Name: create-agent
Rating: 80.2 (1 reviews)
Author: harness

create-agent

Create and update Harness AI agent instances - standalone templates for agentic workflows in pipelines. Use when asked to create agent, update agent, modify agent spec, build autonomous systems, or work with AI agents.

6.84x

Quality

72%

Does it follow best practices?

Impact

89%

6.84x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude/skills/create-agent/SKILL.md

Quality

Content

62%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete YAML and a clear interactive workflow, but it is verbose (heavy repetition across sections and the guidelines table) and monolithic, inlining material that would benefit from separate reference files. Adding validation feedback loops and trimming repetition would lift the weaker dimensions.

Suggestions

Add an explicit YAML-validation checkpoint (e.g. parse the assembled spec and confirm required env vars/inputs are present) between Phase 3 and the create/update call to strengthen the destructive-operation feedback loop.

Trim redundancy by consolidating the env-var/inputs reference into the worked example and the CRITICAL GUIDELINES table rather than restating the same fields three times, improving token efficiency.

Move the detailed v0/v1 pipeline integration material into a reference file (e.g. references/pipeline-usage.md) and keep SKILL.md as an overview that links to it, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is thorough but heavily padded, repeating the same structure/fields across Phase 3, the CRITICAL GUIDELINES table, and the worked example, which inflates token cost without adding new capability.	3 / 5
Actionability	Provides concrete, copy-paste YAML blocks, named MCP tools with parameters, a UID-generation rule, and a full worked example; minor gaps are placeholder IDs the user must replace rather than executable defaults.	4 / 5
Workflow Clarity	Five clearly sequenced phases with an explicit interactive confirmation checkpoint before the destructive create/update step, though the verification of YAML validity before submission is only loosely implied.	4 / 5
Progressive Disclosure	No bundle/reference files exist and the entire detailed spec, env-var reference, and pipeline integration live inline in one monolithic SKILL.md with no one-level-deep references, so structure is present but content is not split out.	3 / 5
	Total	14 / 20 Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and clearly answers both what the skill does and when to use it, with natural trigger terms. Minor room for improvement lies in enumerating more distinct capabilities and adding synonym-level trigger coverage.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Create and update ... agent instances') tied to a concrete artifact ('standalone templates for agentic workflows in pipelines'), but does not enumerate several distinct capabilities beyond create/update.	4 / 5
Completeness	Explicitly states what the skill does and a clear 'Use when ...' clause with multiple concrete trigger phrases, satisfying both what and when.	5 / 5
Trigger Term Quality	Strong natural triggers ('create agent', 'update agent', 'modify agent spec', 'build autonomous systems', 'work with AI agents') that users would say, missing only minor synonyms or file/extension-style variants.	4 / 5
Distinctiveness Conflict Risk	The Harness-agent niche and explicit trigger phrases make it largely distinct, with only minor overlap risk against generic 'autonomous systems' or coding-agent skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: harness/harness-ai
Path: plugins/claude/skills/create-agent/SKILL.md
Commit: 23e9b8b

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

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.