Skip to content
Let’s chat ↗
AGENT SKILL / THE TDP TOOLKIT

Use concise agent responses

A concise communication mode for iterative agent work. Use shorter responses while retaining the technical detail the task requires.

How TDP uses it

I turn it on when I want shorter, denser responses — saves tokens and reads faster. Best for iterative work where I don't need polished prose. Switch with /caveman or 'caveman mode'.

Usage note adapted from the original TDP skills collection. Activation and available tools depend on the agent host and installed version.

When to use this workflow

Use concise-response guidance when brief updates help someone keep track of ongoing work. Define the information that must survive compression: the result, relevant evidence, unresolved issues, and any action the reader needs to take. Brevity is useful only when the message remains understandable.

A worked example

For a UI review, a short update can state that the form works at the tested widths, identify the remaining error-state issue, and name the next check. It should not collapse into “done” when the work is still incomplete. Keep commands, file references, and important constraints precise even when the surrounding prose is short.

Decisions and common mistakes

Do not use compressed language for a decision that needs explanation. A nuanced design tradeoff, a failed check, or an unfamiliar setup may require several sentences. Match the detail to the reader’s task rather than treating the shortest output as the best one.

What to hand off

Review whether a teammate can act on the message without reconstructing the conversation. If key context was lost, restore it and adjust the instruction. Use this skill as a communication preference alongside the task workflow, not as a substitute for evidence or complete work.

Set up and try the skill

1. Start with one concrete task

Bring: A task where concise updates are useful and a list of details that must be preserved.

First task: Request shorter status updates while keeping commands, constraints, and unresolved questions explicit.

Choose a small task for “use concise agent responses.” Provide the relevant file, screen, or brief and define what a useful result should contain. Keep the original version available for comparison.

2. Install and verify the instructions

Run this command from the project where you want the skill available. Follow the installer’s host selection, then confirm the skill appears in that host. The command is the installation method documented by the TDP repository.

npx skills add thedesignproject/agent-skills -s caveman

Read the full skill instructions for prerequisites and supported tools. Installing a skill does not automatically connect Figma or grant access to external tools.

3. Apply it with your project context

Use the starter request below with the relevant inputs attached or referenced. Confirm that the host loaded the intended skill; a matching name alone is not evidence that its instructions were applied.

4. Review the result

Confirm the response still explains the result and any action you need to take; brevity is not a quality metric by itself.

Compare the output with the task’s acceptance criteria. Check factual claims, unsupported assumptions, and any changes to the interface. For code or design changes, review real states and behavior before treating the result as finished.

5. Keep what works

Save approved outputs with their source and ownership. Note which instructions helped, where the result needed correction, and what must be checked next time. Use the workflow below to connect this task to its next step.

A starter request

Adapt this example to your files, audience, and requirements.

Use concise responses for this task. Keep exact commands, important constraints, and uncertainty explicit; do not omit necessary explanations.

Completion checklist

  • The inputs and intended result are explicit.
  • Required files and tools are available in the chosen host.
  • The result has been reviewed against the actual task.
  • Limitations and follow-up checks are recorded.
CONNECT THE NEXT STEP

Use it in a workflow

Find, create, and improve skills

Any time, in parallel with the main flows.

  1. Use concise agent responses — Use concise responses for iteration while keeping necessary technical detail
  2. Find an agent skill — Before building anything custom, check if a skill already exists
  3. Create a Cursor skill — Package a repeated workflow as a SKILL.md (Cursor authoring)
  4. Write and verify shared skills — When the skill will be shared: most thorough variant — includes testing and verification