create-agent-template
Generate Harness Agent Template files for AI-powered automation agents. Produces metadata.json, pipeline.yaml (v1 syntax), and wiki.MD files. Agents automate tasks like code review, security scanning, test generation, and documentation. This is a YAML generation skill. Use when asked to create an agent template, build an AI agent, create an automation agent, generate agent pipeline files, or set up a Harness agent. Trigger phrases: create agent template, agent template, AI agent, automation agent, build agent, code review agent, security scanner agent, Harness agent.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what it does (generates specific Harness Agent Template files), when to use it (explicit trigger phrases and use-when clause), and occupies a distinct niche. It uses proper third-person voice throughout and provides comprehensive trigger term coverage without being unnecessarily verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generates metadata.json, pipeline.yaml (v1 syntax), and wiki.MD files. Also names specific agent types like code review, security scanning, test generation, and documentation. | 3 / 3 |
Completeness | Clearly answers both 'what' (generates Harness Agent Template files including metadata.json, pipeline.yaml, and wiki.MD) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios, plus a dedicated trigger phrases list). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'create agent template', 'AI agent', 'automation agent', 'build agent', 'code review agent', 'security scanner agent', 'Harness agent'. These are terms users would naturally use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with the 'Harness Agent Template' niche, specific file outputs (metadata.json, pipeline.yaml v1 syntax, wiki.MD), and domain-specific triggers. Unlikely to conflict with generic YAML or code generation skills due to the Harness-specific framing. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill that provides concrete, executable templates for generating Harness Agent Template files. Its main strengths are the completeness of code examples and the clear reference tables for input types, expression syntax, and error handling. Its weaknesses are moderate verbosity with some redundant sections, a long monolithic structure that could benefit from splitting content into referenced files, and workflow validation steps that lack explicit feedback loops.
Suggestions
Add an explicit feedback loop to the workflow: 'If input references in pipeline.yaml don't match metadata.json inputs, fix the mismatch and re-validate before finalizing.'
Move the detailed clone configurations, step types, and expression syntax sections into a separate reference file (e.g., references/pipeline-syntax.md) to reduce the main skill's length and improve progressive disclosure.
Remove the duplicate clone configuration that appears both in 'Core Structure' and 'Clone Configurations' sections to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy (e.g., clone configuration shown twice—once in core structure and again in clone configurations section). The 'Performance Notes' section largely repeats validation guidance from the instructions. Some sections like the examples showing trigger phrases add little value. However, it mostly avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready templates for all three output files (metadata.json, pipeline.yaml, wiki.MD) with concrete YAML/JSON syntax, specific expression syntax references, and detailed input type tables. The code examples are complete and specific rather than pseudocode. | 3 / 3 |
Workflow Clarity | The instructions section provides a clear 4-step sequence including a validation step ('Validate consistency'), but lacks explicit feedback loops—there's no 'if validation fails, fix and retry' pattern. For a generation task that produces multiple interdependent files, the missing error recovery loop and the fact that validation is described abstractly ('ensure input references match') rather than with concrete validation commands caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill references 'references/agent-examples.md' for complete examples and common patterns, which is good progressive disclosure. However, no bundle files are provided, so this reference is unverifiable. The main file itself is quite long (~250 lines) with substantial inline content (full wiki.MD template, multiple clone configurations, troubleshooting sections) that could be split into reference files for better organization. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- harness/harness-ai
- Commit
a000afa
- Reviewed
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.