fast-analysis
Analyze exported game files to assess gameplay, model decisions, and likely bugs without raw logs. Use for quick game triage.
npx skills add majiayu000/claude-skill-registry --skill fast-analysis --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Fast Game Analysis Quickly analyze a game using only the exported game file (`.json` or `.json.gz`). This covers ~85-90% of what the full analysis finds — game narrative, LLM decision quality, error patterns, bug identification — without needing the raw log directory. ## Workflow ### Step 1: Select the games Determine which game(s) to analyze: - If the user specified game ID(s), use those. - If the user said "most recent" or similar, find the latest: ```bash uv run python scripts/list_recent_games.py ``` - If the user mentioned a config name (e.g. "round-robin-commander", "jumpstart-dumb", "modern-staller"), use the corresponding symlink: ```bash uv run python scripts/list_recent_games.py --config {config} ``` where `{config}` might be `round-robin-commander`, `jumpstart-dumb`, `modern-staller`, etc. Check what symlinks exist with `--symlinks`. - **If no game specified at all**, find the most recent unanalyzed games: ```bash make list-games-to-analyze ``` This cross-references all game exports in `website/public/games/` (both `.json` and `.json.gz`) against existing analysis files in `doc/claudes/analyses/fast/` and prints the unanalyzed ones newest-first. Use `ARGS="--count N"`
- Workflow
- Step 1: Select the games
- Step 2: Resolve the game file path
- Step 3: Use reusable analysis scripts
- Known model error patterns (not platform bugs)
- Step 4: Check existing issues and verify bugs still exist
- Step 5: Log the analysis
- Step 6: Present summary
- Step 7: Update this skill
- What this skill does NOT do
uv run python scripts/list_recent_games.py
uv run python scripts/list_recent_games.py --config {config}
make list-games-to-analyze
uv run python scripts/export_game.py ${GAME_ID}
uv run python scripts/analysis/toolbox/game_overview.py $GAME_PATH
uv run python scripts/analysis/toolbox/game_narrative.py $GAME_PATH
uv run python scripts/analysis/toolbox/llm_events.py $GAME_PATH
uv run python scripts/analysis/toolbox/llm_reasoning.py $GAME_PATH
uv run python scripts/query_issues.py
git log --oneline --since="YYYY-MM-DD" origin/master # date of the gameWhat does the fast-analysis skill do?
Analyze exported game files to assess gameplay, model decisions, and likely bugs without raw logs. Use for quick game triage.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill fast-analysis --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.