Skip to content
anyai.fyi

Agent Skills for Claude, Codex & Cursor – top SKILL.md skills

91 skills match · 13 ms

Skill obsidian-vault mattpocock/skills

No description in the SKILL.md.

Other 196k installs curated Not checked yet
Skill edit-article mattpocock/skills

No description in the SKILL.md.

Other 192k installs curated Not checked yet
Skill copy-editing coreyhaines31/marketingskills

When the user wants to edit, tighten, proofread, or refresh existing copy, or asks whether to keep, cut, or change a line in it, without rewriting from scratch. Every edit removes AI tells: 'it's not X, it's Y' reveals,…

Other 163k installs No risky patterns found
Skill azure-cost-optimization microsoft/azure-skills

No description in the SKILL.md.

Other 155k installs curated Not checked yet
Skill hyperframes-media heygen-com/hyperframes

No description in the SKILL.md.

Other 142k installs curated Not checked yet
Skill chief-of-staff mattpocock/skills

Pursue a long-running goal in a single session by co-ordinating subagents.

Other 136k installs curated No risky patterns found
Skill churn-prevention coreyhaines31/marketingskills

When the user wants to reduce churn, or asks why customers cancel, whether to offer a discount or pause: cancellation flows, exit surveys, save offers, dunning and failed-payment recovery. For win-back emails, see…

Other 132k installs No risky patterns found
Skill funnel-platform-picker autonnel/autonnel-skills

Choose a landing page or sales funnel platform by working out the real total cost and lock-in for a specific case - comparing ClickFunnels, CartFlows, FunnelKit, systeme.io, GoHighLevel, Shopify apps, hand-rolled pages…

Other 127k installs No risky patterns found
Skill caveman-optimize juliusbrussee/caveman

Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.

Other 126k installs No risky patterns found
Skill investigate-first juliusbrussee/caveman

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.

Other 126k installs No risky patterns found
Skill verify-and-stop juliusbrussee/caveman

Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.

Other 126k installs No risky patterns found