Ready to supercharge your AI agents?

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

Get Started Free →

Create Subagents · majiayu000 | DecimalAI

agent toolingby majiayu000

Create Subagents

majiayu000/create-subagents

Source majiayu000/claude-skill-registry ↗License MIT

Expert guidance for creating, building, and using Claude Code subagents and the Task tool.

SkillScore100Maintained

Automatic

AI Engineer pack

Last verified 8/19/2026

What it changes

Passed 22 of 22 test cases with the skill, and 13 of 22 without it.

Without skill59%

With skill100%

Checks it passed that the model alone missed

The response specifies the directory path .claude/agents/
The response states that the default timeout duration is 30000 milliseconds
The response recommends using the <constraints> XML tag for operational rules

and 8 more in the full report

9 fixed13 passed either way0 still failing0 broke

Pass-rate lift: +41 pp
Tokens: +122%
Agent turns: 0%
Response time: -53%

Model gemini-3.6-flashMeasured 8/19/2026v122 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-create-subagents/SKILL.md https://app.decimal.ai/s/majiayu000-create-subagents/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-create-subagents, 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-create-subagents/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-create-subagents

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

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

Raw file: /s/majiayu000-create-subagents/SKILL.md ↗ · machine-readable summary at /s/majiayu000-create-subagents.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

When invoking TaskOutput with blocking enabled, what is the default timeout duration in milliseconds if no explicit timeout argument is provided?

What was checked, without and with the skill
Checked	Without skill	With skill
The response states that the default timeout duration is 30000 milliseconds	Missed	Passed

case-17 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md446 linessingle file

Subagents enable delegation of complex tasks to specialized agents that operate autonomously without user interaction, returning their final output to the main conversation.

<quick_start>

Run /agents command
Select "Create New Agent"
Choose project-level (.claude/agents/) or user-level (~/.claude/agents/)
Define the subagent:
- name: lowercase-with-hyphens
- description: When should this subagent be used?
- tools: Optional comma-separated list (inherits all if omitted)
- model: Optional (sonnet, opus, haiku, or inherit)
Write the system prompt (the subagent's instructions)

<focus_areas>

Code quality and maintainability
Security vulnerabilities
Performance issues
Best practices adherence </focus_areas>

Track record

Benchmark

22 / 22

test cases passed, vs 13 / 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 — 8/3/2026

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/create-subagents/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version 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.