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 589 of 1186 skillsShell Writes Files Network Git Clear all
Model-led1,259 tokens in use

WordPress Pro

12,471

WordPress themes, plugins, Gutenberg blocks, WooCommerce and REST API work, written to coding standards with security checks built in.

Skill
97idle
1,259in use
31,701up to
Tokens, counted offlineView skill
Model-led4,236 tokens in use

dbs-action

11,518

Diagnoses why you know what to do and still do not do it, using Adlerian psychology, and ends with one step you can finish today.

Skill
60idle
4,236in use
12,788up to
Tokens, counted offlineView skill
Model-led4,645 tokens in use

dbs-ai-check

11,518

Scans long articles, video scripts and posts for 22 signs of AI writing, quotes each hit with a severity, and rewrites only after asking what you meant.

Skill
114idle
4,645in use
4,645up to
Tokens, counted offlineView skill
Model-led4,438 tokens in use

dbs-benchmark

11,518

Finds a competitor worth copying with a five-filter test, maps how it gets and keeps customers, and sets a copying path that cuts out personal excuses.

Skill
64idle
4,438in use
8,488up to
Tokens, counted offlineView skill
Model-led3,493 tokens in use

dbs-chatroom

11,518

Runs a simulated panel of thinkers on your topic, with each expert speaking from their own framework and a judge summing up the clashes and next steps.

Skill
67idle
3,493in use
3,493up to
Tokens, counted offlineView skill
Model-led1,896 tokens in use

dbs-chatroom-austrian

11,518

A fixed three-seat chatroom where simulated Hayek and Mises answer your question from Austrian economics and Claude judges the exchange.

Skill
69idle
1,896in use
1,896up to
Tokens, counted offlineView skill
Model-led3,005 tokens in use

dbs-computer-use

11,518

One entry point for agent computer control on macOS, Windows and Linux: picks Cua Driver, agent-desktop or the built-in tool, works in the background and pauses before risky clicks.

Skill
202idle
3,005in use
8,114up to
Tokens, counted offlineView skill
Model-led3,599 tokens in use

dbs-content

11,518

Diagnoses how to build content around a topic you have already chosen: format, platform, wording, title, efficiency and audience gap, ending in a first step.

Skill
75idle
3,599in use
3,599up to
Tokens, counted offlineView skill
Model-led7,542 tokens in use

dbs-content-risk-check

11,518

Checks posts, scripts, captions and profiles sentence by sentence before publishing, telling machine-filter flags from real content problems and giving the smallest fix.

Skill
216idle
7,542in use
7,542up to
Tokens, counted offlineView skill
Model-led5,678 tokens in use

dbs-content-value

11,518

Judges whether a post or script keeps people past its opening, who it attracts, what they get from watching and what the traffic is worth to you.

Skill
74idle
5,678in use
11,336up to
Tokens, counted offlineView skill
Model-led4,215 tokens in use

dbs-decision

11,518

Builds a local folder of Markdown files for a long-running decision area, keeping facts, patterns, snapshots and open questions apart so later sessions pick up where you stopped.

Skill
78idle
4,215in use
4,215up to
Tokens, counted offlineView skill
Model-led3,647 tokens in use

dbs-deconstruct

11,518

Takes a fuzzy business word or sentence apart: how different people use it, where it is mixed up, and what it means once the jargon is removed.

Skill
74idle
3,647in use
9,475up to
Tokens, counted offlineView skill
Model-led4,723 tokens in use

dbs-diagnosis

11,518

Checks whether a business question holds up before answering it, or runs a seven-point checkup of a whole business, and ends with tomorrow's first action.

Skill
78idle
4,723in use
10,483up to
Tokens, counted offlineView skill
Model-led3,541 tokens in use

dbs-goal

11,518

Turns a vague wish into a goal an agent can act on and check, asking at most one question at a time and only when the answer changes the work.

Skill
95idle
3,541in use
3,541up to
Tokens, counted offlineView skill
Model-led3,970 tokens in use

dbs-good-question

11,518

Rewrites a fuzzy question into a problem brief an agent can reason about, and rates whether the task can be automated, from fully to not yet.

Skill
89idle
3,970in use
5,906up to
Tokens, counted offlineView skill
Model-led2,806 tokens in use

dbs-jtbd

11,518

Applies Jobs to Be Done to a customer, product or AI request: the progress the person wants, why now, how they choose, and what holds them back.

Skill
117idle
2,806in use
2,806up to
Tokens, counted offlineView skill
Model-led7,653 tokens in use

dbs-knowledge

11,518

Gives a local folder a navigation file and agent rules so your agent can find documents, file new ones, name the current version and check for broken paths.

Skill
87idle
7,653in use
7,653up to
Tokens, counted offlineView skill
Model-led5,398 tokens in use

dbs-learning

11,518

Turns a topic into a numbered series of study articles and reads the feedback you write at the end of each one to set the depth of the next.

Skill
75idle
5,398in use
5,398up to
Tokens, counted offlineView skill
Model-led6,925 tokens in use

dbs-plain-writing

11,518

Writes, rewrites or checks product, feature and update descriptions in the order of the facts, leaving out hooks, pain-point openers and inflated claims.

Skill
198idle
6,925in use
7,808up to
Tokens, counted offlineView skill
Model-led2,926 tokens in use

dbs-resonate

11,518

Finds where a written draft fails to reach its target audience, ties the diagnosis to the original sentences, and lists what to cut, trim and strengthen.

Skill
99idle
2,926in use
2,926up to
Tokens, counted offlineView skill
Model-led2,323 tokens in use

dbs-restore

11,518

Pulls the latest saved diagnosis from local storage and shows where you stopped, so a new chat can continue without retelling everything.

Skill
49idle
2,323in use
4,194up to
Tokens, counted offlineView skill
Model-led4,251 tokens in use

dbs-script-flow

11,518

Checks a short-video transcript for logic gaps, repeated points and lines that are hard to speak, and marks the spots where viewers are likely to swipe away.

Skill
78idle
4,251in use
4,251up to
Tokens, counted offlineView skill
Model-led1,910 tokens in use

dbs-speak-human

11,518

Rewrites Chinese messages meant for real people, such as WeChat chats, customer replies and agent answers, so they read like something a person would type.

Skill
204idle
1,910in use
4,895up to
Tokens, counted offlineView skill
Model-led3,559 tokens in use

dbs-spread

11,518

Explains why a piece of content moves its audience or gets shared, picking one communication theory and tying each claim to quoted text.

Skill
96idle
3,559in use
3,559up 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