Skip to content
Directory

Agent skills

Skills for AI coding agents, each with what it costs to load, how much of it is scripts and what it touches on your machine.

1,186 skills5 categories Measured from their files, refreshed weekly

How to read a skill

Tokens

What it costs to keep

Idle in context, in use when it runs, and up to with its linked files.

Model dependence

Scripts or instructions

Script-led, mixed or model-led: how much the model has to work out itself.

Touches

What it can reach

Shell, network, file writes, git and credentials, declared or detected.

Scores

Quality, security, repo health

Out of 100, each with what it is made of. Turn a card over to see them.

Showing 586 of 1186 skillsShell Network Writes Files Git Credentials Clear all
Model-led399 tokens in use

hunt-regressions

8,319

The discovery stage of regression-hunt: read a pinned change and trace it through callers to list possible regressions for later proof.

Skill
21idle
399in use
399up to
Tokens, counted offlineView skill
Model-led2,227 tokens in use

modern-cpp

8,319

Guides C++ code to C++20, C++23 and C++26 idioms and adds compiler hardening, hardened libc++ and sanitizers to cut vulnerability classes.

Skill
70idle
2,227in use
13,565up to
Tokens, counted offlineView skill
Model-led800 tokens in use

property-based-testing

8,319

Write, review and debug property-based tests across Hypothesis, fast-check, proptest and Echidna, with a catalog of properties and failure triage.

Skill
189idle
800in use
4,696up to
Tokens, counted offlineView skill
Model-led968 tokens in use

regression-hunt

8,319

The coordinator for regression campaigns: dispatch fresh agents through prepare, hunt, reproduce, replay, adjudicate and report, with sealed records.

Skill
27idle
968in use
968up to
Tokens, counted offlineView skill
Model-led380 tokens in use

replay-regression

8,319

Independently replay a regression proof of concept against freshly built before and after systems, and seal a record of whether the results agree.

Skill
21idle
380in use
380up to
Tokens, counted offlineView skill
Model-led1,344 tokens in use

Secure Workflow Guide

8,319

Guides a smart contract project through Trail of Bits' five-step secure development workflow, from a Slither scan to manual review areas.

Skill
101idle
1,344in use
3,916up to
Tokens, counted offlineView skill
Model-led2,874 tokens in use

Token Integration Analyzer

8,319

Analyzes ERC20 and ERC721 token implementations and the protocols that accept arbitrary tokens, including 24 known weird token behaviors.

Skill
109idle
2,874in use
7,076up to
Tokens, counted offlineView skill
Model-led259 tokens in use

remotion-captions

7,648

Transcribe audio with local Whisper, import SRT files and display word-timed captions in a Remotion video.

Skill
14idle
259in use
3,555up to
Tokens, counted offlineView skill
Model-led336 tokens in use

remotion-docs

7,648

Search the Remotion documentation and fetch any page as Markdown before implementing.

Skill
9idle
336in use
336up to
Tokens, counted offlineView skill
Model-led87 tokens in use

remotion-license

7,648

Find Remotion license information, FAQs, terms, and where to buy a license.

Skill
21idle
87in use
87up to
Tokens, counted offlineView skill
Model-led141 tokens in use

remotion-multimedia

7,648

Read audio duration, video duration and video dimensions with Mediabunny in the browser, Node.js or Bun.

Skill
11idle
141in use
1,318up to
Tokens, counted offlineView skill
Model-led223 tokens in use

remotion-saas

7,648

Architecture guidance for apps built on Remotion: templates, the Player, and server or Lambda rendering.

Skill
12idle
223in use
1,612up to
Tokens, counted offlineView skill
Model-led2,221 tokens in use

scenario-analyzer

7,430

Turns one news headline into an 18-month scenario report with base, bull and bear cases, sector impacts by order and a second-opinion review.

Skill
104idle
2,221in use
8,824up to
Tokens, counted offlineView skill
Mixed4,990 tokens in use

US Market Bubble Detector

7,430

Scores US market bubble risk from six measured indicators and a capped qualitative adjustment, then labels a phase from Normal to Critical with a stated risk budget.

Skill
96idle
4,990in use
19,603up to
Tokens, counted offlineView skill
Model-led2,168 tokens in use

US Stock Analysis

7,430

Researches a US stock ticker with web search and writes a quick overview, a fundamental or technical analysis, a full report or a side-by-side comparison of several stocks.

Skill
94idle
2,168in use
5,942up to
Tokens, counted offlineView skill
Model-led2,836 tokens in use

Market News Analyst

7,428

A six-step method that gathers the last 10 days of market news by web search, scores each event for impact, and writes a ranked Markdown report of how equities and commodities reacted.

Skill
115idle
2,836in use
18,081up to
Tokens, counted offlineView skill
Model-led546 tokens in use

Humanize

6,692

A slash command that sends Korean text or a file to the Humanize Korean pipeline and reports the status, changes and grade.

Skill
100idle
546in use
546up to
Tokens, counted offlineView skill
Model-led1,171 tokens in use

Humanize Korean for Copilot CLI

6,692

A single-call edition of Humanize Korean for GitHub Copilot CLI that detects, rewrites and self-checks AI-written Korean text in one pass.

Skill
286idle
1,171in use
1,171up to
Tokens, counted offlineView skill
Model-led605 tokens in use

Humanize Redo

6,692

A slash command that reruns the latest Korean humanizing result for one category, one paragraph or a different strength, up to three rounds.

Skill
97idle
605in use
605up to
Tokens, counted offlineView skill
Model-led2,390 tokens in use

Humanize Scan

6,692

A quick scout for Korean text: checks six AI tells that held up in testing, shows before and after counts, and says whether a full pass is worth it.

Skill
238idle
2,390in use
2,390up to
Tokens, counted offlineView skill
Model-led6,466 tokens in use

n8n Agents

6,686

A guide for designing n8n AI agents: which AI node to use, how to name tools, wire memory, force structured output and gate risky actions behind human review.

Skill
152idle
6,466in use
28,780up to
Tokens, counted offlineView skill
Model-led3,645 tokens in use

n8n Binary and Data

6,686

A guide to files in n8n: where bytes live, how to read and write them, how to stop transforms from dropping them, and how to pass files to agent tools and chat apps.

Skill
134idle
3,645in use
12,472up to
Tokens, counted offlineView skill
Model-led5,349 tokens in use

n8n Code JavaScript

6,686

A guide to writing JavaScript in n8n Code nodes: a gate that checks native nodes first, data access, return format, webhook body, sandbox limits and loop pitfalls.

Skill
254idle
5,349in use
32,189up to
Tokens, counted offlineView skill
Model-led2,755 tokens in use

n8n Code Python

6,686

A guide to native Python in n8n 2.x Code nodes: the two input variables, blocked imports, denied builtins, accepted return shapes and how errors interact with onError.

Skill
226idle
2,755in use
5,186up to
Tokens, counted offlineView skill

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers