- Home
- Skills
- Prompt & Skill Engineering
- I've Got the Big Sad
I've Got the Big Sad
A playful Codex skill for concise, low-affect answers: less emotional padding, fewer unnecessary words.
Free
Works with the AI Agents you already use
I've Got the Big Sad
Example session with this skill installed
Illustrative example (not a captured model run):
Use $ive-got-the-big-sad to tell me the capital of France.
- Read your context and instructions
- Compiled the i ve got
Illustrative expected answer
The capital of France is Paris.
This is an example of the intended response style, not a benchmark or a recorded agent session.
Connects securely to your tools. The creator never sees your data.
About this skill
Give your AI the Big Sad. Not a clinical condition: just fewer paragraphs of verbal bubble wrap.
This free toy skill leads with the answer, removes redundant greetings and praise, uses direct wording, and states uncertainty plainly. Accuracy, requested detail, citations, and safety take priority over brevity.
Designed for Codex and explicitly invoked with $ive-got-the-big-sad. The included Codex metadata disables implicit invocation. Mentioning sadness or mental-health concerns should not activate it automatically.
Includes the SKILL.md response contract, Codex interface metadata, mental-health safety override, and MIT license. No executable scripts, external service credentials, or dependencies are needed for the skill itself.
This is a humorous prompt-engineering experiment, not a tool to diagnose, simulate, or treat depression. Token savings vary and are not guaranteed. The repository's illustrative evaluation fixture is not a live-model performance claim.
Open source: https://github.com/rastagan-git/ive-got-the-big-sad
Toy prompt-engineering project. Token savings and response quality vary; no live-model reduction percentage is guaranteed. Designed for explicit Codex invocation; other agents are not independently verified. Not a mental-health diagnosis or treatment tool.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Permissions
Reads the bundled references/mental-health-safety.md when sensitive mental-health topics arise. No shell execution, file writes, environment-variable access, or external account connection is required by the skill itself. Any tools used for an underlying user task remain subject to the host agent permissions.