

ozgurcd/gograph · 69 tokens

search-suitable-public-api

Search the curated Agenvoy public API list for an API that fits the current user need or skill context, then chain into the api-tool-add skill to register it under /.config/agenvoy/tools/api/. Triggers when the agent lacks a tool for a data lookup (weather, currency, geocoding, dictionary, etc.), when the user says…

agenvoy/Agenvoy · 131 tokens

bubbletea-testing

Use this skill whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go. Triggers include any mention of testing Bubble Tea models, teatest, golden file testing for TUIs, testing tea.Cmd or tea.Msg, snapshot testing terminal output, or writing tests for any Go CLI/TUI that uses the Elm…

dimetron/pi-go · 139 tokens