Prompts for Claude: explicit steps and quality bar

Templates for Claude that emphasize clear evaluation criteria and careful handling of missing info.

Last updated: November 9, 2026 · Markdown version

What changes with this model

Even if prompt structure is similar, each model has biases: some follow strict instructions better, some are more creative, and some need examples. These templates are designed to reduce ambiguity and improve consistency.

Recommendation: define output format (ideally with a checklist), add constraints, and if you need precision, use few-shot or require strict JSON.

Strict JSON Few-shot Hallucinations

Current models Promptea supports

Data taken from each provider’s official documentation; every entry shows the date it was last verified.

Claude Opus 5.5

default

Anthropic's recommended starting model (GA 2026-09-22): long-running agentic coding and knowledge work, 1M context. It always thinks — depth is set with effort (default medium), not with 'think carefully' in the prompt.

Context window: 1M tokens
Max output: 128K tokens
Input / output: text, image, pdf / text
Latency: balanced
Structured output: yes
Tool use / native search: yes / yes

How to prompt it: Give the goal, context, constraints, and what 'done' looks like in one complete request; drop 'think carefully' or 'double-check' lines — it always thinks and effort (default medium) is the control. For frontend work name the specific styles to avoid, and wrap pasted third-party text in tags so its instructions are treated as data.

Verified on September 24, 2026 · official source

Claude Fable 5.1

Anthropic's most capable widely released model (GA 2026-09-01), for the most demanding reasoning and long autonomous runs. Explain the intent and state boundaries — over-prescriptive step lists reduce its quality.

Context window: 1M tokens
Max output: 128K tokens
Input / output: text, image, pdf / text
Latency: slower (deliberate)
Structured output: yes
Tool use / native search: yes / yes

How to prompt it: Say who the result is for and what it enables, and state goals and constraints instead of steps. Mark what not to touch, ask for a final message that leads with the outcome, and keep your verification instructions. Effort starts at high; step down to medium/low where your evals hold.

Verified on September 24, 2026 · official source

Claude Sonnet 5.5

The Claude with the best combination of speed and intelligence (2026-09-28), for everyday coding, agent, and enterprise work; 1M context. Sonnet 5 prompts keep working; effort (default high) is the main control.

Context window: 1M tokens
Max output: 128K tokens
Input / output: text, image, pdf / text
Latency: fast
Structured output: yes
Tool use / native search: yes / yes

How to prompt it: Structure with XML tags, long documents at the top and the query at the end, and explicit success criteria. Control thinking with effort (default high; medium or low for chat and latency-sensitive work), not with lines like 'think less'. If you only want ideas or a plan, say so, and don't ask it to write out its reasoning: ask for a short explanation instead.

Verified on October 9, 2026 · official source

Claude Haiku 5.5

The fastest Claude (2026-10-07), for high-volume, latency-sensitive work: classification, extraction, routing, and subagents. 1M context and, for the first time on Haiku, effort levels (default medium).

Context window: 1M tokens
Max output: 128K tokens
Input / output: text, image, pdf / text
Latency: fast
Structured output: yes
Tool use / native search: yes / yes

How to prompt it: Keep prompts short and explicit: a clear task, an exact output format, and 1-2 examples. Effort replaces Haiku 4.5's budget_tokens: low for chat and high volume, medium (default) for most work, high for strict instruction following. If it can search, give it today's date.

Verified on October 9, 2026 · official source

Quick tips

Give a checklist of what must be covered.
Ask for a short plan before the final answer (when complex).
Add examples of desired tone/format when needed.

Templates

Rubric-based review

Review this code with a rubric.
Rubric: correctness, security, performance, readability, tests.
Return:
- prioritized issues (P0/P1/P2)
- concrete fixes (snippets)
- test checklist

Opens the analyzer with the prompt prefilled.

Open in Promptea

Long-context summarizer

Summarize the text below.
Output:
1) 10 bullets (key facts)
2) 5 decisions
3) 5 open questions
Text:
"""[paste]"""

Opens the analyzer with the prompt prefilled.

Open in Promptea

FAQ

Should I ask for chain-of-thought?

Ask for a brief plan or key steps instead of full hidden reasoning. It keeps output short and useful.