agent-skills skills

41,107 tagged agent-skills, measured the same way as everything else here.

Browse within: agentic-ai 457agents 255coding-agents 215ai-skills 188azure 167foundry 167sdk 167agent-plugins 163ai-coding-agent 159claude-plugin 158anthropic-claude 137claude-ai 137geo 129chatgpt 127

inner-life

1081

DKistenev/agent-inner-life

Skill Claude CodeCodex

Keeps a dated record of how an agent's work has been going — an evening journal, free thinking at night, and a way to read it back. Use when asked to run the inner-life evening or night routine, to note something in state, or to recall how a stretch went. Writes under inner-life/ and replaces a short summary in native…

not rated 13 23d ago A 83 tokens original MIT

call-matt

1082

KoukkuAi/call-matt

Skill Claude CodeCodex

Orchestrator and router for Matt Pocock's open-source agent skills (github.com/mattpocock/skills). Use whenever the user invokes /call-matt, asks "which skill should I use", feels stuck about what to do next in a coding project, or describes a situation that maps to one of the toolkit's skills (vague plan, messy…

not rated 13 3mo ago A 122 tokens original MIT

pariyar07/kybernetes

Skill Claude CodeCodex

Design a bounded execution contract using dynamically generated independent lenses when decision consequence and unresolved uncertainty justify architecture work.

not rated 13 1mo ago A 29 tokens original MIT

deep-research

1084

Orkas-AI/Orkas-Awesome-AgentSkills

Skill Claude CodeCodex

Guide-type skill for rigorous, transparent research. Use it to investigate a complex topic, collect and evaluate evidence, resolve contradictions when possible, and produce a cited research report.

not rated 13 2mo ago A 3 tokens original MIT

sondar

1085

geekjourneyx/sondar

Skill Claude CodeCodex

Use whenever the user asks to monitor AI builder signals, GitHub AI projects, model/app launch opportunities, hot keywords, PMF signals, commercial trend detection, or daily AI radar workflows. Sondar converts early signals into STRIKE/WATCH/IGNORE/KILL decisions with evidence, owner, deadline, metric, and commercial…

not rated 13 19d ago A 79 tokens AGPL-3.0

Neeeophytee/ai-watermarks-reality-check

Skill Codex

Compare an original asset with resized, converted, uploaded, or downloaded derivatives and produce a JSON, Markdown, or HTML provenance-survival report. Use when testing whether a CMS, image optimizer, social network, editor, screenshot, watermark-removal tool, or publishing workflow preserves Content Credentials.

not rated 13 1mo ago A 64 tokens AGPL-3.0

thesis-reviewer

1087

Agents365-ai/thesis-reviewer

Skill Claude Code

A thesis-reviewing guide for master's and doctoral research papers across different fields. It recognizes requests in Chinese and English and uses field-specific review guidance where available.

not rated 13 4mo ago A 143 tokens

agent-native-design

1088

Agents365-ai/agent-native-design

Skill Codex

Use when designing, reviewing, or refactoring a CLI that must serve AI agents alongside humans, or when converting an API or SDK into an agent-usable CLI interface.

not rated 13 changed 9d ago A 38 tokens original MIT

fact-driven-batch

1089

context4ai/agent-graph

Skill Claude CodeCodex

Process a host-owned batch through a static Agent Graph.

not rated 13 +1 7d ago A 16 tokens original MIT

forge-fupan

1091

yike-gunshi/forge-skills

Skill Codex

A Chinese-language engineering workflow for managing project engineering documents and implementing code changes. It includes worktree isolation, TDD, task waves, testing, verification gates, and separate commits.

not rated 13 1mo ago A 118 tokens original MIT

md2idx-read

1092

oubakiou/md2idx

Skill Claude CodeCodex

Read a large Markdown file efficiently using md2idx: first fetch the numbered index (table of contents), then retrieve only the sections relevant to the current task — instead of loading the entire file into context. Use this skill whenever asked to read, analyze, summarize, or answer questions about a Markdown file…

not rated 13 +1 1mo ago A 161 tokens original MIT

douyin-creator-insight

1093

tars1230/douyin-creator-insight

Skill Claude CodeCodex

A research tool for studying publicly accessible Douyin creators. Douyin is a Chinese short-video platform; the tool examines video topics, interaction patterns, and representative content, then produces HTML, Markdown, or JSON reports.

not rated 13 1mo ago A 68 tokens original MIT

word-deep-dive

1094

hwl668/Scientific-learning-skills-

Skill Claude CodeCodex

An English vocabulary study aid that explains a word’s meanings, usage, differences from similar words, and exam relevance. It can also save selected words and schedule them for spaced review, meaning review at increasing intervals.

not rated 13 1mo ago A 95 tokens original MIT

fable-harness

1095

AAO-SH/fable-harness

Skill Claude CodeCodex

Use when installing or updating a project-local Fable Harness for Codex, Claude Code, or compatible agent workflows; when a workspace needs AGENTS.md or CLAUDE.md boot instructions, .codex/.claude/.agents templates, decision traces, semantic notes, native loop governance, loop state, event logs, checklist evidence…

not rated 13 2mo ago A 87 tokens original MIT

abaqus-sim

1096

svd-ai-lab/sim-plugin-abaqus

Skill Claude CodeCodex

Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to automate, inspect, run, or debug Abaqus through sim-cli. Supports Abaqus/CAE noGUI workflows, batch jobs, model inspection, ODB diagnostics, bounded execution, artifact reporting, and troubleshooting. Requires a user-owned…

not rated 13 2mo ago A 77 tokens original Apache-2.0

odoo-dev-superskill

1097

CodeForUsers/odoo-dev-superskill

Skill Claude CodeCodex

Expert guide for creating, reviewing, refactoring, and migrating Odoo modules in versions 16.0, 17.0, 18.0, and 19.0, strictly following OCA Guidelines. Use it when the user mentions: creating an Odoo module, inheriting models or views, writing security (ACL/ir.rule), migrating between Odoo versions (e.g., 16 to 18…

not rated 13 +1 2mo ago A 181 tokens original MIT

gongyijie85/mattpocock-skills-dsh

Skill Claude Code

Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

not rated 13 2d ago A 44 tokens copy · 95% MIT

repo-to-skill

1099

shuyhere/repo-to-skill

Skill Claude CodeCodex

Generate an agent skill from a GitHub open-source repository. Use when asked to create a skill from a repo URL, turn a GitHub project into a usable skill, or generate skill files for a CLI/library/framework. Triggers on phrases like "create a skill from this repo", "make a skill for vllm", "turn this GitHub project…

not rated 13 +1 6mo ago A 123 tokens original MIT

tufte-viz

1100

pjsny/tufte-viz

Skill Claude CodeCodex

Ideate and critique data visualizations using Edward Tufte's principles from "The Visual Display of Quantitative Information." Use this skill when: (1) Designing new data visualizations or charts (2) Critiquing or improving existing visualizations (3) Reviewing dashboards or reports for graphical integrity (4)…

not rated 13 +2 3mo ago A 129 tokens original MIT

Jaimo-so/personal-ip-illustrations

Skill Claude CodeCodex

A Chinese-language image-creation skill for turning an article's key idea, process, or metaphor into hand-drawn illustrations. It uses a consistent brown-haired, round-glasses character on a mostly white 16:9 canvas.

not rated 13 26d ago A 140 tokens original MIT

orchardcore-admin

1102

CrestApps/CrestApps.AgentSkills

Skill Claude CodeCodex

Guidance for working with the Orchard Core admin panel, including admin controllers, menu registration, dashboard widgets, admin theme customization, settings pages, and admin-specific shapes and zones. Use this skill when requests mention Orchard Core Admin Panel, TheAdmin Theme, Admin Controllers, Admin Route URL…

not rated 13 2d ago A SkillSpector: pass 185 tokens original MIT

emblem-ai

1103

EmblemCompany/Agent-skills

Skill Claude Code

One-shot user management for apps, multi-chain wallet authentication, an AI-powered assistant, and AI app introspection. Use when the user wants to let website users sign in with wallets, email/password, or social login and give each user a wallet-enabled account, then embed EmblemAI chat surfaces, connect plugins, or…

not rated 12 4mo ago A Socket: passSnyk: warn 100 tokens original MIT

weread-skills

1104

gandli/weread-skills

Skill Claude CodeCodex

A WeRead assistant for 微信读书, a Chinese digital reading platform.

not rated 12 23d ago A 36 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: