CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

92

3.42x
Quality

88%

Does it follow best practices?

Impact

96%

3.42x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is highly actionable with clear sequenced workflows and validation checkpoints, but it is a long monolithic document that would benefit from pruning redundant prose and offloading reference material into separate files.

Suggestions

Trim the Phase 2 requirements-gathering section: condense the seven enumerated questions into a compact checklist, dropping explanatory bullets that restate concepts Claude already knows.

Extract the troubleshooting, best-practices, and full config-reference blocks into separate referenced files (e.g. TROUBLESHOOTING.md, REFERENCE.md) and link to them one level deep to improve progressive disclosure.

De-duplicate Phase 3 against the CRITICAL GUIDELINES table, which restates much of the same spec-assembly and connector guidance.

DimensionReasoningScore

Conciseness

The ~340-line body is mostly useful but padded in places — the interactive requirements section enumerates seven questions with explanatory bullets that restate concepts Claude already knows, and Phase 3 overlaps with the CRITICAL GUIDELINES table. It is mostly efficient but could be tightened.

2 / 3

Actionability

Provides concrete executable YAML blocks, specific MCP tool calls with full parameter objects, and a complete worked Code Review Agent example — copy-paste ready guidance rather than pseudocode.

3 / 3

Workflow Clarity

A clear five-phase sequence with explicit interactive validation checkpoints ('show YAML for review and wait for confirmation', 'Wait for explicit confirmation before creating/updating') gives strong feedback loops for the destructive create/update operation.

3 / 3

Progressive Disclosure

No bundle files exist and all content — troubleshooting, examples, and the full config reference — lives inline in one ~340-line SKILL.md rather than being split into one-level-deep references. Structure is present but content that should be separate is inline.

2 / 3

Total

10

/

12

Passed

Description

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.

The description is specific, uses third person, and explicitly covers both capabilities and trigger conditions with a strong, naturally-worded trigger-phrase list. It is a clear, well-targeted skill description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Create and update Harness AI agent instances', connector architecture 'requiring llmConnector... optional mcpConnectors', 'runtime inputs and task/rules-based instruction'), matching the score-3 anchor.

3 / 3

Completeness

Clearly answers 'what' (create/update agent instances with connector-driven architecture) and 'when' via an explicit 'Use when...' clause with enumerated triggers.

3 / 3

Trigger Term Quality

Explicit 'Trigger phrases:' list gives broad natural-term coverage (create agent, update agent, AI agent, autonomous agent, agentic pipeline, automate workflow) that users would actually say.

3 / 3

Distinctiveness Conflict Risk

Scoped to 'Harness AI agent instances' with Harness-specific triggers, giving it a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
harness/harness-ai
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.