Head-to-head

Skills in the same category run on the same benchmark tasks, the same model, the same container — so their outputs can be compared directly. 1691 evidence-backed pairs available.

Agents, MCP & Prompting

10 benched · 45 pairs

dispatching-parallel-agents · +2000.0 context-engineering · +1250.0 agent-introspection-debugging · +1250.0 agents · 0.0 agent-sort · 0.0 dmux-workflows · 0.0 full-output-enforcement · -1250.0 planning-and-task-breakdown · -2500.0 using-superpowers · -2500.0 using-agent-skills · -2500.0

dispatching-parallel-agents vs context-engineering →dispatching-parallel-agents vs agent-introspection-debugging →dispatching-parallel-agents vs agents →dispatching-parallel-agents vs agent-sort →dispatching-parallel-agents vs dmux-workflows →context-engineering vs agent-introspection-debugging →context-engineering vs agents →context-engineering vs agent-sort →context-engineering vs dmux-workflows →agent-introspection-debugging vs agents →agent-introspection-debugging vs agent-sort →agent-introspection-debugging vs dmux-workflows →agents vs agent-sort →agents vs dmux-workflows →agent-sort vs dmux-workflows →+4 more skills — link any two as /versus/<a>-vs-

Coding & Development

53 benched · 1378 pairs

rea-ci-tests-audit · +2500.0 using-git-worktrees · +2500.0 requesting-code-review · +2500.0 git-workflow-and-versioning · +2500.0 understand-diff · +2500.0 terminal-bench-loop · +2500.0 triage · +2000.0 prcheckloop · +1500.0 bun-runtime · +1429.0 retro · +1270.0 ponytail-audit · +1250.0 remotion-upgrade · +1250.0 change-impact · +1250.0 understand-dashboard · +1250.0 ponytail-gain · +1250.0 constraint-driven-development · +1250.0 gsap-utils · +1250.0 test-driven-development · +1250.0 paperclip-create-plugin · +1250.0 check-pr · +1250.0 prepare-paperclip-pr · +1250.0 api-design · +833.0 e2e-testing · +417.0 module-regression · +313.0 finishing-a-development-branch · +14.5 receiving-code-review · +9.2 verification-before-completion · +6.5 test-driven-development · +6.5 deprecation-and-migration · 0.0 code-simplification · 0.0 rea-changelog-update · 0.0 prototype · 0.0 api-and-interface-design · 0.0 tdd · 0.0 fix-slow-queries · 0.0 spec-driven-development · 0.0 control-browser · 0.0 documentation-lookup · 0.0 codebase-design · 0.0 debugging-and-error-recovery · 0.0 setup-code-maintenance-bot · 0.0 to-spec · -0.5 domain-modeling · -1233.0 doubt-driven-development · -1250.0 improve-codebase-architecture · -1250.0 code-review-and-quality · -1250.0 performance-optimization · -1250.0 code-review · -1269.0 pr-report · -1500.0 writing-plans · -2500.0 create-verification-skill · -3333.0 setup-matt-pocock-skills · -3772.5 understand-explain · -7500.0

rea-ci-tests-audit vs using-git-worktrees →rea-ci-tests-audit vs requesting-code-review →rea-ci-tests-audit vs git-workflow-and-versioning →rea-ci-tests-audit vs understand-diff →rea-ci-tests-audit vs terminal-bench-loop →using-git-worktrees vs requesting-code-review →using-git-worktrees vs git-workflow-and-versioning →using-git-worktrees vs understand-diff →using-git-worktrees vs terminal-bench-loop →requesting-code-review vs git-workflow-and-versioning →requesting-code-review vs understand-diff →requesting-code-review vs terminal-bench-loop →git-workflow-and-versioning vs understand-diff →git-workflow-and-versioning vs terminal-bench-loop →understand-diff vs terminal-bench-loop →+47 more skills — link any two as /versus/<a>-vs-

Data Analysis & BI

2 benched · 1 pairs

financial-statements · +2500.0 financial-model · 0.0

financial-statements vs financial-model →

DevOps & Cloud

5 benched · 10 pairs

release-changelog · +2625.0 shipping-and-launch · +1250.0 paperclip-dev-workspace-run-verify-fix · 0.0 mle-workflow · 0.0 observability-and-instrumentation · 0.0

release-changelog vs shipping-and-launch →release-changelog vs paperclip-dev-workspace-run-verify-fix →release-changelog vs mle-workflow →release-changelog vs observability-and-instrumentation →shipping-and-launch vs paperclip-dev-workspace-run-verify-fix →shipping-and-launch vs mle-workflow →shipping-and-launch vs observability-and-instrumentation →paperclip-dev-workspace-run-verify-fix vs mle-workflow →paperclip-dev-workspace-run-verify-fix vs observability-and-instrumentation →mle-workflow vs observability-and-instrumentation →

Documents & PDF

4 benched · 6 pairs

documentation-and-adrs · +3.7 doc-maintenance · 0.0 context-and-decisions · -9.5 investor-materials · -2000.0

documentation-and-adrs vs doc-maintenance →documentation-and-adrs vs context-and-decisions →documentation-and-adrs vs investor-materials →doc-maintenance vs context-and-decisions →doc-maintenance vs investor-materials →context-and-decisions vs investor-materials →

Images & Visuals

2 benched · 1 pairs

imagegen-frontend-mobile · +3500.0 brandkit · 0.0

imagegen-frontend-mobile vs brandkit →

Marketing & SEO

8 benched · 28 pairs

viral-instagram-reels · +2500.0 yt-audit · +1250.0 brand-discovery · +500.0 crosspost · 0.0 copywriting · 0.0 viral-short-form · 0.0 viral-youtube-shorts · -1250.0 yt-seo · -2021.0

viral-instagram-reels vs yt-audit →viral-instagram-reels vs brand-discovery →viral-instagram-reels vs crosspost →viral-instagram-reels vs copywriting →viral-instagram-reels vs viral-short-form →yt-audit vs brand-discovery →yt-audit vs crosspost →yt-audit vs copywriting →yt-audit vs viral-short-form →brand-discovery vs crosspost →brand-discovery vs copywriting →brand-discovery vs viral-short-form →crosspost vs copywriting →crosspost vs viral-short-form →copywriting vs viral-short-form →+2 more skills — link any two as /versus/<a>-vs-

Productivity & Automation

6 benched · 15 pairs

wayfinder · +3341.7 understand-onboard · +1250.0 strategic-compact · +750.0 product-capability · +313.0 to-tickets · +9.5 executing-plans · -8.5

wayfinder vs understand-onboard →wayfinder vs strategic-compact →wayfinder vs product-capability →wayfinder vs to-tickets →wayfinder vs executing-plans →understand-onboard vs strategic-compact →understand-onboard vs product-capability →understand-onboard vs to-tickets →understand-onboard vs executing-plans →strategic-compact vs product-capability →strategic-compact vs to-tickets →strategic-compact vs executing-plans →product-capability vs to-tickets →product-capability vs executing-plans →to-tickets vs executing-plans →

Research & Analysis

6 benched · 15 pairs

interview-me · +6500.0 understand-domain · +2500.0 diagnose-why-work-stopped · +1250.0 deep-research · +1250.0 exa-search · 0.0 competitive-report-structure · -1250.0

interview-me vs understand-domain →interview-me vs diagnose-why-work-stopped →interview-me vs deep-research →interview-me vs exa-search →interview-me vs competitive-report-structure →understand-domain vs diagnose-why-work-stopped →understand-domain vs deep-research →understand-domain vs exa-search →understand-domain vs competitive-report-structure →diagnose-why-work-stopped vs deep-research →diagnose-why-work-stopped vs exa-search →diagnose-why-work-stopped vs competitive-report-structure →deep-research vs exa-search →deep-research vs competitive-report-structure →exa-search vs competitive-report-structure →

Security & Compliance

4 benched · 6 pairs

security-review · +2500.0 deal-with-security-advisory · +2500.0 security-and-hardening · 0.0 mcp-dependency-review · 0.0

security-review vs deal-with-security-advisory →security-review vs security-and-hardening →security-review vs mcp-dependency-review →deal-with-security-advisory vs security-and-hardening →deal-with-security-advisory vs mcp-dependency-review →security-and-hardening vs mcp-dependency-review →

Video & Motion

6 benched · 15 pairs

remotion-create · +3250.0 remotion-studio · +2500.0 remotion-saas · +1250.0 remotion-render · +750.0 yt-shorts · 0.0 viral-hooks · -1250.0

remotion-create vs remotion-studio →remotion-create vs remotion-saas →remotion-create vs remotion-render →remotion-create vs yt-shorts →remotion-create vs viral-hooks →remotion-studio vs remotion-saas →remotion-studio vs remotion-render →remotion-studio vs yt-shorts →remotion-studio vs viral-hooks →remotion-saas vs remotion-render →remotion-saas vs yt-shorts →remotion-saas vs viral-hooks →remotion-render vs yt-shorts →remotion-render vs viral-hooks →yt-shorts vs viral-hooks →

Web Development & Design

15 benched · 105 pairs

gsap-plugins · +2500.0 maintain-storybook · +2500.0 gsap-core · +2500.0 image-to-code · +1250.0 redesign-existing-projects · +750.0 gsap-frameworks · +625.0 gsap-timeline · 0.0 design-guide · 0.0 frontend-ui-engineering · 0.0 gsap-scrolltrigger · 0.0 industrial-brutalist-ui · 0.0 gsap-performance · 0.0 frontend-slides · -1250.0 gsap-react · -1250.0 high-end-visual-design · -2500.0

gsap-plugins vs maintain-storybook →gsap-plugins vs gsap-core →gsap-plugins vs image-to-code →gsap-plugins vs redesign-existing-projects →gsap-plugins vs gsap-frameworks →maintain-storybook vs gsap-core →maintain-storybook vs image-to-code →maintain-storybook vs redesign-existing-projects →maintain-storybook vs gsap-frameworks →gsap-core vs image-to-code →gsap-core vs redesign-existing-projects →gsap-core vs gsap-frameworks →image-to-code vs redesign-existing-projects →image-to-code vs gsap-frameworks →redesign-existing-projects vs gsap-frameworks →+9 more skills — link any two as /versus/<a>-vs-

Writing & Content

12 benched · 66 pairs

content-engine · +2500.0 viral-captions-and-ctas · +2500.0 business-plan · +1250.0 article-writing · +1250.0 viral-short-form-ideas · 0.0 brand-voice · 0.0 yt-plan · -1000.0 writing-shape · -1244.0 to-questionnaire · -1250.0 viral-tiktok-content · -1250.0 yt-comment · -1250.0 writing-for-agents · -1257.0

content-engine vs viral-captions-and-ctas →content-engine vs business-plan →content-engine vs article-writing →content-engine vs viral-short-form-ideas →content-engine vs brand-voice →viral-captions-and-ctas vs business-plan →viral-captions-and-ctas vs article-writing →viral-captions-and-ctas vs viral-short-form-ideas →viral-captions-and-ctas vs brand-voice →business-plan vs article-writing →business-plan vs viral-short-form-ideas →business-plan vs brand-voice →article-writing vs viral-short-form-ideas →article-writing vs brand-voice →viral-short-form-ideas vs brand-voice →+6 more skills — link any two as /versus/<a>-vs-