Ready to supercharge your AI agents?

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

Get Started Free →

Agent Tuning Skill · majiayu000 | DecimalAI

agent toolingby majiayu000

Agent Tuning Skill

majiayu000/agent-tuning

Source majiayu000/claude-skill-registry ↗License MIT

Configure and optimize AI coding agents (OpenCode/Claude).

SkillScore82Maintained

Automatic

AI Engineer pack

Last verified 8/18/2026

What it changes

Passed 18 of 22 test cases with the skill, and 9 of 22 without it.

Without skill41%

With skill82%

Checks it passed that the model alone missed

The response sets interruptionSensitivity to high.
The response recommends voice ID ErXwobaYiN019PkySvjV.
The response recommends eleven_flash_v2_5 as the primary model.

and 8 more in the full report

9 fixed9 passed either way4 still failing0 broke

Pass-rate lift: +41 pp
Tokens: +148%
Agent turns: 0%
Response time: -39%

Model gemini-3.6-flashMeasured 8/18/2026v218 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-agent-tuning/SKILL.md https://app.decimal.ai/s/majiayu000-agent-tuning/SKILL.md

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

decimalai skills add majiayu000-agent-tuning

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

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

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

In a 3-minute lead qualification conversation flow, how long should the initial greeting step take, and what is the target overall call duration?

What was checked, without and with the skill
Checked	Without skill	With skill
The response allocates 5 to 10 seconds for the initial greeting.	Missed	Passed
The response sets the target total conversation duration to approximately 3 minutes.	Passed	Passed

case-13 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md616 linessingle file

Agent Tuning Skill

Expert guidance for optimizing ElevenLabs Conversational AI agents for Next Level Real Estate platform. This skill provides systematic approaches to agent configuration, performance optimization, and continuous improvement.

When to Use This Skill

Invoke this skill when you need to:

✅ Create a new conversational AI agent
✅ Select the optimal voice for an agent
✅ Craft or improve system prompts
✅ Configure agent parameters (latency, turn-taking, language)
✅ Design conversation flows for real estate use cases
✅ Set up A/B testing for agent optimization
✅ Analyze agent performance and identify improvements
✅ Update knowledge bases with successful patterns

Agent Configuration Framework

1. Define Agent Purpose

Every agent needs a clear, specific purpose:

Good Examples:

"Qualify wholesale leads within 3 minutes by assessing motivation, timeline, and property condition"
"Follow up with warm leads who haven't responded in 7 days, re-engage and schedule viewing"
"Conduct market research calls to gather intel on neighborhood pricing and seller motivations"

Bad Examples:

"Talk to leads" (too vague)
"Do real estate stuff" (no clear objective)
"Help with sales" (not specific enough)

Template:

Purpose: [Action] [Target] within [Timeframe] by [Method]
Success Criteria: [Measurable outcome]

2. Voice Selection Process

Track record

Benchmark

18 / 22

test cases passed, vs 9 / 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/agent-tuning-wildwasser-opencode-agents/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v2

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

Ready to supercharge your AI agents?

See it in action

What's inside

Agent Tuning Skill

When to Use This Skill

Agent Configuration Framework

1. Define Agent Purpose

2. Voice Selection Process

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills