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.

1,119 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 548 of 1119 skillsShell Writes Files Network Git Credentials Clear all
Model-led5,283 tokens in use

app-lifecycle

680

The detailed SaaS path from idea to production: eleven stages, each with its output and a done-when, grouped into phases the owner can try, with shape switches and owner decisions.

Skill
42idle
5,283in use
32,319up to
Tokens, counted offlineView skill
Model-led1,240 tokens in use

beachhead-segment

680

Choose the first customer segment to win by scoring candidates on burning pain, willingness to pay, winnable share and referral potential.

Skill
31idle
1,240in use
1,311up to
Tokens, counted offlineView skill
Model-led2,703 tokens in use

Code Review

680

Review code for correctness first, with performance and security as options, and report only defects that survived a check of the strongest counterargument.

Skill
36idle
2,703in use
6,240up to
Tokens, counted offlineView skill
Model-led859 tokens in use

competitor-analysis

680

Research up to five direct competitors and the substitutes people use, source every figure with a date, and recommend where to differentiate.

Skill
25idle
859in use
1,111up to
Tokens, counted offlineView skill
Model-led2,736 tokens in use

derive-tests

680

Turns documented intent into a test coverage map: which rules have tests today, which are proposed, and which gaps are left, ranked by what crossing them exposes.

Skill
32idle
2,736in use
2,914up to
Tokens, counted offlineView skill
Model-led1,408 tokens in use

document-app

680

Writes or refreshes an app's system docs from its code (architecture, flows, permissions, variables), or checks existing docs against the code and reports disagreements.

Skill
39idle
1,408in use
1,408up to
Tokens, counted offlineView skill
Model-led2,123 tokens in use

environments

680

Keep development and production apart in an AI-built app: named targets, separate keys, a variables doc and env schema, safe migrations, secret rotation, backups with restore drills.

Skill
43idle
2,123in use
16,382up to
Tokens, counted offlineView skill
Model-led2,382 tokens in use

Flight Deck

680

A status board for long agent work: STATUS.md, LOG.md and an owner page that survive compaction and show only what needs you.

Skill
42idle
2,382in use
15,590up to
Tokens, counted offlineView skill
Model-led1,198 tokens in use

growth-loops

680

Compare the five growth loop types, choose the one that fits your product, and get its conversion chain and a first measurable test.

Skill
27idle
1,198in use
1,198up to
Tokens, counted offlineView skill
Model-led798 tokens in use

intended-vs-implemented

680

A review method that compares AI-built code with its recorded intent to find unenforced permissions, public cron endpoints and private data leaking onto public surfaces.

Skill
37idle
798in use
798up to
Tokens, counted offlineView skill
Model-led1,812 tokens in use

legal-pages

680

Draft privacy, terms and cookie pages from what the code collects, stores and sends, hold them to the code with a test, and leave facts and approval to the owner.

Skill
47idle
1,812in use
1,947up to
Tokens, counted offlineView skill
Model-led568 tokens in use

market-segments

680

Identify three to five distinct customer segments and evaluate each one's jobs to be done, pains, product fit and competing alternatives.

Skill
28idle
568in use
568up to
Tokens, counted offlineView skill
Model-led3,188 tokens in use

propose

680

Research an idea, then propose what to build in one HTML page with sourced claims, key screens, open decisions and a recommendation.

Skill
41idle
3,188in use
5,311up to
Tokens, counted offlineView skill
Model-led5,758 tokens in use

release-gate

680

How a change ships: the full gate, an owner preview, a go/no-go with evidence, migrations before promotion, proof that the reviewed build is serving, and rollback.

Skill
48idle
5,758in use
22,169up to
Tokens, counted offlineView skill
Model-led1,268 tokens in use

Retro

680

At the end of a session, list the friction, find its cause and build a checked fix into your agent setup, or conclude that no change is warranted.

Skill
69idle
1,268in use
1,417up to
Tokens, counted offlineView skill
Model-led2,722 tokens in use

saas-authorization

680

Decide who may do what across every tenant boundary of a multi-tenant SaaS: workspace model, three access functions, permissions versus entitlements, and thirteen threat classes.

Skill
44idle
2,722in use
15,009up to
Tokens, counted offlineView skill
Model-led2,475 tokens in use

shipping-artifacts

680

Defines the small set of documents that make an AI-built app reviewable: architecture, flows, permissions, variables, a coverage map and conditional docs for email, cron, SEO and agents.

Skill
36idle
2,475in use
2,573up to
Tokens, counted offlineView skill
Model-led2,387 tokens in use

transactional-email

680

Send app email once and never lose it: an outbox written with the event, leased sending, settled retries, one-click unsubscribe and a discard address in development.

Skill
36idle
2,387in use
6,351up to
Tokens, counted offlineView skill
Model-led1,374 tokens in use

value-curve

680

Score your product and its alternatives on one segment's top needs plus price, and draw a value curve that shows where you must be far ahead.

Skill
31idle
1,374in use
1,483up to
Tokens, counted offlineView skill
Model-led1,132 tokens in use

value-proposition

680

Build a six-part value proposition for one customer segment (who, why, what before, how, what after, alternatives) and a statement ready for marketing.

Skill
32idle
1,132in use
1,132up 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