agentsclimarketplace

Vgc battle review

Skill NoahJenkins/vgc-coach/skills/vgc-battle-review

Use when reviewing a Pokemon Champions replay for mistakes and better lines.From its SKILL.md

Install
npx -y skills add NoahJenkins/vgc-coach --skill vgc-battle-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.2 KB, as published. Nobody here has run it

VGC Battle Review

Turn a battle into actionable review instead of hindsight theater.

Inputs

  • battle-state-v1 JSON produced by tools/ingest_battle_state.py
  • replay summaries
  • logs
  • turn-by-turn notes
  • post-game self-reflections
  • optional review goal
  • optional player-side context

Structured battle state is preferred when available, but prose notes and turn summaries remain supported. Treat omitted structured fields as unknown; do not infer hidden information. See the shared battle-state-v1 contract.

If format is omitted, assume the current Pokemon Champions regulation and say so.

Output

Return these sections in order:

  1. Review Goal and Match Context
  2. Key Turning Points
  3. Actual Mistakes vs Variance
  4. Stronger Alternative Lines
  5. Prep and Practice Implications
  6. Open Questions

Workflow

  1. Identify the player's likely plan before judging the result. When battle-state-v1 is supplied, ground this in its observed events and revealed-information timeline.
  2. Focus on the real swing turns instead of narrating every turn equally.
  3. Separate information the player had in game from hindsight-only knowledge.
  4. Distinguish sequencing or planning mistakes from acceptable losing lines and variance.
  5. Offer alternative lines that were realistic from the actual board state.
  6. End with what should change in prep, habits, or team assumptions next time.

Required behavior

  • Read review-checklist and output-rubric before finalizing.
  • If a turning point depends on one benchmark, hand that point to vgc-calcs-assistant.
  • If the loss exposes a repeatable prep pattern, leave a clean handoff for vgc-practice-journal.
  • If public opponent tendencies mattered, point toward vgc-opponent-scout.
  • Use live meta verification when the review depends on current matchup assumptions.
  • Do not call every loss a misplay, judge with unavailable hindsight, or offer impossible alternative lines.

Keep looking

Skills are one crate of 610,677. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.