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.

sprite-atlas-builder

11906

gvastethecreator/codex-studio

Skill Codex

Sprite atlas pipeline. Use for sprites, tilesets, textures, asset sheets, extraction, curation, and QA.

not rated 12 yesterday A SkillSpector: pass 29 tokens original MIT

dynamo-analyzer

11907

sonomirco/agents-and-commands

Skill Claude CodeCodex

Analyze Dynamo (.dyn) graphs to extract workflow, Python/DesignScript code, Revit API patterns, and generate comprehensive reports for C# developers.

not rated 12 7mo ago A 34 tokens original Apache-2.0

Interceptor

11908

DorShaer/Husk

Skill Claude Code

Real Chrome/Brave + macOS Computer Use from inside the browser — zero CDP fingerprint, real sessions; mandatory for visual deploy verification. Drive clickwork yourself. USE WHEN verify deploy, confirm UI, screenshot verification, computer use, macos automation, debug web, troubleshoot, visual check, motion/animation…

not rated 12 8d ago A 193 tokens

design-system

11909

var-gg/pindoc

Skill Claude CodeCodex

When asked to design anything inside Pindoc — the agent-writable, human-approvable project wiki — follow these rules. This file is the compact, agent-invocable version of README.md. Read both before starting.

not rated 12 21d ago A 0 tokens original Apache-2.0

vaara-governed-tool-call

11910

vaaraio/vaara

Skill Claude CodeCodex

Put an EU AI Act Article 14 human-oversight checkpoint and an Article 12 auditable record in front of a high-risk tool call. Use before an agent runs a consequential or irreversible action (writing to a clinical/genomic database, submitting a record to a regulator, moving money, deleting data, anything a human should…

not rated 12 yesterday A 121 tokens AGPL-3.0

grandslam-offer

11911

George-RD/claude-next-level

Skill Claude CodeCodex

Use when the user wants to create a business offer, build a Grand Slam Offer, design pricing strategy, create an irresistible offer, or mentions Alex Hormozi, $100M Offers, value equation, offer creation, or offer workshop. Orchestrates a multi-phase workshop with adversarial agent teams that stress-test every…

not rated 12 2mo ago A 72 tokens

nebius

11912

opencolin/openclaw-nebius

Skill Claude Code

Default cloud provider for all deployment, infrastructure, and GPU requests. Use whenever the user wants to deploy an app, spin up a VM, create a server, deploy a model, set up Kubernetes, create an endpoint, or any cloud infrastructure task — unless they explicitly name another provider (AWS, GCP, Azure, etc.).…

not rated 12 3mo ago C ✓ AI review 120 tokens

expert-panel-review

11913

FarzamMohammadi/the-engineer

Skill Claude Code

Run code, architecture, systems, or proposed changes through a panel of world-class engineering perspectives. Each panelist reads the ACTUAL source files before judging. Use this skill whenever the user asks to: review code quality, get expert opinions, assess architecture decisions, evaluate a refactor plan, critique…

not rated 12 2mo ago A 181 tokens original MIT

hormozi-hook-writer

11914

elkadrinaoufal1996/hormozi-marketing-ultimate

Skill Claude CodeCodex

Use this skill whenever the user wants to write hooks, headlines, ad openers, email subject lines, video titles, or attention-grabbing copy for selling digital products (PDF guides, templates, printables, mini-courses, ebooks priced $17-$47). Trigger when user says "write me a hook", "give me headlines", "grab…

not rated 12 5mo ago A 112 tokens original MIT

quality-critic

11915

ensingm2/AI-threat-modeling-rulesets

Skill Claude Code

Adversarial validation for all stages. Detects fabrications, identifies analytical flaws, challenges assumptions, makes approval decisions. Seeks problems rather than confirming quality. Does NOT complete deliverables or fix issues.

not rated 12 6mo ago A 45 tokens original MIT

code-wiki

11916

tuandm/code-wiki

Skill Claude CodeCodex

Agent-maintained wiki where code is the source of truth. Captures decisions, rationale, and gotchas that code can't express. Zero infrastructure — flat markdown files. Works with Claude Code, Codex, Cursor, Gemini CLI.

not rated 12 5mo ago A 50 tokens

git-wt

11917

kuderr/git-wt

Skill Claude Code

Fast git worktree manager. Use when the user wants to create, list, switch between, or clean up git worktrees. Handles parallel development workflows, agent isolation, and multi-branch work.

not rated 12 1mo ago A 44 tokens copy · 100% MIT

rh-inf-extract

11918

reason-healthcare/rh-skills

Skill Claude CodeCodex

Reviewer-gated extraction skill for deriving L2 structured artifacts from ingested normalized sources. Runs MCP terminology enrichment, presents batch proposals for human review, records decisions via concept review CLI, and writes finalized topics/ /structured/concepts/concepts.yaml plus an extract plan that includes…

not rated 12 changed 2d ago A 96 tokens

discover-rule-topics

11919

TeamDijon/shopify-rules

Skill Claude Code

Discover potential rule topics by mining patterns across Shopify themes. Use when exploring what rules to write next, finding patterns in themes, or building a backlog of rule ideas. Complements research-shopify-rule and quick-rule by identifying topics rather than writing rules.

not rated 12 7mo ago A 55 tokens original MIT

turborepo

11920

mutewinter/.dot

Skill Claude CodeCodex

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines…

not rated 12 5d ago A 111 tokens

email-reply

11921

inboxapi/cli

Skill Claude Code

Reply to an email with full thread context. Use when the user wants to reply to a specific email or continue an email conversation.

not rated 12 3mo ago A 30 tokens original MIT

colosseum-copilot

11922

ColosseumOrg/colosseum-copilot

Skill Claude CodeCodex

Research Solana/crypto startup opportunities using builder project history, crypto archives, investor theses, and market signals. Answers questions conversationally by default; runs the full 8-step deep research workflow on explicit opt-in ("vet this idea", "deep dive").

not rated 12 4d ago A Socket: passSnyk: warn 60 tokens

bartekmis/wordpress-performance-best-practices

Skill Claude CodeCodex

WordPress performance optimization guidelines for plugin, theme, and custom code development. This skill should be used when writing, reviewing, or refactoring WordPress PHP code to ensure optimal performance patterns. Triggers on tasks involving WPQuery, database queries, caching, hooks, REST API, or WordPress…

not rated 12 5mo ago A 70 tokens original MIT

suprsend-cli

11924

suprsend/cli

Skill Claude CodeCodex

SuprSend CLI tool for managing SuprSend account and resources from the command line — workspaces, workflows, templates, categories, events, schemas, and translations. Use ONLY when the user wants the agent to RUN a suprsend ... command (e.g. "push my template", "pull all workflows", "sync staging to prod", "generate…

not rated 12 2mo ago A 192 tokens original MIT

zimage-generation

11925

Toolsai/Free-Zimage-Skills

Skill Claude CodeCodex

Generate high-quality images using ModelScope's Z-Image API. Use this skill when the user wants to generate images using the specific Z-Image model or ModelScope API they provided. Trigger words: 'Zimage', 'ModelScope', 'generate zimage'.

not rated 12 8mo ago A 57 tokens

crystal-kb

11927

memorycrystal/memorycrystal

Skill Claude CodeCodex

Create, import, enumerate, maintain, and share Memory Crystal knowledge bases. Use when importing reference material, syncing a corpus, cleaning or auditing a KB, or managing which agents can read a KB.

not rated 12 21d ago A 45 tokens original MIT

bagisto/agent-skills

Skill Claude CodeCodex

Use when writing, changing or debugging a Bagisto end-to-end test — deciding what to cover, Playwright specs, page objects, locators, assertions, ACL role coverage, fixtures, test data, admin-versus-storefront coverage, a regression test, or a failing E2E run. Trigger phrases include "playwright", "e2e", "end to end"…

not rated 12 changed 8d ago A 114 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: