create-agent
Create and update Harness AI agent instances - standalone templates used as building blocks in pipelines. Agents contain a single agent step with connector-driven architecture requiring llmConnector (LLM access) and optional mcpConnectors (GitHub, Slack, Harness platform). Supports runtime inputs and task/rules-based instruction. Use when asked to create an agent, update agent spec, modify agent configuration, automate tasks, perform agentic workflows, build autonomous systems, or work with AI agents. Trigger phrases: create agent, update agent, modify agent spec, AI agent, autonomous agent, agentic pipeline, automation task, automate workflow, Harness agent, code coverage agent, review agent, agentic task.
82
73%
Does it follow best practices?
Impact
96%
3.42xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/claude/skills/create-agent/SKILL.mdEvaluation results
100%
81%Automated Docstring Generation Agent
New agent YAML spec generation
Correct container image
0%
100%
ANTHROPIC_MODEL env var
0%
100%
PLUGIN_HARNESS_CONNECTOR env var
0%
100%
llmConnector input
0%
100%
anthropicModel input
0%
100%
Default model ARN
0%
100%
max_turns in valid range
0%
100%
No forbidden sections
100%
100%
Correct YAML structure
0%
100%
Input reference syntax
37%
100%
Placeholder connector IDs
100%
100%
100%
88%CI Failure Triage and Notification Agent
Multi-MCP agent YAML spec
mcp_format: harness
0%
100%
mcp_servers syntax
0%
100%
mcpConnectors as array
0%
100%
Correct container image
0%
100%
ANTHROPIC_MODEL env var
0%
100%
PLUGIN_HARNESS_CONNECTOR env var
0%
100%
llmConnector input
0%
100%
anthropicModel with default ARN
0%
100%
max_turns in valid range
0%
100%
No forbidden sections
100%
100%
Placeholder connector IDs
50%
100%
Correct YAML structure
0%
100%
88%
34%Expanding an Architecture Review Agent
Update existing agent spec
harness_get first
100%
100%
harness_update not harness_create
66%
100%
Custom agents only note
0%
0%
RULES section added
0%
100%
Character limit rule
100%
100%
max_turns in valid range
0%
100%
Required inputs preserved
100%
100%
Container image preserved
100%
100%
No forbidden sections added
100%
100%
Minimal update scope
0%
80%
- Repository
- harness/harness-ai
- Commit
a000afa
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.