skills.rest
kent013
kent013COMMUNITY
Explore all skills by this author →
WebsiteGitHub

zenigame-recent-trends

Aggregate recent runs from run-reports and alpha-sieve into a labeled trends report.

Updated Apr 17, 2026
Search Tags:#trend-analysis#timeseries#alpha-sieve#run-reports#llm-labeling#ephemeral-output
One-click install
npx skills add https://github.com/kent013/zenigame-fx --skill zenigame-recent-trends
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: zenigame-recent-trends
Source: https://github.com/kent013/zenigame-fx/tree/main/.claude/skills/zenigame-recent-trends
Command: npx skills add https://github.com/kent013/zenigame-fx --skill zenigame-recent-trends

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Observation of cross-run trends by collecting the most recent N runs from run-reports and alpha-sieve to generate a machine-generated, label-enabled report without making causal claims, stored temporarily for review.

Core Features & Use Cases

  • Cross-run trend extraction across metrics from run-reports and alpha-sieve.
  • Ephemeral, non-committal output written to tmp/ with fixed vocabulary labeling for downstream LLM use.
  • Independent execution with default N=10 and optional focus themes and timeline observation.

Quick Start

Run the skill to generate a cross-run trends report for the N runs and save the ephemeral results under tmp/.

Frequently Asked Questions about zenigame-recent-trends

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

FAQPage Schema
How do I identify cross-run trends from run-reports and alpha-sieve outputs?▼

Cross-run trends are identified by aggregating the most recent N runs from run-reports and alpha-sieve, producing a machine-generated observations report. The skill uses fixed vocabulary labeling and defaults to N=10 runs if no value is specified.

What is fixed vocabulary labeling for LLM annotation in timeseries analysis?▼

Fixed vocabulary labeling restricts output annotations to a predetermined set of terms for LLM-only annotation. This approach structures cross-run trend observations without making causal claims, ensuring consistent downstream machine processing.

Can I generate trend analysis reports without committing output to version control?▼

Yes, trend analysis reports can be generated without version control commits by writing ephemeral results to the tmp/ directory. This non-committal output storage allows for temporary review of cross-run insights before any permanent action.

Does the cross-run trend extraction skill support custom focus themes and timeline observation?▼

Cross-run trend extraction supports optional focus themes and timeline observation during execution. Users can specify these parameters alongside the N runs parameter to tailor the machine-generated observations report.

What are the limitations of using ephemeral output for cross-run trend analysis?▼

Ephemeral output limitations include the loss of generated trend observations stored in tmp/ upon session end, requiring users to manually persist results. Additionally, the report makes no causal claims, limiting analysis to observational insights only.

Related Skills

Explore More Data & Analytics Skills→
kent013kent013

zenigame-fx-alpha-sieve

Automate Alpha Sieve execution and analyze reports for Stage C survivors.

Community
Advanced
Cnext-euCnext-eu
1

kairos-medallion-staging

Generate bronze vocabulary TTL files from source system documentation.

Official
Advanced
kent013kent013

zenigame-alpha-sieve

Analyze Alpha Sieve OOS results and generate validation reports.

Community
Advanced
omniauraomniaura
17

S3 Analytics Skill

Fetch and analyze S3 time-series analytics data for KPI trend reports.

Official
Intermediate