Research latest Claude models and update selection guide — run when new models drop or periodically to stay current
Scanned 6/11/2026
Install via CLI
openskills install shenxingy/Clade---
name: model-research
description: Research latest Claude models and update selection guide — run when new models drop or periodically to stay current
when_to_use: "research models, latest Claude, update model guide, new models"
argument-hint: '[--apply]'
user_invocable: true
---
# Model Research Skill
Searches the web for latest Claude model information, compares benchmarks and pricing, then updates the model selection guide.
## What it does
1. Searches for latest Claude model announcements, benchmarks, and pricing
2. Compares against the current guide in `docs/research/models.md`
3. Shows what changed (new models, price changes, benchmark updates)
4. With `--apply`: updates `models.md`, `session-context.sh` model guidance, and `batch-tasks/prompt.md` model assignment
## Usage
```
/model-research # Research + show diff (no changes written)
/model-research --apply # Research + update all configs
```
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...