Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pnp/copilot-promptsnpx agentmods add skills/pnp/copilot-prompts/create-skill-sampleWrote 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.
[](https://agentmods.dev/skills/pnp/copilot-prompts/create-skill-sample)<a href="https://agentmods.dev/skills/pnp/copilot-prompts/create-skill-sample"><img src="https://agentmods.dev/badge/skills/pnp/copilot-prompts/create-skill-sample/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.
<a href="https://agentmods.dev/skills/pnp/copilot-prompts/create-skill-sample"><img src="https://agentmods.dev/badge/skills/pnp/copilot-prompts/create-skill-sample.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00102 | $0.03077 |
| Opus 5.5 | $0.00041 | $0.01231 |
| Sonnet 5.5 | $0.00020 | $0.00615 |
| Haiku 4.5 | $0.00010 | $0.00308 |
Grade A, and why
create-skill-sample 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a New GitHub Copilot Skill Sample
This skill guides creating new custom skill samples for the pnp/copilot-prompts repository. These samples live inside samples/skills/ and represent reusable instruction files (SKILL.md) that teach GitHub Copilot how to perform specific, repeatable tasks.
Before Starting
Critical: Always ask the user for the following information before scaffolding:
- Skill name — a short, descriptive name for the skill (e.g., "Code Review for C#", "API Documentation Generator", "Unit Test Scaffolder")
- Skill purpose — a clear description of what the skill does. What task does it teach GitHub Copilot to perform?
- Trigger phrases — 3–5 example phrases a user might say to activate the skill (e.g., "review my C# code", "generate API docs")
- Inputs needed — what information the skill needs from the user before it can proceed (e.g., a source file, a framework version, a language)
- Output format — what the skill produces (e.g., a Markdown report, generated code files, a checklist)
- Steps — the high-level steps the skill follows (3–7 steps). Each step should be a discrete action.
- Rules — any hard constraints the skill must always follow (e.g., "never modify source files directly")
- Author name — the contributor's full name
- Author GitHub username — the contributor's GitHub handle
If the user doesn't provide all details upfront, ask for the missing ones before proceeding.
Sample Directory Structure
Create the sample in samples/skills/{skill-name}/:
samples/skills/{skill-name}/
├── SKILL.md # The skill definition file (core contribution)
├── README.md # Documentation and usage instructions
├── assets/
│ └── sample.json # Metadata for the M365 Solution Gallery
Folder naming rules:
- Use lowercase and hyphens only (e.g.,
code-review-csharp,api-docs-generator,unit-test-scaffolder) - Do NOT use periods/dots in the folder name
- Keep it concise but descriptive — 2–5 words
- Do NOT include prefixes like
m365-orgithub-— skill folders use plain descriptive names
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.
- 1mo ago Changed c67ef47a98c5
- 1mo ago First seen · 308 lines · 102 tokens per session scan A 964e4290ef80
create-skill-sample is a skill published in the GitHub repository pnp/copilot-prompts (898 stars, last pushed 3d ago), licensed MIT. It adds 102 tokens to every session and 3,077 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
image-prompt-builder-nl
Craft high-quality natural-language image prompts for any modern text-to-image or image-edit model that accepts flowing English. Trigger when the user wants help writing, rewriting, improving, or translating an English natural-language image prompt — including "write me an image prompt", "improve this image prompt"…
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
promptfoo-provider-setup
Connect Promptfoo to a model, live HTTP API, local Python/JavaScript provider, or app code. Use for request/auth mapping, response parsing, OpenAPI setup, and connection smoke tests. Use promptfoo-evals for broader eval coverage and promptfoo-redteam-setup for attack selection.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
forensic-prompt-compiler
Forensic image-to-prompt compiler for image generation models. Use this skill whenever the user wants to: convert/describe an existing image into a generation prompt, reconstruct a scene as a prompt, generate prompts from reference images for AI image tools (Midjourney, FLUX, Stable Diffusion, DALL-E, or any diffusion…