DC CAP Enterprise AI  ·  Week 4

Write the method once.
Load it every time.

Any task you would teach a new teammate can be written down once and handed to Claude whenever it comes up. That written method is called a Skill, and building your first one is this week's work.

Week 4 of 8 About 30 min here, plus the tasks you run in Claude · at your pace Nothing to turn in
Week 4 · the setup

Here's how Week 4 goes

Week 3 gave one lane of your work a place to live; this week you write down a method you repeat, so Claude runs it the same way every time.

1Tell a place from a method, five quick calls
2See the four parts every Skill carries
3Write one, with Claude drafting from your example
4Share it, the first pattern your team inherits
Move 1 · the idea

Place or method?

A Project is the kitchen and a Skill is the recipe: one holds a lane of your work, the other holds a procedure you repeat.

Week 3 ended on the line: a Project is a place, a Skill is a method. Now you have both halves, and they stack. Sort these five; a couple are closer calls than they look.

Everything Claude should know about our GEAR UP program.

Place · a Project. Everything Claude should know about one program is a lane of work: background, standing instructions, knowledge files. Build it a home and every chat inside starts briefed.

How we write the weekly partner update, step by step.

Method · a Skill. "Step by step" is the tell here. A procedure you could walk a new teammate through belongs in a Skill, written once and loaded every Monday.

The board memo format with our headings and sign-off.

Method · a Skill. A format is a procedure for producing one kind of output: these headings, in this order, with this sign-off. Write it down once and Claude follows it every time.

Background docs for the fall report cycle.

Place · a Project. Reference material for one cycle of work sits in Project knowledge, where every conversation about the report can see it without you re-attaching anything.

Our checklist for turning event notes into a recap email.

Method · a Skill. A checklist is a Skill that's most of the way written. Add when to use it, one sample recap, and the guardrails, and it's done.

They stack: run a method inside a place and the window gets both.

Move 2 · the parts

Anatomy of a Skill

Write a Skill the way you'd train a new teammate: when to use it, what to do, one sample of good output, and what never happens.

TriggerWhen to use it: the moment this method applies
StepsWhat to do, in order, short enough to follow
ExampleOne worked sample of good output to match
GuardrailsWhat never happens, with the data-safety line first

Skills live with you: create one under Skills in your own Claude settings and Claude loads it when the task calls for it. The same four parts also work as a saved text block you paste in first; step 3 below shows where to keep it.

Every Skill ends with guardrails, and the first guardrail never changes: nothing that identifies a scholar or family enters the window. Wherever the method travels, the gate travels with it.
Move 3 · the doing

Write one

Claude writes the first draft of your Skill; you supply one finished example and then test what it hands back.

  1. Pick a task you've done three or more times the same way: the weekly update, the meeting summary, the recap email.
  2. Have Claude draft the Skill from your work, using the prompt below. You supply one raw input and the finished version you made from it.
  3. Save it where it lives: under Skills in your own Claude settings, or in a doc titled "Skill · [task name]" that you paste in at the start of each run.
  4. Test the draft on fresh input the Skill has never seen.
  5. Tighten the one step that came out wrong. It's usually something you do on autopilot and never thought to name.
  6. Run it once more. A method that works twice in a row is ready to share. (Once your team relies on it, the regression check keeps every later edit honest.)
The prompt that drafts your Skill

Claude writes a better method from one worked example than from any description of the task.

Watch how I do this task, then write the instructions you'd give yourself to repeat it: when to use, steps, one example, guardrails. Here's my input and my finished version: [paste both]
Watch a Skill run

This one turns event notes into a recap email. Fresh notes go in; the house format comes out. The event details below are invented for the demo.

You[Skill loaded: event recap email] Notes from yesterday's fall welcome session at a partner campus: about 30 scholars attended, two coaches ran the room, the financial aid office joined for the last half hour, and three scholars asked about DCTAG paperwork with no answer on hand. Run the recap.
ClaudeSubject: Fall welcome session recap and one follow-up

Team: about 30 scholars came out for yesterday's welcome session at our partner campus, and the financial aid office joined for the back half. One follow-up before Friday: three scholars asked about DCTAG paperwork and we owe them a clear answer. Full notes are in the shared folder.

[Your name]

New notes went in and the recap came out on format, because you wrote the format down once.

Move 4 · the payoff

Why DC CAP cares

One written method pays off twice: once on your own plate, and again the day a teammate loads it.

FY27 · DC CAP's goal

Brand content, from everyone

DC CAP set an FY27 goal: every staff member produces external brand content independently, using DC CAP templates plus AI. A Skill that carries the template is how you get there; write it once and the format shows up right every time.

Your team · the build weeks open

The first pattern your team inherits

A method in your head helps you; a method written down helps whoever loads it next. Share yours with a teammate this week, or bring it to office hours. We are stronger when learning together.

Your win

What you can do now

Writing a method clearly enough to hand off is Description and Delegation in one move, and you just did both.

This is your own check that the week landed. It stays in your browser — nobody else sees it.

What's nextWeek 5 · Team context
Start Week 5 →
Optional

Under the hood

Skip it and lose nothing.  Three questions people usually ask about skills.

What actually loads when a Skill runs?

When a Skill triggers, the method enters the window: trigger, steps, example, guardrails. (At larger scales Claude keeps only a Skill’s name and description in view and loads the body when the trigger fires; the effect is the same.) Claude reads it the way it reads everything else you load, which is why the writing matters: a vague step gets a vague result, and a missing guardrail never gets applied. A skill also takes space in the window, so keep it as short as the method allows.

Why does one example beat three sentences of description?

Week 0 covered the reason: Claude predicts from patterns, and an example is a pattern in its purest form. Three sentences describing your board memo ask Claude to imagine the result; one real memo shows the headings, the length, the sign-off, and a dozen things you'd never think to mention. When a Skill drifts off format, swap in a better example before you add more instructions.

When does a Skill go stale?

The moment the real process changes and the written method doesn't. A new template, a new approver, a new deadline: the Skill keeps producing last season's version, confidently, because Claude only sees what you wrote. The cure is the same curation habit you built for your Project in Week 3: give the Skill an owner, and reread it whenever the process it describes moves.