skill tutorial · scenario
Run a communication workshop with your agent
A communication session is three exercises strung together — one that shows how instructions drift, one that trains listening, one that closes it. Your agent can assemble the chain, do the minutes, and prep the measure. Here is the loop for the communication category specifically.
What lives in the communication drawer
Five folders, all pairs-based and printable: Blind Portrait and Draw What I Mean make instruction drift visible; Relay Brief exposes how a handover leaks down a line; The Listening Ladder climbs from the words to the feeling to the unsaid; Paper Tower records how a team plans under a clock. The agent reads each folder's SKILL.md fields to sequence them — it does not guess the timings.
Hand it the brief
Name the constraints, because those are the fields the agent matches on:
the brief
> communication workshop, 12 people, 90 minutes, no projector. > One exercise on how instructions drift, one on listening, > a quick measurable close. Propose the chain with agenda math.
Let it shortlist from the skills index
With a shell, the agent narrows the communication set itself:
communication candidates
curl -s https://workshopskill.com/en/skills.json | jq -r ' .skills[] | select(.category=="communication") | [.name, .duration_minutes, .setting] | @tsv' # pick a drift + a listening + a close whose minutes fit your window
Install the chain and print the kit
Once chosen, the set installs in one loop and the agent lays it into the day:
the chain in one pass
for s in blind-portrait the-listening-ladder exit-ticket; do curl -LO https://workshopskill.com/en/activities/$s/files/$s.zip unzip -o $s.zip done # agent then builds: agenda (durations sum), shopping list (props fields), # print order (one prop deck per pair), and the measure choice
For the measure, Blind Portrait ships a pair-level assessment.json — run it on paper, or take the formlm-cli lane for a generated delta report. The debrief questions are already in each folder; the agent prints them so you run the reflection, not improvise it.
keep going
questions
Which folders does a communication workshop draw on?
The communication category ships five: Blind Portrait, Draw What I Mean, Paper Tower, Relay Brief and The Listening Ladder. For a tight session a good chain is one that exposes how instructions drift (Blind Portrait or Draw What I Mean), one that trains receiving rather than sending (The Listening Ladder), and a quick close (an exit ticket). They are all pairs-based and run offline, so the agent can lay them into one agenda without a projector.
Can the agent pick the right ones or do I choose?
It shortlists, you decide. Give the brief — headcount, minutes, whether you want a measured before/after — and the agent filters the communication skills by their SKILL.md fields and proposes a set with the agenda math. It will not know that your team has already done Blind Portrait twice; you do. The agent removes the clerical work of matching and printing; the editorial call stays yours.
Does the pre/post measure need accounts or software?
Not necessarily. Every assessment-type communication folder ships a plain assessment.json you run on paper — no account, no login, the delta comes from two passes on one sheet. The online lane through formlm-cli exists if you want the report generated for you, but it is optional and it is the one place a human login enters the flow.