copilot-skill-builder

A meta-skill for creating and maintaining Agent Skills for GitHub Copilot CLI. It explains the required SKILL.md file, its metadata, optional folders, trigger conditions, allowed tools, and recommended structure.

In plain words
What is it for?
Use it to create, document, configure, or improve Copilot CLI skills and their supporting scripts, examples, or templates.
Why use it?
It gives developers a consistent format for writing skills that Copilot CLI can discover and use. This avoids missing required fields or placing skill files where the CLI will not find them.

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/trsdn/github-copilot-cli/copilot-skill-builder
Any agent
npx skills add trsdn/github-copilot-cli --skill copilot-skill-builder
Clone the repo
git clone --depth 1 https://github.com/trsdn/github-copilot-cli

Made for: Claude Code, Codex.

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,175 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 $0.00061 $0.01175
Opus 5 $0.00030 $0.00588
Sonnet 5 $0.00012 $0.00235
Haiku 4.5 $0.00006 $0.00118

Measured yesterday against content hash cc22e6c20f75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-skill-builder 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 yesterday.

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.

.github/skills/copilot-skill-builder/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Builder

This skill helps you create well-structured Agent Skills for GitHub Copilot CLI.

When to use this skill

  • User wants to create a new Agent Skill
  • User asks about the SKILL.md format or best practices
  • User wants to understand how skills work in Copilot CLI
  • User needs to debug or improve an existing skill

SKILL.md Format

Every skill lives in its own directory and must contain a SKILL.md file:

.github/skills/<skill-name>/
├── SKILL.md          # Required: skill instructions
├── scripts/          # Optional: helper scripts
├── examples/         # Optional: example files
└── templates/        # Optional: template files

SKILL.md Structure

---
name: skill-name
description: What the skill does and when Copilot should use it. Be specific to help Copilot decide when to load this skill.
license: MIT
allowed-tools: read, grep
user-invocable: true
disable-model-invocation: false
---

# Skill Title

Overview of what this skill accomplishes.

## When to use this skill

- Specific trigger 1
- Specific trigger 2

## Step-by-step procedure

1. First step
2. Second step

## Examples

### Example 1: Description
...

## References

- [Link to relevant docs](https://...)

Frontmatter Fields

Field Required Description
name ✅ Yes Unique identifier, lowercase with hyphens, max 64 chars
description ✅ Yes What it does and when to use it, max 1024 chars
license ❌ No License information for the skill
allowed-tools ❌ No Comma-separated string or YAML array of tools to allow when active
user-invocable ❌ No Whether users can invoke the skill with /skill-name; defaults to true
disable-model-invocation ❌ No Prevents automatic model invocation; defaults to false

Skill Locations

Type Location Scope
Project skills .github/skills/<name>/SKILL.md Current repository
Project skills .agents/skills/<name>/SKILL.md Current repository, cross-agent standard
Project skills .claude/skills/<name>/SKILL.md Current repository, Claude-compatible
Personal skills ~/.copilot/skills/<name>/SKILL.md All your projects
Personal skills ~/.agents/skills/<name>/SKILL.md Shared across agent tools
Custom locations COPILOT_SKILLS_DIRS Additional comma-separated directories
Plugin skills <plugin>/skills/<name>/SKILL.md Installed plugin scope

Read the full file on GitHub · 151 lines

Files

What ships with it

1 file 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. yesterday First seen · 151 lines · 61 tokens per session scan A cc22e6c20f75

Subscribe to this mod's changes

copilot-skill-builder is a skill published in the GitHub repository trsdn/github-copilot-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 1,175 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.