skills.rest
infantesromeroadrian
infantesromeroadrianCOMMUNITY
Explore all skills by this author →
Website𝕏@infantes_adrianGitHub

skill-effectiveness

Aggregate skill usage telemetry from JSONL logs and flag low success rates.

Updated Jun 21, 2026
Search Tags:#quality assurance#performance review#telemetry analysis#skill monitoring#manual review trigger
One-click install
npx skills add https://github.com/infantesromeroadrian/arca-agent --skill skill-effectiveness
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-effectiveness
Source: https://github.com/infantesromeroadrian/arca-agent/tree/main/template/skills/skill-effectiveness
Command: npx skills add https://github.com/infantesromeroadrian/arca-agent --skill skill-effectiveness

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill analyzes the success rates of skills based on log data, identifying those with low performance and requiring manual review.

Core Features & Use Cases

  • Aggregate skill-telemetry logs: Processes the JSONL log file to compile a weekly report.
  • Flag low-performance skills: Highlights skills whose success rates fall below a defined threshold.
  • Manual review trigger: Generates a report that can be reviewed to determine if a skill requires rework.

Quick Start

To generate a report flagging low-performance skills over the last 4 weeks with a success rate threshold of 0.7, use the following command:

/skill-effectiveness --weeks 4 --threshold 0.7

Frequently Asked Questions about skill-effectiveness

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I monitor skill performance using telemetry logs?▼

To monitor skill performance, this Skill aggregates usage telemetry from JSONL log files to compute per-skill success rates. It processes your logs to compile a weekly report highlighting low-performing skills based on your defined threshold.

How do I flag low success rates in skill usage logs for manual review?▼

You can flag low success rates in skill usage logs by running the command with a specific threshold parameter. The Skill identifies any skills falling below your defined success rate and generates a report triggering a manual review for potential rework.

How do I compute per-skill success rates from JSONL log files?▼

To compute per-skill success rates from JSONL log files, the Skill parses the telemetry data and aggregates execution outcomes. It evaluates the parsed logs over a specified number of weeks to calculate the overall effectiveness of each skill.

What file format is required to trigger a manual review for low-performing skills?▼

The manual review trigger requires access to skill usage logs formatted as JSONL. The Skill relies on this specific structured data format to accurately parse telemetry and compute the success rate thresholds needed to flag skills.

Can I analyze skill telemetry over a custom time period?▼

Yes, you can analyze skill telemetry over a custom time period by specifying the weeks parameter. For example, passing the weeks argument allows the aggregation script to limit the log data evaluation to your desired reporting window.

Related Skills

Explore More Product & Management Skills→
cas-bigdatalabcas-bigdatalab
541

tsv_formatter

Convert TSV files into JSONL format using Python.

Official
Basic
barichterbarichter

rework-rate

Analyze pull request rework rates and review cycle metrics.

Community
Intermediate
protoLabsAIprotoLabsAI
2

Blue Team / Defensive Methodology Skill

Automate defensive security assessments, incident response workflows, and purple team coverage analysis.

Official
Advanced
nihaoshinihaoshi
27

detect-wordcount

Count words in a text document and validate against a specified threshold.

Community
Basic