Skip to content

Category

AI Skills

Skills for AI agents — Claude skills, agent skills, cursor rules and MCP servers that teach Claude Code, Codex, Cursor and other agents new tricks.

12841 apps.

AI Skills, page 3

Ranked by popularity.

101
U

using-superpowers

Starting any conversation

Launch
102
V

verification-before-completion

Enforce verification commands before claiming work completion, fixes

Launch
103
W

writing-plans

Comprehensive implementation plans for multi-step tasks

Launch
104
W

writing-skills

Test-driven documentation for creating reusable agent techniques, patterns

Launch
105
A

ask-matt

Ask which skill or flow fits your situation

Launch
106
C

caveman

Ultra-compressed communication mode cuts token usage ~75%

Launch
107
C

chief-of-staff

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

Launch
108
C

claude-handoff

Hand the current conversation off to a fresh background agent

Launch
109
C

code-review

Review the changes since a fixed point

Launch
110
C

codebase-design

Shared vocabulary for designing deep modules

Launch
111
D

decision-mapping

Turn a loose idea into a sequenced map of investigation tickets

Launch
112
D

design-an-interface

Generate multiple radically different interface designs for a module

Launch
113
D

diagnose

Structured debugging workflow for reproducing, minimizing

Launch
114
D

diagnosing-bugs

Diagnosis loop for hard bugs and performance regressions

Launch
115
D

domain-modeling

Build and sharpen a project's domain model

Launch
116
E

edit-article

Edit and improve articles by restructuring sections, improving clarity

Launch
117
G

git-guardrails-claude-code

Set up Claude Code hooks to block dangerous git commands

Launch
118
G

grill-me

Relentless interviewing skill

Launch
119
G

grill-with-docs

Relentless design interrogation

Launch
120
G

grilling

Grill the user relentlessly about a plan, decision, or idea

Launch
121
H

handoff

Summarize conversations into handoff documents

Launch
122
I

implement-spec

Implement the result of /to-spec and /to-tickets in code

Launch
123
I

improve-codebase-architecture

Analyze codebases for architectural friction

Launch
124
L

loop-me

Grill me about specs for the workflows I want to build, within this workspace

Launch
125
M

migrate-to-shoehorn

Migrate test files from `as` type assertions to @total-typescript/shoehorn

Launch
126
O

obsidian-vault

Search, create, and manage notes in the Obsidian vault

Launch
127
P

pr

Writing a PR body

Launch
128
P

prototype

Throwaway code that answers a single design or logic question through an

Launch
129
Q

qa

Interactive QA session where user reports bugs or issues conversationally

Launch
130
R

request-refactor-plan

Create a detailed refactor plan with tiny commits

Launch
131
R

research

Investigate a question against high-trust primary sources

Launch
132
R

resolving-merge-conflicts

Resolve an in-progress git merge/rebase conflict

Launch
133
R

retro

Conduct a retrospective on a coding session

Launch
134
R

review

Review the changes since a fixed point

Launch
135
S

scaffold-exercises

Create exercise directory structures

Launch
136
S

setup-matt-pocock-skills

Configuration scaffold for engineering skills to locate issue tracker

Launch
137
S

setup-pre-commit

Set up Husky pre-commit hooks with lint-staged

Launch
138
S

setup-ts-deep-modules

Wire dependency-cruiser into a TypeScript repo

Launch
139
T

tdd

Test-driven development with vertical slices, behavior-focused tests

Launch
140
T

teach

Teach the user a new skill or concept, within this workspace

Launch
141
T

to-issues

Break a plan into independently-grabbable vertical-slice issues

Launch
142
T

to-prd

Synthesizes conversation context into a structured PRD and publishes it

Launch
143
T

to-questionnaire

Turn a decision you can't fully answer into a questionnaire for someone else

Launch
144
T

to-spec

Turn the current conversation into a spec and publish it

Launch
145
T

to-tickets

Break a plan, spec, or the current conversation into a set of tracer-bullet

Launch
146
T

triage

State machine-driven issue triage

Launch
147
U

ubiquitous-language

Extract a DDD-style ubiquitous language glossary from the current conversation

Launch
148
W

wait-what

Stop. That last message did not land: re-pitch it

Launch
149
W

wayfinder

Plan a huge chunk of work

Launch
150
W

wizard

Generate an interactive bash wizard

Launch

Other categories