Pack 314 · AI · 18 items
LLM Specs, Evals & Costs Pack
16 prompts + 2 skills for LLM feature specs, evals and costs — real jobs from the week, with the steps, rules and output an expert would ask for.
€6one-time · 18 prompts & skills · ≈ €0.33 each
- Instant download
- Yours to keep
- Works in ChatGPT, Claude, Gemini
What's inside
Made for LLM feature specs, evals and costs
16 prompts + 2 skills- PromptAgent Loop Halt-Condition Design
Answers as an applied AI engineer who has shipped agents that completed millions of tool-calling iterations in production.
- PromptAI Experiment Readout
Answers as a data scientist reading out an LLM experiment to a non-technical audience.
- PromptAI Feature Spec
Answers as an AI PM scoping a new feature.
- PromptAI UX Writing Spec
Answers as a senior UX writer for AI products.
- PromptEmbedding Model Selector
Answers as an AI engineer who has benchmarked 20+ embedding models on real corpora.
- PromptEvals Harness Design for [Domain]
Answers as an AI engineer who has built evals suites that have caught 30+ production regressions before they shipped.
- PromptFeedback Loop Architecture
Answers as an applied AI engineer who has built 4+ feedback systems that actually improved models.
- PromptFunction Calling Spec
Answers as a senior AI engineer specialized in tool-use / function calling.
- PromptLLM Cost Dashboard Spec
Answers as an engineering manager who has built 3 LLM cost dashboards across companies.
- PromptLLM Failure-Mode Taxonomy
Answers as an AI safety researcher building the team's shared vocabulary for LLM bugs.
- PromptLLM Ops Runbook
Answers as an SRE specialized in LLM-powered services.
- PromptRegression Suite Design
Answers as an AI engineer who has watched 5+ companies regress quality silently when model versions rotated.
- PromptStructured Output Schema Designer
Answers as a senior backend engineer who has integrated 10+ LLM-generated outputs into downstream systems.
- PromptToken Budget Audit
Answers as an AI engineer focused on cost optimization.
- PromptTool-Use Cost Analysis
Answers as an AI ops engineer focused on agent cost.
- PromptVendor LLM Evaluation
Answers as an AI vendor selection lead.
- SkillLLM-as-Judge Rubric Designer
Designs reliable LLM-judge prompts with calibrated rubrics that minimize bias, leniency, and position effects.
- SkillPrompt Documentation & Spec Writer
Produces clear specs and docs for prompts so teams can understand, version, and maintain them like real software.
What you download
Everything comes in one pack (.zip) you keep. Start with 00-GIVE-THIS-TO-YOUR-AI.md: paste it into your AI and it knows which file to use for which job, and what to ask you first.
More for Developers · Product Management
llm-specs-evals-costs/ ├─ 00-GIVE-THIS-TO-YOUR-AI.md ├─ START-HERE.md ├─ TIPS-AND-FOLLOW-UPS.md ├─ AI-CHEAT-SHEET.md ├─ prompts/ │ ├─ 01-niche-ai-agent-loop-halt-design.md │ ├─ 02-niche-ai-ai-experiment-readout.md │ ├─ 03-niche-ai-ai-feature-spec.md │ ├─ 04-niche-ai-ai-ux-writing-spec.md │ ├─ 05-niche-ai-embedding-model-selector.md │ ├─ 06-niche-ai-evals-harness-design-domain.md │ ├─ 07-niche-ai-feedback-loop-architecture.md │ ├─ 08-niche-ai-function-calling-spec.md │ ├─ 09-niche-ai-cost-dashboard-spec.md │ ├─ 10-niche-ai-failure-mode-taxonomy.md │ ├─ 11-niche-ai-llm-ops-runbook.md │ ├─ 12-niche-ai-regression-suite-design.md │ ├─ 13-niche-ai-structured-output-schema.md │ ├─ 14-niche-ai-token-budget-audit.md │ ├─ 15-niche-ai-tool-use-cost-analysis.md │ └─ 16-niche-ai-vendor-llm-evaluation.md └─ skills/ ├─ llm-as-judge-rubric-designer/SKILL.md └─ prompt-documentation-spec-writer/SKILL.md
A look inside
**Role:** Applied AI engineer who has shipped agents that completed millions of tool-calling iterations in production. You believe most agents that ship to prod loop forever because their authors didn't specify halts. …
Questions
What do I get?
A .zip with 16 prompts + 2 skills for LLM feature specs, evals and costs: each prompt as a ready .md file, each skill as a SKILL.md folder, plus 00-GIVE-THIS-TO-YOUR-AI.md (a start file your AI reads first), START-HERE.md, TIPS-AND-FOLLOW-UPS.md (tips and the follow-up questions for every file) and the free AI cheat sheet.
How do I use it?
Open ChatGPT, Claude or Gemini and paste 00-GIVE-THIS-TO-YOUR-AI.md, or attach the folder. It asks a few questions about your work once, then picks the right file for each job and fills in the blanks.
Is it a subscription?
No. €6 once, and the files are yours to keep. Nothing renews.
How do I download it?
Right after checkout, on the confirmation page. Sign in later with the email you paid with and the download button waits for you on this page.
Why this price?
Packs are priced by what they hold: €0.50 a prompt and €1 a skill. This one is €6, about €0.33 an item.