CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-operations

Configure Harness AI-powered operations (AIDA) via MCP. Set up predictive failure analysis with ML models for memory leaks, disk exhaustion, connection pool saturation, and latency degradation. Configure intelligent alert correlation and noise reduction to reduce alert volume. Use when asked to set up predictive failure analysis, configure AI-powered alerting, reduce alert noise, or enable ML-based anomaly detection. Do NOT use for pipeline debugging (use debug-pipeline instead) or SLO management (use manage-slos instead). Trigger phrases: AIDA, predictive failure, alert correlation, noise reduction, anomaly detection, AI ops, predictive analysis, alert fatigue, ML alerting, intelligent alerting.

69

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

68%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 body is well-structured and largely actionable with concrete configuration options and a clear step sequence, but it lacks explicit validation checkpoints in the workflow and ships all material inline with no reference files despite a length that would benefit from progressive disclosure.

Suggestions

Add explicit validation/verification checkpoints to the workflow (e.g., after Step 3 verify the model has completed initial training, and after Step 4 send a test alert to confirm correlation and routing behave as expected).

Move the detailed configuration option catalogs (Step 3/4 option lists) and the Troubleshooting section into reference files under ./references/ and link to them from SKILL.md to improve progressive disclosure.

Show the concrete MCP tool invocations used to actually apply each configuration (not just harness_list), so the guidance is copy-paste ready rather than implied.

DimensionReasoningScore

Conciseness

The body is mostly lean bullet lists of concrete options with no padding or explanation of concepts Claude already knows; a few enumerated option lists (e.g., data sources, alerting tools) could be tightened. It is not a 5 because some list repetition across Steps 3 and 4 could be consolidated.

4 / 5

Actionability

Concrete enumerated configuration options (prediction horizons, correlation methods, data sources, routing targets) give actionable guidance; it is not a 5 because only one MCP call is shown as an example and the actual configuration tool invocations are implied rather than copy-paste ready.

4 / 5

Workflow Clarity

A clear four-step sequence (Establish Scope, Identify Task, Configure Predictive Failure Analysis, Configure Alert Correlation) is present, but there are no explicit validation/verification checkpoints within the workflow (e.g., confirm model trained, test alert routing), keeping it at the validation-gap anchor rather than 4.

3 / 5

Progressive Disclosure

Content is well-organized into clear sections (Instructions with steps, Examples, Performance Notes, Troubleshooting) with no nested or buried references; it is not a 5 because the skill exceeds ~50 lines and the detailed option catalogs and troubleshooting material could reasonably be externalized into reference files that are absent.

4 / 5

Total

15

/

20

Passed

Description

100%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.

A strong, well-structured description that clearly states capabilities, provides concrete natural trigger phrases, and explicitly bounds the skill against overlapping siblings. It fully satisfies what/when/distinctiveness without padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Configure Harness AI-powered operations (AIDA) via MCP', 'Set up predictive failure analysis with ML models for memory leaks, disk exhaustion, connection pool saturation, and latency degradation', 'Configure intelligent alert correlation and noise reduction') with comprehensive coverage of the domain.

5 / 5

Completeness

Explicitly answers both what ('Configure...predictive failure analysis', 'Configure intelligent alert correlation') and when ('Use when asked to set up predictive failure analysis, configure AI-powered alerting, reduce alert noise, or enable ML-based anomaly detection') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides comprehensive natural trigger terms including synonyms users would actually say: 'AIDA, predictive failure, alert correlation, noise reduction, anomaly detection, AI ops, predictive analysis, alert fatigue, ML alerting, intelligent alerting'.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Harness AIDA / AI ops) with explicit negative boundary guidance ('Do NOT use for pipeline debugging (use debug-pipeline instead) or SLO management (use manage-slos instead)') minimizing conflict with sibling skills.

5 / 5

Total

20

/

20

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.