Agent Report Card (Pass/Fail Tests)
Builds simple pass/fail tests for an AI agent and scores a run. Why it matters: if you can't test it, you can't trust it.
- Output
- Text
- Input
- Text
Prompt directory
A prompt library for work, code, research, photos, and more. Every prompt shows what you need to provide, what it produces, and which AI models it was tested with.
Need reusable instructions with versions and install commands? Browse Claude Code skills, Cursor skills, or the full agent skills registry—and see how an AI package manager differs from copy-paste.
Browse by model: Gemini prompts, Claude prompts, and Nano Banana photo prompts. Or start with a use case: LinkedIn headshot prompts or product photography prompts.
Browse by series
Explore
10 prompts
Builds simple pass/fail tests for an AI agent and scores a run. Why it matters: if you can't test it, you can't trust it.
Clinician / therapist directory photo: trustworthy light, optional white coat, no fake credentials. Educational only — not medical advice. Why it matters: people judge a photo in a second.
Turn commit messages into a user-facing changelog in Rust with clear constraints and verification steps. Why it matters: clear steps stop silent bugs later.
Build RBAC matrix from roles and resources in Rust with clear constraints and verification steps. Why it matters: clear steps stop silent bugs later.
Writes an ADR for a tech decision in Rust with clear constraints and verification steps. Why it matters: clear steps stop silent bugs later.
Metrics, logs, traces checklist for a service in Rust with clear constraints and verification steps. Why it matters: clear steps stop silent bugs later.
Design idempotent event consumers in Rust with clear constraints and verification steps. Why it matters: clear steps stop silent bugs later.
Turn a selfie into a polished corporate LinkedIn headshot with tailored blazer, soft gray studio backdrop, and trustworthy eye contact. Why it matters: people judge a photo in a second.
Examines a system diagram for failure points, trust boundaries, scaling risks, and hidden dependencies. Why it matters: clear steps stop silent bugs later.
Reviews a landing-page screenshot and copy for unclear value, weak hierarchy, missing trust, and user friction. Why it matters: clear words get more clicks than fluff.