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 Vironnimo/vbot --skill skill-writinggit clone --depth 1 https://github.com/Vironnimo/vbotWrote 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/vironnimo/vbot/skill-writing)<a href="https://agentmods.dev/skills/vironnimo/vbot/skill-writing"><img src="https://agentmods.dev/badge/skills/vironnimo/vbot/skill-writing/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/vironnimo/vbot/skill-writing"><img src="https://agentmods.dev/badge/skills/vironnimo/vbot/skill-writing.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 | $0.00000 | $0.01858 |
| Opus 5.5 | $0.00000 | $0.00743 |
| Sonnet 5.5 | $0.00000 | $0.00372 |
| Haiku 4.5 | $0.00000 | $0.00186 |
Grade A, and why
skill-writing 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill writing
This Skill says what a Skill must look like. Every Skill you create and every change you make to a Skill follows it, so that Agents load the Skill exactly when it applies and can follow it to the end.
What a Skill looks like
A Skill is a folder: SKILL.md, plus optional support files under references/, scripts/ and assets/. A Skill holds the method for one recognizable kind of task, including the user's preferences and corrections for that work.
SKILL.md is front matter with name and description, then the instructions:
---
name: <kind-of-task>
description: <What the Skill does>. Use when <situations>.
---
# <Title>
<At most three sentences: what the task produces and where this Skill ends.>
## Steps
1. <One action>. Done when <a result the Agent can check>.
2. <One action>. Done when <a result the Agent can check>.
## Pitfalls
- <A general rule>, because <a short reason>.
Replace every <...> placeholder; delete a section that has nothing to say.
Name
- Name the kind of task in two to four words, lowercase and joined by hyphens:
release-notes,invoice-filing. - Never name a ticket, an error message, a codename, today's output or a generic word such as
helper. A name that fits only today's task belongs to no Skill: extend an existing Skill instead. - vBot accepts at most 64 characters: letters, digits,
-and_, starting with a letter or digit.
Description
Every Agent that has the Skill reads its description on every request, in the list of available Skills. The description decides whether the Agent loads the Skill; it does not teach the task.
- Write one or two sentences: what the Skill does, then
Use whenand the situations that call for it, in the words a user's request would contain. - Keep it under 250 characters.
- Leave out the Skill's name, how to do the task, keyword lists, "This Skill ..." and praise such as "powerful" or "comprehensive".
Good: description: Draft release notes from merged changes in the user's format. Use when the user asks for release notes, a changelog entry or a summary of what a version changed.
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.
- 2d ago Changed a8a2e0be877e
- 9d ago First seen · 101 lines · 0 tokens per session scan A ce0c447cd167
skill-writing is a skill published in the GitHub repository Vironnimo/vbot (1 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,858 tokens. 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 2026-10-08.
Other skills, from other repositories
django-patterns
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
accelerate
Run PyTorch training across GPUs with minimal changes.
fastapi-patterns
FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.
python-patterns
Python-specific design patterns and best practices including protocols, dataclasses, context managers, decorators, async/await, type hints, and package organization. Use when working with Python code to apply Pythonic patterns.
python-testing
Python testing best practices using pytest including fixtures, parametrization, mocking, coverage analysis, async testing, and test organization. Use when writing or improving Python tests.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.