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.

openclaw

14761

udjin-labs/mnemostack

Skill Claude CodeCodex

Wire mnemostack into OpenClaw as an MCP server, alongside the native OpenClaw memory tools (memorysearch / memoryget). The two coexist — mnemostack handles the hybrid pipeline (Vector + BM25 + Memgraph + Temporal + 8-stage rerank), while the native tools do fast file-scoped retrieval.

not rated 7 2d ago A 0 tokens original Apache-2.0

claude-api

14762

KUP-IP/the-bridge

Skill Claude CodeCodex

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…

not rated 7 yesterday A 193 tokens

steno

14763

AkashAi7/stenographer-mode

Skill Claude CodeCodex

Shorthand-first communication mode for token reduction w/ better readability than caveman mode. Compresses resps through consistent abbreviations, symbolic links, and dropped filler while keeping technical precision and exact literals. Use when user says "steno mode", "shorthand mode", "compressed resps", "token…

not rated 7 1mo ago A 88 tokens original MIT

gsDesign

14764

keaven/gsDesignSkills

Skill Codex

Guide users through classical group sequential trial design using the gsDesign R package. Use this skill when the user asks about: group sequential boundaries, spending functions (sfLDOF, sfHSD, sfPoints), sample size for time-to-event or binomial trials, gsDesign objects, plotting group sequential bounds, gsSurvPower…

not rated 7 2mo ago A 85 tokens

color-system

14765

yuqizhang1228-blip/AI-color-system

Skill Claude CodeCodex

A brand-based UI colour system covering brand, background, text, and semantic colours, with light and dark modes, accessibility checks, and platform token names.

not rated 7 3mo ago A 136 tokens

deepresearch

14766

trotsky1997/My-Claude-Agent-Skills

Skill Claude CodeCodex

Comprehensive DeepResearch methodology for conducting rigorous, traceable research projects with quality gates, structured analysis, and decision-ready deliverables. Use when (1) Conducting deep research projects requiring evidence-based analysis, (2) Managing research progress with quality gates and artifacts, (3)…

not rated 7 8mo ago A 134 tokens

liaocao-figmaX

14767

liaocaoxuezhe/FigmaX

Skill Claude CodeCodex

A workflow for creating visual designs in the Figma desktop app through a coding agent. Figma is a design tool; the workflow can read design context and write design elements to its canvas.

not rated 7 4mo ago A 187 tokens

notebooklm

14768

LuisSambrano/antigravity-config

Skill Claude CodeCodex

Sistema universal para crear y mantener notebooks de NotebookLM como Memoria Viva de Proyecto. Úsalo cuando el usuario describe una idea de proyecto, pide crear un "libro", registrar decisiones de arquitectura/diseño o auditar la consistencia del proyecto. Actúa como el cerebro central que cualquier IA puede leer…

not rated 7 3mo ago A 101 tokens

obsidian-plugin-release

14769

ssoriche/dotfiles

Skill Claude Code

Guide for setting up and managing the release process for Obsidian plugins. Use when adding a release workflow to a new plugin, debugging release issues, or understanding the standardized Makefile/version-bump/GitHub Actions pattern used across ssoriche's Obsidian plugin repos.

not rated 7 22d ago A 61 tokens

add-skill-source

14770

keska-labs/enterprise-skills

Skill Claude CodeCursor

Adds a third skill source mode beside GitHub repo and custom registry for Agent Skill Sync. Use when extending SourceMode, ConfigService, SyncEngine branching, or marketplace settings schema.

not rated 7 1mo ago A 41 tokens original MIT

create-profile

14771

merencia/pairwith

Skill Claude CodeCodex

Generate a community AI style profile for pairwith — a respectful homage inspired by publicly observable aspects of a developer's technical work. Follows TEMPLATE.md, PROFILEPOLICY.md, and DISCLAIMER.md.

not rated 7 5mo ago A 41 tokens original MIT

template-skill

14772

caoguanjie/codeplugins

Skill Claude Code

Replace with description of the skill and when Claude should use it.

not rated 7 7mo ago A 17 tokens

unsafe-installer

14773

buzzicra/skillguard

Skill Claude CodeCodex

Intentionally unsafe SkillGuard demo fixture.

not rated 7 3mo ago C 12 tokens original MIT

vendure

14774

niko91i/Skills-Vendure

Skill Claude CodeCodex

Assiste au développement avec le framework e-commerce Vendure pour Node.js. Gère le commerce headless, les APIs GraphQL, la gestion des commandes, les catalogues produits, l'intégration des paiements et le développement TypeScript e-commerce. Utiliser lors du travail sur des projets Vendure, la création de plugins, ou…

not rated 7 8mo ago A 78 tokens

memory

14775

g1itchbot8888-del/agent-memory

Skill Claude CodeCodex

Complete memory system for OpenClaw agents. Combines behavioral protocol (when to save) + auto-capture (heartbeat-enforced) + semantic search (recall) + maintenance (consolidation). Use for persistent memory, context recovery, answering "what did we discuss about X", and surviving context compaction. Includes…

not rated 7 7mo ago A 86 tokens original MIT

skill-audit

14776

simplybychris/skill-audit

Skill Claude CodeCodex

Audytuje bezpieczeństwo skilla, pluginu lub agenta Claude Code przed instalacją. Warstwa statyczna (heurystyki) plus subagent-audytor tylko do odczytu wykrywają prompt injection, kradzież sekretów, exfiltrację danych, obfuskację i persistence. Pozyskuje kod do izolowanego katalogu tymczasowego, nigdy bezpośrednio do…

not rated 7 3mo ago B 131 tokens original MIT

omg-payment

14777

chenmitchell/omg-payment-skill

Skill Claude CodeCodex

A natural-language guide for helping non-technical merchants in Taiwan connect to the OMG payment gateway, which handles online payments such as cards, ATM transfers, and convenience-store payments.

not rated 7 3mo ago A 190 tokens

safelint

14778

shelkesays/safelint

Skill Claude CodeCodex

Run safelint static analysis on the user's project and present Holzmann Power-of-Ten safety violations grouped by file. Supports any language registered with safelint (Python, JavaScript, TypeScript including TSX / AssemblyScript, Java, Rust, Go, PHP, C, and C++ today; more can be added). Use this for "safelint…

not rated 7 today B 129 tokens original MIT

sandy

14779

jamestelfer/sandy

Skill Claude CodeCodex

Run TypeScript scripts in sandboxed microVMs or Docker containers with AWS SDK access via IMDS. Use when investigating AWS resources, running read-only queries, or executing TypeScript automation that needs AWS credentials.

not rated 7 1mo ago A 45 tokens original Apache-2.0

opencli

14780

memorysaver/dotfiles

Skill Claude CodeCodex

Use OpenCLI to gather information from websites without login. Trigger when the user wants to fetch data from websites (news, finance, research papers, tech trends, Stack Overflow, Wikipedia, etc.) via CLI, needs structured web data in JSON/CSV/Markdown, mentions opencli, or wants to discover public APIs on any…

not rated 7 5d ago A SkillSpector: warn 92 tokens original MIT

email-sequence

14781

Nirusan/claude-config

Skill Claude CodeCodex

When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle…

not rated 7 5mo ago A 84 tokens

arch-schema

14782

URaux/archviber-plugin

Skill Claude Code

Internal knowledge about the architect.json data format used by ArchViber plugin. Auto-triggered when CC operates on .archviber/architect.json files.

not rated 7 5mo ago A 34 tokens

recursive-dep-trace

14783

gyy0592/claude-config

Skill Claude CodeCodex

Recursive first-principles static dependency tracing for a single code entry point, producing a real-time stream-of-consciousness trace markdown that embodies the AI's reading process as a call-stack of TODOs. Given one entry script (e.g. train.py, minimalgenerateimagev3.py, main.py), the AI reads the code…

not rated 7 4mo ago A 270 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: