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.
65
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/claude/skills/create-trigger/SKILL.mdQuality
Discovery
89%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 solid skill description with excellent trigger term coverage and clear completeness. The 'Use when' clause is well-constructed with multiple natural user phrases. The main weakness is that the 'what' portion could be more specific about the concrete actions performed beyond just 'generate YAML and create via MCP'.
Suggestions
Expand the capability description to list more specific actions, e.g., 'Generate Harness Trigger YAML for webhook, cron, and artifact-based pipeline triggers, configure trigger conditions, and create triggers via MCP.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Harness Trigger YAML) and mentions 'automated pipeline execution' and 'create via MCP', but doesn't list multiple specific concrete actions beyond generating YAML. It could specify actions like configuring webhook endpoints, setting cron schedules, defining artifact conditions, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (Generate Harness Trigger YAML for automated pipeline execution and create via MCP) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Both components are present and explicit. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'create trigger', 'webhook trigger', 'cron trigger', 'scheduled build', 'artifact trigger', and the conceptual phrase 'pipelines to run automatically'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Harness Trigger YAML' is a very specific niche, and the trigger terms like 'webhook trigger', 'cron trigger', 'artifact trigger' are clearly scoped to this domain. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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 with excellent YAML templates covering all major Harness trigger types and clear MCP integration instructions. Its main weaknesses are the lack of explicit validation/error-recovery loops in the workflow and the monolithic structure that could benefit from splitting detailed templates into separate reference files. Minor verbosity in the examples and performance notes sections could be trimmed.
Suggestions
Add an explicit validation step after harness_create (e.g., call harness_get to confirm creation, check response status) and integrate error recovery into the main workflow sequence.
Consider splitting per-trigger-type YAML templates into separate reference files (e.g., WEBHOOK_TRIGGERS.md, ARTIFACT_TRIGGERS.md) and keeping only the most common template inline.
Remove the 'Examples' section — it merely restates trigger type mappings already obvious from the templates above it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good YAML templates, but includes some unnecessary sections like 'Examples' (which just restates what the triggers do) and 'Performance Notes' that are somewhat obvious. The troubleshooting section adds value but could be tighter. | 2 / 3 |
Actionability | Provides fully executable YAML templates for each trigger type, specific MCP tool calls with parameters, concrete payload condition examples with operator options, and real cron expressions. All templates are copy-paste ready with clear placeholder values. | 3 / 3 |
Workflow Clarity | The 5-step instruction sequence is clear, and verification is mentioned (step 5: verify webhook registration). However, there's no explicit feedback loop for validation failures — e.g., what to do if the harness_create call fails or if the webhook isn't registered. The troubleshooting section partially compensates but isn't integrated into the workflow. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and logical grouping by trigger type. However, at ~150 lines with detailed YAML for each trigger type, some templates (GitLab, Artifact) could be split into referenced files. No bundle files exist to offload this content, making the skill somewhat monolithic. | 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.