compare-models
Compare two or more AI models on benchmark scores with overlapping and non-overlapping benchmark tables.
Skill by 144126
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/144126-compare-models
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/compare-models
What's inside
- Skill name
compare-models- Description
- Compare two or more AI models on benchmark scores with overlapping and non-overlapping benchmark tables. Trigger whenever a user asks to 'compare', 'benchmark', or 'versus' AI models (e.g. 'compare model X vs Y', 'how does model A compare to B', 'benchmark scores for model C and D', 'which is better, X or Y'). Also trigger when user asks to add, create, or write a comparison skill. Do NOT trigger for simple model version comparisons without benchmarks.
- License
- unknown
- Instructions
- 124 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from 144126/skills
- 0.565score
motion-doctrine
144126
GATEWAY — load FIRST before composing any HyperFrames animation or video.
SkillAFreshness: AClaude Code +9 - 0.565score
naming
144126
Use when naming or renaming an app, product, company, feature, or project, or judging a name - "what should I call it", "name ideas", "is this a good name"…
SkillAFreshness: AClaude Code +9 - 0.565score
graphic-design
144126
Use when making or reviewing any static visual - posters, thumbnails, social graphics, slides, logos, cards, flyers, layouts, UI screens, infographics…
SkillAFreshness: AClaude Code +9 - 0.561score
creative
144126
Use on any task where a fresh, beautiful result beats a merely correct one - names, copy, titles, UI, design, video, music, stories, jokes, ideas, features…
SkillAFreshness: AClaude Code +9 - 0.559score
captions-overlay
144126
Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of…
SkillAFreshness: AClaude Code +9 - 0.559score
ghost-edit
144126
Edit a document in small bits without putting your own prose in the file, because the text may be checked for AI.
SkillAFreshness: AClaude Code +9 - 0.559score
cut-the-curve
144126
The technique catalog: five velocity-matched SEAMS (zoom-through, INVERSE zoom-through, cut-the-curve, waterfall cut, rack-focus blur-cut) plus the two…
SkillAFreshness: AClaude Code +9 - 0.524score
digital-root
144126
Compute the numeric sum and digital root of a string by mapping each alphabetic character to its position in the alphabet (a=1, b=2, ...
SkillBFreshness: BClaude Code +9 - 0.524score
atomic-task-graph
144126
Plan and execute a long-horizon task as an Atomic Task Graph — recursive interface-preserving decomposition, a pre-execution thought experiment, parallel…
SkillBFreshness: BClaude Code +9 - 0.524score
condense-search
144126
Truth-seeking condense of live web results into an audited claim ledger: adaptive dual-channel sampling, quote-anchored extraction, deterministic…
SkillBFreshness: BClaude Code +9 - 0.519score
bible-search
144126
Semantic search over the Bible (Young's Literal Translation) via a live API backed by a state-of-the-art embedding model.
SkillBFreshness: BClaude Code +9 - 0.519score
dre
144126
Deep Research → Markdown Report.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 5, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/144126/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from 144126
- 0.565score
naming
144126
Use when naming or renaming an app, product, company, feature, or project, or judging a name - "what should I call it", "name ideas", "is this a good name"…
SkillAFreshness: AClaude Code +9 - 0.565score
graphic-design
144126
Use when making or reviewing any static visual - posters, thumbnails, social graphics, slides, logos, cards, flyers, layouts, UI screens, infographics…
SkillAFreshness: AClaude Code +9 - 0.565score
motion-doctrine
144126
GATEWAY — load FIRST before composing any HyperFrames animation or video.
SkillAFreshness: AClaude Code +9 - 0.561score
creative
144126
Use on any task where a fresh, beautiful result beats a merely correct one - names, copy, titles, UI, design, video, music, stories, jokes, ideas, features…
SkillAFreshness: AClaude Code +9 - 0.559score
ghost-edit
144126
Edit a document in small bits without putting your own prose in the file, because the text may be checked for AI.
SkillAFreshness: AClaude Code +9 - 0.559score
captions-overlay
144126
Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of…
SkillAFreshness: AClaude Code +9
Cite this page
compare-models skill. Agent Mart. https://agentmart.dev/skills/144126-compare-models (last updated 2026-10-24)