t3chnaztea/batocera-skills/template
Claude Code and agent skill by t3chnaztea/batocera-skills
- community
Checking that the SKILL.md file is still in the repository.
Use when [the specific situations, symptoms, and phrases that should trigger this skill]. Pack the words someone would actually type or think when they hit this problem. Describe ONLY when to use it, never summarize the workflow inside. Keep the whole frontmatter under 1024 characters. End by naming what this skill is NOT for, pointing at the sibling skill that covers it.
Install
npx vskill@latest install t3chnaztea/batocera-skills/templateSKILL.md
Batocera Yourskill
One or two sentences: what this skill covers and that it assumes the connection pattern, filesystem model, and safety doctrine from batocera-ops. Cross- reference sibling skills by name (batocera-roms, batocera-display, batocera-tuning, batocera-maintenance) rather than repeating their content.
Guidelines for a good Batocera skill
Delete this section in your real skill; it's guidance for authoring.
- Name:
batocera-<area>, lowercase and hyphens only. The directory name
MUST equal the frontmatter name.
- Description: starts with "Use when…", lists concrete triggers and keywords,
ends with a "not for X, use Y" pointer. No workflow summary (an agent will follow the description instead of reading the body).
- Original prose only. Do not paste text from the Batocera wiki or other
docs — write the lesson in your own words and link the wiki as the canonical manual. Ship institutional knowledge the wiki doesn't have.
- Parameterize everything host-specific. Use
$BATOCERA_HOST, never a real
IP; read passwords from env; never commit tokens, credentials, MQTT secrets, or personal ROM/library specifics.
- Non-destructive doctrine. Prefer hide/move/append over delete/overwrite;
back up configs and gamelists before editing; never inject synthetic input.
- Verify against ground truth. Show the reader how to confirm the change
(read the generated config, launch + screenshot), not just make it.
- Keep
SKILL.mdunder ~500 lines. Push heavy detail intoreferences/*.mdand
reusable code into scripts/. Scripts should be --dry-run-first where they mutate, idempotent, and self-documenting in a header.
Overview
What this is and the core principle in 1–2 sentences.
When to use
Symptoms and situations (bullets). When NOT to use.
[Your sections]
Quick-reference tables, worked examples, the specific traps you learned. One excellent example beats five generic ones.
References
- references/topic.md — heavy detail loaded on demand.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingtemplate/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/t3chnaztea/batocera-skills/template)