skill-creation

A skill for creating and updating Agent Skills, which are instruction packages that give coding agents repeatable abilities.

In plain words
What is it for?
Use it when creating a skill, converting a prompt into a skill, refactoring an existing skill, or checking its structure.
Why use it?
It helps keep skills in the required format and reminds authors to address security when a skill uses tools, commands, external content, or other agents.

Skill for Claude CodeCodex

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 skills/keminghe/common-devx/skill-creation
Any agent
npx skills add KemingHe/common-devx --skill skill-creation
Clone the repo
git clone --depth 1 https://github.com/KemingHe/common-devx

Made for: Claude Code, Codex.

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,240 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 $0.00056 $0.02240
Opus 5 $0.00028 $0.01120
Sonnet 5 $0.00011 $0.00448
Haiku 4.5 $0.00006 $0.00224

Measured 2d ago against content hash 2b53e6c4ee76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-creation 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 2d 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.

.agents/skills/skill-creation/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Creation

Create Agent Skills following the agentskills.io specification for platform-agnostic AI capabilities.

When to Use This Skill

  • Creating a new skill from scratch
  • Converting an existing prompt to skill format
  • Refactoring or validating existing skills
  • Understanding skill structure and best practices

Security Best Practices

This skill creates other skills that may interact with external systems. The Security Best Practices (SBP) block in ./assets/security-best-practices.md should be included in any skill that:

  • Uses MCP tools to fetch external content
  • Executes CLI/shell commands
  • Orchestrates subagents or A2A communications
  • Reads from external URLs or user-generated content

Skill authors are responsible for including SBP in relevant skills. This meta-responsibility is the security mechanism for skill-creation itself.

Asset Resolution

  1. Check ./assets/skill-template.md for the SKILL.md template
  2. Check ./assets/general-doc-constraints.md for the General Doc Constraints block (used conditionally for documentation-output skills)
  3. Check ./assets/security-best-practices.md for the Security Best Practices block (used conditionally for skills that use external tools)
  4. If not found, search **/skill-template.md, **/general-doc-constraints.md, and **/security-best-practices.md in repository
  5. If still not found, use the specification below to generate from scratch

Process

Step 1: Gather Context

Before creating a skill, understand:

  • Purpose: What task does this skill accomplish?
  • Triggers: What keywords or scenarios should activate this skill?
  • Inputs: What information does the agent need from the user?
  • Outputs: What should the agent produce?
  • Assets: Are there templates or reference materials needed?

When refactoring from existing prompt/content:

Analyze the original for critical elements that must be preserved:

Element Look For Why It Matters
Safety mechanisms Read-only operations, forbidden actions, pipe to cat Prevents destructive actions
Setup instructions cd to directory, environment prep Ensures correct execution context
Role/persona "You are a..." statements Sets expertise level and tone
Tool guidance MCP tools, remote APIs, search patterns Enables deeper analysis
User consultation Questions to ask user Ensures alignment with intent
Edge cases Error handling, fallbacks Improves robustness

Read the full file on GitHub · 180 lines

Files

What ships with it

4 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. 2d ago First seen · 180 lines · 56 tokens per session scan A 2b53e6c4ee76

Subscribe to this mod's changes

skill-creation is a skill published in the GitHub repository KemingHe/common-devx (10 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 2,240 once invoked, about $0.0003 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.