Agent skills

The moves that held up, installable.

The installable layer beneath the principles. Each skill is a real artifact — a CLAUDE.md rule, slash command, SKILL.md, or prompt — copy it straight into your CLAUDE.md, or copy a ready prompt that tells your agent to install it.

1
Pick a skillby the problem you have
2
Copy the artifactor the agent prompt
3
Paste into your agentinstalled — and it runs
14 skills · bilingual
Pillar

A principle you have to remember is a principle you'll forget

The field handbook: turn each lesson into something installable — so the right thing happens without waiting on your memory

View
01
CLAUDE.md rule

Verify Before You Call It Done

A forcing function so the agent proves a fix instead of claiming it.

View
02
CLAUDE.md rule

Plan First, Then Code

A forcing function that makes the agent show its approach — and stop — before touching code.

View
03
CLAUDE.md rule

Map the Blast Radius Before You Edit

A forcing function that makes the agent trace who depends on a symbol before it changes it.

View
04
CLAUDE.md rule

If It's Deterministic, Don't Make It Guess

A forcing function that sends exact-answer work to a script instead of the model's reasoning.

View
05
Prompt

Diagnose From the Symptom, Not the Guess

A prompt that forces a real diagnosis before a single line of fix.

View
06
Prompt

Make It Argue Against Its Own Plan

A prompt that pressure-tests an approach before you commit a single line to it.

View
07
Slash command

Hand Off to Your Next Session

A slash command that turns a session into a note the next one can pick up cold.

View
08
SKILL.md

A Review That Doesn't Rubber-Stamp

A reusable Skill that reviews a change for real problems instead of approving it by reflex.

View
09
Prompt

Run to the gate, then stop — not step-by-step

A prompt that lets the agent run on its own but stop at the few places worth stopping — so you can let go without losing control.

View
10
CLAUDE.md rule

A CLAUDE.md skeleton — turn a description into operating law

A minimal frame to paste into CLAUDE.md that tells the agent what to default to, when to stop and ask, and where the danger is.

View
11
Prompt

The weekly review prompt — five minutes that turn experience into skill

Three questions a week to know whether you're getting better or just getting used to mediocre.

View
12
Prompt

Split the work into focused slices, each with clean context

A prompt that makes the agent break a big task into a few independent, checkable pieces — instead of cramming it all into one blind run.

View
13
Prompt

Is this even worth an agent — ask before you open the chat

A pre-flight prompt that makes the agent sanity-check whether the task is worth handing over, instead of plowing into work a one-liner could do.

View
14
Prompt

Probe with a small task before you trust it in a new domain

A prompt that makes the agent do one small slice and show how it thinks — before you hand over the whole task in a field it hasn't proven itself in.

View
The pack

Take all 14 skills at once

One markdown file with every rule, prompt and artifact in the handbook — paste it straight into your CLAUDE.md. Leave an email, download now.

c
The author

Each story here wraps a lesson paid for in full.

craftagentsomeone building and learning at once

What are you building with agents? Want to trade notes, push back, or build something together — drop a line.

58pieces12clustersVI·ENbilingual

Get new pieces by email

Field notes on working with AI agents — occasional, no spam.