Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

claude-code-setup

21625

jt247/claude-code-setup

Skill Claude CodeCodex

Expert guide for setting up Claude Code as a complete solo development environment. Covers MCPs, skills, agents, production stack selection, and day-to-day workflows for non-technical product builders who want to ship web and mobile products alone.

not rated 2 3mo ago D 53 tokens

sql-analytics-patterns

21626

justanesta/claude-code-resources

Skill Claude CodeCodex

Window functions, analytical queries, and advanced aggregation patterns for business intelligence and reporting. Use this skill when writing ranking queries, running totals, moving averages, percentile calculations, period-over-period comparisons, gap-and-island analysis, or pivot/crosstab transformations. Covers all…

not rated 2 5mo ago A 78 tokens original MIT

context-management

21627

stateofthehart/claude-code-config

Skill Claude CodeCodex

This skill should be used when the conversation is getting long, context feels bloated, Claude mentions compaction or context limits, the user asks about "context", "pruning", "memory", "compaction", or when Claude notices tool outputs are very large. Also activate when resuming a session, starting a large task, or…

not rated 2 5mo ago A 86 tokens

cc-chain

21628

Golm117/Claude_Code_start

Skill Claude CodeCodex

Drive an async Claude Code chain — investigate the next slice, run confirm-understanding at a configurable threshold (default 95%), auto-fire via RemoteTrigger if confidence clears, otherwise ping the user. Use when the user has explicitly authorized auto-fire mode (Pattern B+) and asks for the next slice in a chain.

not rated 2 4mo ago A 66 tokens

init-project

21629

Iteam-company/claude-code-boilerplates

Skill Claude Code

Full project initialization after cloning the boilerplate. Installs dependencies, walks through .env setup, configures the database, and writes a project-specific CLAUDE.md. Run this once after cloning. Triggers on /init-project.

not rated 2 22d ago A 50 tokens

agent-browser

21630

jeffjacobsen/yokeflow2

Skill Claude CodeCodex

Browser automation CLI for AI agents. Use when you need to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, or testing web apps.

not rated 2 7mo ago A 40 tokens

drawio

21631

shaynemeyer/claude-code-awesomeness

Skill Claude CodeCodex

Always use when user asks to create, generate, draw, or design a diagram, flowchart, architecture diagram, ER diagram, sequence diagram, class diagram, network diagram, mockup, wireframe, or UI sketch, or mentions draw.io, drawio, drawoi, .drawio files, or diagram export to PNG/SVG/PDF.

not rated 2 1mo ago A 75 tokens

discuss-with-codex

21632

yfe404/claude-codex-pairing

Skill Claude CodeCodex

Use codex/codex-reply as a persistent second-engineer thread for non-trivial uncertainty — design choices, risky implementation decisions, debugging when stuck, review, spec ambiguity, needing a current/authoritative websearch, or any point where you'd otherwise guess. Keep one thread and iterate; don't treat the…

not rated 2 3mo ago A 75 tokens original MIT

init

21633

airvalona/antigravity-like-claude-code

Skill Claude CodeCodex

Scans the current project and generates or updates an AGENTS.md file containing directory structure, build/test/lint commands, coding conventions, and architecture notes. Use when the user says "/init", "initialize this project", "set up project memory", or asks the agent to learn the codebase's conventions for the…

not rated 2 2mo ago A 68 tokens original MIT

main

21635

soemsakplus/pantheon

Skill Claude CodeCodex

Capability layer. For identity see AGENT.md, for permissions see POLICY.md.

not rated 2 4mo ago A 0 tokens original Apache-2.0

Waylon524/us-visa.SKILL

Skill Claude CodeCodex

Use when the user wants to practice a U.S. nonimmigrant visa interview as a Chinese citizen, roleplay a consular officer, estimate B1/B2 approval odds, identify 214(b) or 221(g) risk factors, or get concrete interview-prep feedback before a U.S. visa appointment.

not rated 2 4mo ago A 72 tokens original MIT

listen

21637

PatrickJaiin/claude-code-connect

Skill Claude Code

Put this Claude Code session into listener (child) mode so another session can connect to it with /connect, read a summary of this session, send it prompts, and read its replies. Use when the user runs /listen.

not rated 2 2mo ago A 48 tokens original MIT

safety-trinity

21639

AutoZYX-Labs/ADSafetyPilot

Skill Claude CodeCodex

A combined safety-analysis method covering vehicle functional safety, limits of intended functionality, and cybersecurity. It maps risks from system failures, difficult operating conditions, and attacks into one analysis.

not rated 2 3mo ago A 48 tokens original MIT

ui_node_link

21640

SnoopCorleone/e2e-methodology

Skill Claude Code

A planning skill for connecting related business-page nodes. It combines links within a page, relationships between pages, and feature points into connection units for later agent work.

not rated 2 1mo ago A 116 tokens

consolidate

21641

eddiesmo/second-brain-demo

Skill Claude Code

Review recent journal entries, identify recurring themes, and suggest evergreen notes to extract.

not rated 2 7mo ago A 20 tokens

skills

21642

bybit-exchange/pay-docs

Skill Claude CodeCodex

Skill "skills" from bybit-exchange/pay-docs, covering bybit pay — ai integration skill, products overview, authentication (both products), required headers and signature construction.

not rated 2 today A 0 tokens

gh-stack

21643

adrienlupo/Claude-code-config

Skill Claude CodeCodex

Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch chains, or incremental code review workflows.

not rated 2 3d ago A 65 tokens

[object Object]

21644

SnowBeatRain/skills

Skill Claude CodeCodex

A partially filled skill template from a collection of agent skills. Its shown guidance covers confirming the desired result, checking relevant files, using supporting references and scripts, and reporting verification or blockers.

not rated 2 21d ago A 8 tokens original MIT

write-plan

21645

arcadesunlabs/skills

Skill Claude CodeCodex

Plan and implement non-trivial work with a fixed workflow - explore, plan, confirm, implement, validate, review, update docs. Use after write-spec, for direct implementation tasks, bug fixes, or refactors that need a plan.

not rated 2 changed 20d ago A 51 tokens

use-ig

21646

Facets-cloud/praxis-cli

Skill Claude CodeCodex

Use when working in a project that is onboarded to ig (infragraphify) and you need to answer how repos/services connect, where the code for a concept or endpoint lives, how a frontend call reaches its backend handler, what infrastructure backs a service, or the blast radius of a change — instead of grepping a…

not rated 2 yesterday A 116 tokens original MIT

model-validator

21648

gizix/cc_projects

Skill Claude Code

Add comprehensive validation to Django models using validators, clean methods, and constraints. Use when implementing model validation, business rules, or data integrity checks.

not rated 2 6mo ago A 32 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: