skills.rest
Tomoda826
Tomoda826COMMUNITY
Explore all skills by this author →
GitHub

qa-precon-rerun

Re-run QA tests on decks flagged HAS_ISSUES and update statuses.

Updated Aug 27, 2026
Search Tags:#automation#logs#qa#archiving#rerun#precon#deck-testing
One-click install
npx skills add https://github.com/Tomoda826/mtg-goldfisher --skill qa-precon-rerun
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qa-precon-rerun
Source: https://github.com/Tomoda826/mtg-goldfisher/tree/main/.claude/skills/qa-precon-rerun
Command: npx skills add https://github.com/Tomoda826/mtg-goldfisher --skill qa-precon-rerun

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

qa-precon-rerun addresses the need to re-validate decks that previously failed QA by re-running the QA pipeline, re-reviewing logs, and managing status transitions.

Core Features & Use Cases

  • Re-run games and QA reviews for decks with status HAS_ISSUES and aiReviewed: true
  • Check prior FIXED/WONT_FIX notes and archive confirmed fixes after re-verification
  • Generate per-deck engine-health and summary logs to support AI review

Quick Start

Initiate a rerun for a target deck to re-check issues, re-run tests, and archive fixes.

Frequently Asked Questions about qa-precon-rerun

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

FAQPage Schema
How do I re-run QA tests for decks that previously failed validation?▼

Re-run QA tests for failed decks by executing automated scripts that identify items marked HAS_ISSUES, perform game simulations, run gate checks, and update the QA index with new PASS or FAIL statuses.

What happens to decks marked as FIXED when re-validation is performed?▼

Decks marked as FIXED are re-verified during the QA rerun; if the issues are confirmed resolved, their prior fixes are archived and their status transitions away from HAS_ISSUES.

How are engine health and summary logs prepared for AI review?▼

Engine health and summary logs are prepared by running log preparation scripts that generate per-deck health metrics and game summaries, providing the necessary data inputs for accurate AI review.

Can I check prior archiving decisions before re-running QA on a flagged deck?▼

Yes, prior archiving decisions and WONT_FIX notes are consulted from the PRECON_QA_ISSUES log before re-testing, ensuring previous fixes are verified and historical context informs the new validation cycle.

Does the deck testing pipeline support automated regression checks?▼

Yes, the deck testing pipeline includes automated regression checks via dedicated coach regression scripts that evaluate engine health and verify whether previously flagged gameplay issues have been resolved.

What are the limitations of re-running QA only for decks with aiReviewed status?▼

Re-running QA is limited to decks marked HAS_ISSUES with aiReviewed set to true and not yet PASSED, meaning decks lacking prior AI review or already passing validation are excluded from this scope.

Related Skills

Explore More Data & Analytics Skills→
Dino-StarkDino-Stark

examples-auto-run

Run Python examples in auto mode and capture logs.

Community
Intermediate
joojae02joojae02
1

publish

Validate blog drafts, update frontmatter metadata, and move files to Archives.

Community
Intermediate
stopitdanstopitdan

run-evals

Run the recommendation engine evaluation suite and summarize pass rates, NDCG, and failures.

Community
Advanced
pabloimrik17pabloimrik17

openspec-ff-change

Automate creation of OpenSpec change artifacts within CLI workflows.

Community
Intermediate