Skill Maintenance

Community

ryoppippi

skill-maintenance

Audits all local skills in this repo for skill-creator and Anthropic best-practice compliance. Use to review the whole skill collection — checking descriptions, SKILL.md length, cross-skill duplication, and documentation references — not to author a single skill.

Overview

Publisher	ryoppippi
Repository	`dotfiles`
Skill name	`skill-maintenance`
Stars	263
Forks	5
Bundled files	2
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by ryoppippi on GitHub. Read the source before you install it.

Installation

Install the Skill Maintenance AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/ryoppippi/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/agents/skills/skill-maintenance .claude/skills/skill-maintenance

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Maintenance in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Skill Maintenance on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Skill Maintenance is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill Maintenance

Repo-wide health check for the skills under agents/skills/. Where the skill-creator skill authors or edits one skill, this skill reviews and optimises the whole collection at once: every SKILL.md, plus the relationships between skills (duplication, merge/link opportunities).

The authoring conventions being enforced all live in skill-creator — this skill does not restate them. It is the auditor; skill-creator is the rulebook.

Workflow

Copy this checklist and work through it:


Skill audit:
- [ ] 1. Run scripts/audit.nu for the mechanical pass
- [ ] 2. Audit each flagged skill against references/audit-checks.md
- [ ] 3. Cross-skill duplication pass (link or merge)
- [ ] 4. Documentation & repo-file references pass
- [ ] 5. Report findings, then fix with confirmation

1. Mechanical pass. Run the script — it lists every skill with its SKILL.md line count, name/description lengths, and references/ + scripts/ presence, flagging hard violations with !:

bash
agents/skills/skill-maintenance/scripts/audit.nu

2. Per-skill audit. For each skill the script flagged (and spot-check the rest), apply the criteria in references/audit-checks.md: best-practice adherence, name/description quality, and SKILL.md length/splitting.

3. Cross-skill duplication. This is the check single-skill authoring cannot do. Compare skills that touch the same topic and decide, per the "Cross-skill duplication" section of the reference, whether to cross-link them by name or merge them. Find candidates with:

bash
rg -N '^description:' agents/skills/*/SKILL.md   # overlapping triggers

4. References pass. Confirm each skill points at sources of truth — docs URLs, node_modules/<package>/README.md for library skills, and named repo files for local skills — instead of pasting copies. See the reference's "Documentation and repo-file references" section.

5. Report and fix. Summarise findings as a per-skill list (issue → proposed fix). Apply fixes following skill-creator, then re-run scripts/audit.nu to confirm the mechanical flags clear. Deploy as skill-creator describes (stage only the skill dirs, then nix run .#switch).

Scope

In scope: structure, metadata, duplication, references, length. Out of scope: rewriting a skill's domain logic — that is ordinary editing via skill-creator.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

references/audit-checks.md2 KB
scripts/audit.nu5 KB

Frequently asked questions

What does the Skill Maintenance AI skill do?

Why use Skill Maintenance on TypingMind?

Because you install it once and use it with any model. Skill Maintenance is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Skill Maintenance in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ryoppippi/dotfiles/tree/main/agents/skills/skill-maintenance. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Skill Maintenance?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Skill Maintenance?

As many as you like. As long as a model supports skills, you can use Skill Maintenance with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Skill Maintenance AI skill free?

Yes. It is published on GitHub by ryoppippi under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Writing For Agents

mattpocock

CommunityPopular

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

Karpathy Guidelines

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define…

Create Agent

Create a custom agent (.agent.md) for a specific job.

Create Hook

Create a hook (.json) to enforce policy or automate agent lifecycle events.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Skill Maintenance

Workflow

Scope

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now