LocalAI is an inference server that runs language, vision, voice, image, and video models through compatible APIs on local hardware. It is used to operate models privately across different hardware, including CPU-only systems, and supports applications, agents, and multi-user services. The catalogue contains instructions for using LocalAI.
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 mudler/LocalAI --skill writing-skillsgit clone --depth 1 https://github.com/mudler/LocalAIWrote 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/mudler/localai/writing-skills)<a href="https://agentmods.dev/skills/mudler/localai/writing-skills"><img src="https://agentmods.dev/badge/skills/mudler/localai/writing-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/mudler/localai/writing-skills"><img src="https://agentmods.dev/badge/skills/mudler/localai/writing-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 | $0.00048 | $0.00681 |
| Opus 5.5 | $0.00019 | $0.00272 |
| Sonnet 5.5 | $0.00010 | $0.00136 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
writing-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 4d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing skills
A skill is a short written procedure that you read before a task. Write one when the user asks for it ("remember how we do this", "make a skill for it"). Do not write a skill on your own. After you write one, tell the user its name.
Where a skill goes
- For the user's own skills:
/workspace/home/.skills/<name>/SKILL.md. They apply in every chat of this user. - For one folder and everything below it:
<folder>/.skills/<name>/SKILL.md, for example/workspace/shared-Reports/.skills/monthly-report/SKILL.md. Choose this when the procedure belongs to the work in that folder, or when the other people who use the folder should get it too. Everyone who can read the folder sees the skill, and everyone who can write the folder can change it. - Do not write to
/workspace/shared-skills/or/workspace/shared-builtin-skills/. They are read-only for the user: a change there is not saved. An administrator puts skills in the first one. - When two skills have the same name, the nearest one wins: a folder skill, then a personal skill, then a shared skill, then a built-in skill.
The format
A skill is a folder named after the skill. It holds a file SKILL.md and, if the skill needs them, other files such as reference pages or scripts.
---
name: monthly-report
description: Use when the user asks for the monthly sales report. It says which files to use and how to lay out the report.
---
# Monthly report
1. Read `Sales/data.xlsx`, sheet "Totals".
2. ...
| Part | Rule |
|---|---|
name |
Lower case letters, digits and hyphens. It starts with a letter or a digit and has at most 64 characters. |
description |
One or two sentences. It is not empty and has at most 1,024 bytes. It says when to load the skill ("Use when ..."), because it is the only text the agent sees before it loads the skill with load_skill. |
SKILL.md |
At most 64 KiB. Keep it short. Put long reference text in separate files in the same folder and link to them. |
A skill that breaks a rule is skipped. The user sees why in the Skills page.
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.
- 4d ago First seen · 49 lines · 48 tokens per session scan A 02a735fd40d2
writing-skills is a skill published in the GitHub repository mudler/LocalAI (50,218 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 681 once invoked, about $0.0002 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 2026-11-02.
writing-skills compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| writing-skillsmudler/LocalAI | Skill | 50k | yesterday | MIT | A | 48 | Claude Code, Codex |
| sglang-diffusion-performancesgl-project/sglang | Skill | 39k | today | Apache-2.0 | A | 29 | Claude Code, Codex |
| sglang-diffusion-add-modelsgl-project/sglang | Skill | 39k | today | Apache-2.0 | A | 24 | Claude Code, Codex |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 12k | yesterday | CC0-1.0 | A | 116 | Claude Code, Codex |
| sglang-diffusion-cache-ditsgl-project/sglang | Skill | 39k | today | Apache-2.0 | A | 161 | Claude Code |
| sglang-diffusion-modelopt-quantsgl-project/sglang | Skill | 39k | today | Apache-2.0 | A | 49 | Claude Code, Codex |
| skill-creatorunslothai/unsloth | Skill | 79k | today | Apache-2.0 | A | 26 | Claude Code |