Skip to main content
Jeden Skill in Manus ausführen
mit einem Klick
GitHub-Repository

mage-bench

mage-bench enthält 10 gesammelte Skills von GregorStocks, mit Repository-Berufsabdeckung und Skill-Detailseiten auf SkillsMP.

gesammelte Skills
10
Stars
63
aktualisiert
2026-07-02
Forks
5
Berufsabdeckung
2 Berufskategorien · 100% klassifiziert
Repository-Explorer

Skills in diesem Repository

investigate-golden-flake
Softwarequalitätssicherungsanalysten und -tester

Debug a failing golden test from GitHub Actions logs and fix the root cause without papering over nondeterminism.

2026-07-02
deep-analysis
Softwareentwickler

Investigate a game from raw logs, trace bugs to source code, and file detailed issues. Use for deeper debugging than export-only analysis.

2026-03-27
create-pr-local
Softwareentwickler

Repo-specific validation and PR instructions for mage-bench.

2026-03-24
card-finder
Softwarequalitätssicherungsanalysten und -tester

Find Magic cards for compact golden-test scenarios using existing repo goldens, curated references, and Scryfall search recipes.

2026-03-23
fast-analysis
Softwarequalitätssicherungsanalysten und -tester

Analyze exported game files to assess gameplay, model decisions, and likely bugs without raw logs. Use for quick game triage.

2026-03-23
golden-test
Softwarequalitätssicherungsanalysten und -tester

Write or update low-noise golden prompt tests in tests/, including minimal decks, replay scripts, and golden regeneration.

2026-03-23
new-export-version
Softwareentwickler

Create a new game export schema version, migration module, and related tests.

2026-03-23
solve-issue-local
Softwareentwickler

Repo-specific build, test, and PR instructions for mage-bench issue solving.

2026-03-23
blunder-backfill
Softwarequalitätssicherungsanalysten und -tester

Re-annotate recent games with outdated or missing blunder analysis. Use when users ask to backfill or refresh blunder annotations.

2026-03-22
find-improvable-errors
Softwarequalitätssicherungsanalysten und -tester

Analyze MCP tool errors across exports to find unhelpful error messages and recommend improvements.

2026-03-22