Name: create-trigger
Rating: 69.6 (1 reviews)
Author: harness

create-trigger

Generate Harness Trigger YAML for automated pipeline execution and create via MCP. Use when user says "create trigger", "webhook trigger", "cron trigger", "scheduled build", "artifact trigger", or wants pipelines to run automatically.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Quality

Content

70%

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 executable YAML and MCP calls, but it leans long and keeps all variant templates inline without external references, and the create/verify workflow lacks explicit validation checkpoints for state-mutating operations.

Suggestions

Move per-provider webhook and artifact-source YAML variants into a references/ file (e.g. references/trigger-templates.md), keeping one canonical example inline for leaner progressive disclosure.

Add an explicit validation checkpoint after the MCP create step (e.g. call harness_get on the created trigger and confirm the returned identifier) applicable to all trigger types, not just webhooks.

Trim the restated concept lists (Trigger Types, GitHub Event Types, Artifact Source Types) to the essential entries or move them to a reference, since Claude can infer many of these from the templates.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete templates, but the body inlines four full YAML examples plus listing sections that restate concepts (trigger types, event/source types) Claude can infer, and could be tightened by offloading variants to references.	2 / 3
Actionability	Provides complete, copy-paste-ready YAML templates per trigger type and explicit MCP tool calls with parameters, matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	The numbered Instructions sequence exists, but operations that mutate Harness state (create trigger, webhook registration) lack explicit validation checkpoints or error-recovery feedback loops, and step 5's verification is only mentioned for webhooks.	2 / 3
Progressive Disclosure	Reasonably sectioned, but it is a single monolithic SKILL.md with no bundle files; the four YAML templates and artifact/event/source listings are inline content that could be split into reference files for leaner disclosure.	2 / 3
	Total	9 / 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.

A strong, specific description with explicit trigger guidance and concrete capabilities tied to the Harness domain. Third-person voice is maintained and the 'Use when...' clause clearly delineates when to invoke the skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Generate Harness Trigger YAML', 'create via MCP', and supports distinct trigger types (webhook, cron, artifact, scheduled) — matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly states what it does (generate trigger YAML, create via MCP) and when to use it via the 'Use when user says...' clause, satisfying both what and when.	3 / 3
Trigger Term Quality	Includes natural phrasings a user would say verbatim — 'create trigger', 'webhook trigger', 'cron trigger', 'scheduled build', 'artifact trigger' — giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	Targets a narrow, distinct niche (Harness pipeline triggers) with specific trigger phrases unlikely to collide with other skills, so conflict risk is low.	3 / 3
	Total	12 / 12 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-trigger/SKILL.md
Commit: a48c95a

Reviewed: 22 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.