Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Opencode Agent Creation · majiayu000 | DecimalAI

agent toolingby majiayu000

Opencode Agent Creation

majiayu000/opencode-agent-creation

Source majiayu000/claude-skill-registry ↗License MIT

Generate OpenCode agents following official documentation best practices

SkillScore91Maintained

Automatic

AI Engineer pack

Last verified 9/2/2026

What it changes

Passed 20 of 22 test cases with the skill, and 17 of 22 without it.

Without skill77%

With skill91%

Checks it passed that the model alone missed

Sets the mode property to subagent.
Identifies permissions as the configuration field.
Identifies maxSteps as the agent configuration property.

and 1 more in the full report

4 fixed16 passed either way1 still failing1 broke

Pass-rate lift: +14 pp
Tokens: -25%
Agent turns: 0%
Response time: -28%

Model gemini-3.6-flashMeasured 9/2/2026v120 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/majiayu000-opencode-agent-creation/SKILL.md https://app.decimal.ai/s/majiayu000-opencode-agent-creation/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-opencode-agent-creation, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/majiayu000-opencode-agent-creation/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-opencode-agent-creation

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-opencode-agent-creation/SKILL.md https://app.decimal.ai/s/majiayu000-opencode-agent-creation/SKILL.md

Raw file: /s/majiayu000-opencode-agent-creation/SKILL.md ↗ · machine-readable summary at /s/majiayu000-opencode-agent-creation.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

I want to prevent my OpenCode agent from looping indefinitely when running automated refactoring tasks. Which agent configuration key controls the maximum execution steps?

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies maxSteps as the agent configuration property.	Missed	Passed

case-09 · gemini-3.6-flash · 9/2/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md17 linessingle file

What I do

Guide you through creating a new OpenCode agent by prompting for required configuration
Generate agent files in either JSON (opencode.json) or Markdown format following official documentation
Determine appropriate mode (primary or subagent) based on agent purpose
Configure tools, permissions, temperature, maxSteps, and other agent options
Create markdown agent files with proper frontmatter in .opencode/agents/ or ~/.config/opencode/agents/
Ensure description is provided and other required fields are set correctly

When to use me

Use this when:

You want to create a new OpenCode agent without manually formatting configuration
You need to ensure your agent follows official documentation standards
You want to avoid repetitive setup when creating multiple agents

Ask clarifying questions about the agent's purpose, mode, tools access, and permissions.

Track record

Benchmark

20 / 22

test cases passed, vs 17 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

majiayu000 / claude-skill-registry

skills/agent/opencode-agent-creation/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/10/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.