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.
npx skills add ApexIQ/skillsmith --skill how_to_create_skillsgit clone --depth 1 https://github.com/ApexIQ/skillsmithWrote 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/apexiq/skillsmith/how_to_create_skills)<a href="https://agentmods.dev/skills/apexiq/skillsmith/how_to_create_skills"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/how_to_create_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.
<a href="https://agentmods.dev/skills/apexiq/skillsmith/how_to_create_skills"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/how_to_create_skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.00686 |
| Opus 5 | $0.00017 | $0.00343 |
| Sonnet 5 | $0.00007 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
how-to-create-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 12d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📚 How to Create Skills
Philosophy: Skills are reusable playbooks that ensure consistent, high-quality work.
1. File Structure
Every skill is a folder containing at minimum a SKILL.md file:
skills/
my_new_skill/
SKILL.md # Required: Main instructions
scripts/ # Optional: Helper scripts
examples/ # Optional: Reference implementations
templates/ # Optional: Starter files
2. SKILL.md Format
Required: YAML Frontmatter
---
version: 0.1.0
name: my-skill-name
description: A clear description of what this skill does and when to use it.
---
| Field | Purpose |
|---|---|
name |
Unique identifier (lowercase, hyphens). |
description |
Explains WHAT the skill does and WHEN to use it. This is critical for skill discovery. |
Body Structure
# Title with Emoji
> **Philosophy/Rule:** Core principle of this skill.
## 1. Section Name
Content with tables, examples, code blocks.
## Examples
* **Good example:** Description.
* **Bad example:** What to avoid.
## Guidelines
* Key takeaway 1.
* Key takeaway 2.
3. Best Practices
Keep It Focused
- One skill = One purpose. Don't create a "mega skill" that does everything.
- If a skill exceeds 500 lines, split into multiple skills.
Write for Discoverability
- The
descriptionfield is used to find relevant skills. - Be specific: "Use when writing FastAPI endpoints" not "Backend stuff".
Include Concrete Examples
- Show code that demonstrates the pattern.
- Include both GOOD and BAD examples.
Use Tables for Quick Reference
- Tables are scannable and concise.
- Great for checklists, patterns, and comparisons.
Cross-Reference Other Skills
- Link to related skills: "See
debuggingskill for troubleshooting."
4. Skill Creation Checklist
- Created folder in
skills/directory. - Added
SKILL.mdwith YAML frontmatter. -
descriptionclearly states WHAT and WHEN. - Included at least one concrete example.
- Added guidelines section.
- Tested skill is discoverable and clear.
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.
- 12d ago First seen · 108 lines · 34 tokens per session scan A 1d1dcfa36174
how-to-create-skills is a skill published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 686 once invoked, about $0.0002 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.
Other skills, from other repositories
pptx
Extract text from Microsoft PowerPoint presentations.
xlsx
Extract data from Excel and CSV files.
agent-teams
Multi-agent team orchestration with native Agent Teams. Trigger when the user wants to launch a team of agents, coordinate parallel work with inter-agent communication, or use swarm mode.
ops-infra-code
Infrastructure as Code with Terraform/OpenTofu. Trigger to create modules, configure backends, write idiomatic HCL, or audit infrastructure.
Read, create and manipulate PDF files — extract text and tables, merge, split, rotate, reorder and delete pages, read and fill AcroForm fields, add or strip metadata, encrypt and decrypt, and generate new PDFs from HTML or from scratch. Also covers rasterising pages to images so a PDF can actually be looked at, and…
easd-verify
Run the final EASD integration and evidence gate against accepted AC policies, then prepare a convergence recommendation. Use after implementation and any required independent review; not for task-local code review or ordinary tests outside EASD.