What is applying-skill-best-practices?

A set of standards for creating and maintaining Agent Skills, which are reusable instructions that guide a coding agent through a particular job. It covers scope, descriptions, model settings, and test cases.

Use it when creating, editing, reviewing, or testing a skill so its purpose and expected results are clear.

It helps avoid skills that overlap, trigger at the wrong time, contain unnecessary instructions, or have not been tested against real examples.

applying-skill-best-practices — Skill for Claude Code by jamesgray-ai

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.

Any agent

npx skills add jamesgray-ai/handsonai-plugins --skill applying-skill-best-practices

Clone the repo

git clone --depth 1 https://github.com/jamesgray-ai/handsonai-plugins

Made for: Claude Code.

Or install handsonai, the plugin that ships this one along with the rest of its 16 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/applying-skill-best-practices/github.svg)](https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/applying-skill-best-practices)

Your own site

<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/applying-skill-best-practices"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/applying-skill-best-practices/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/applying-skill-best-practices"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/applying-skill-best-practices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,936 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.

Model	Per session	Once invoked
Fable 5.1	$0.00166	$0.01936
Opus 5.5	$0.00066	$0.00774
Sonnet 5.5	$0.00033	$0.00387
Haiku 4.5	$0.00017	$0.00194

Measured 4d ago against content hash 225b94289a82, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

applying-skill-best-practices 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 4d 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/handsonai/skills/applying-skill-best-practices/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Applying Skill Best Practices

These are the standards a good Agent Skill meets, consolidated from Anthropic, OpenAI, AgentSkills.io and Google and checked against each other. Read references/sources.md when the user asks where a rule comes from, or when auditing the standards themselves. The same standards, with a worked example, are written up for people at https://handsonai.info/agentic-building-blocks/skills/skill-best-practices/. Apply them whenever a skill is created, edited, reviewed or tested.

This skill does not build skills. The platform's own skill creator (Anthropic's skill-creator, the ChatGPT or Codex skill creator, Copilot Cowork's guided flow, Gemini Enterprise's "Create skill with Gemini") owns that process. These standards tell it what "good" means at each point. Where the creator already covers something, agree with it: your job is to make sure the user's own material (real examples, what a good result looks like, the cases they worry about) goes in, not to add a competing rule.

Platform registry: platform facts (how a skill is installed, where context lives, scheduling, agents) come from the platform registry. Read it from references/platform-registry.json in this skill's own folder; if that file isn't there, from registries/platform-registry.json at the plugin root; if neither exists, fetch https://raw.githubusercontent.com/jamesgray-ai/handsonai/main/plugins/handsonai/registries/platform-registry.json. Read it once per session and reuse it. Find a platform by its key or by any name in its aliases list.

For this skill, the facts that matter are each platform's capabilities.skill_install, skill_settings (whether a skill can choose its own model and effort), skill_invocation (how a skill is set to run only when named) and skill_evaluation (whether the platform's skill creator runs tests). Never state those facts from memory.

The six decisions

Every skill rests on six decisions, grouped by when they come up. Hold each one to its standard.

Read the full file on GitHub · 89 lines

Files

What ships with it

9 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.

4d ago Changed 225b94289a82
19d ago First seen · 89 lines · 166 tokens per session scan A e06208456495

Subscribe to this mod's changes

applying-skill-best-practices is a skill published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 166 tokens to every session and 1,936 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-19.

Building agents

applying-skill-best-practices next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
applying-skill-best-practicesjamesgray-ai/handsonai-plugins	Skill	8	yesterday	MIT	A	166	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code