Prompt library

Task-based workflow templates, reusable controls, and curated prompt sets for reliable AI work.

Choose a task

Current published task coverage on this page: provided-material analysis, public-source research, code review, technical writing review, and scholarly review.

Analyze provided material
Use when the model must stay inside files, notes, logs, screenshots, or pasted excerpts you provide.
Open provided-material workflows →
Research with public sources
Use when the task depends on current or public information that must be checked and cited.
Open public-source workflows →
Review code
Use when you need an architecture review or an implementation check against official guidance.
Open code-review workflows →
Review technical writing
Use when draft technical content must be checked for claims, terminology, and evidence quality before publication.
Open technical-writing workflows →
Review scholarly sources
Use when the task is literature review, evidence synthesis, source comparison, gap mapping, annotated bibliography, or evidence tables.
Open scholarly-review workflows →

Workflow templates by task

Each section below maps one user task to the workflow templates that fit it.

Analyze provided material

Use these workflows when the model must stay inside files, notes, logs, screenshots, or pasted excerpts you provide.

Research with public sources

Use this workflow when the task depends on current or public information and the answer must include citations.

Review code

Use these workflows for architecture review or implementation review against official documentation.

Review technical writing

Use this workflow when publishable technical writing must be checked before output.

Review scholarly sources

Use these workflows for literature review, synthesis, comparison, gap mapping, annotated bibliography, or evidence tables.

Reusable controls

Use these to add one specific behavior without switching to a full workflow. The controls below are grouped by function so artifact-reading, source verification, and analysis-depth behaviors are not mixed together.

Artifact-reading controls

Use these when the model must fully read and cover user-provided artifacts before answering.

Control
Read all provided artifacts first
Require complete reading of user-provided text or files before answering.
Open file
Control
Scan all artifacts exhaustively
Require exhaustive artifact coverage, scan disclosure, and evidence pointers.
Open file

Verification and source controls

Use these when the task needs stronger evidence discipline or must reach outside the provided artifacts.

Control
Don’t confirm without evidence
Prevent automatic agreement with strong user assertions unless they are supported by evidence.
Open file
Control
Browse the web and cite sources
Require retrieval from current or public sources when correctness depends on external facts.
Open file

Analysis-depth controls

Use these when the answer needs an explicit analysis or compliance pass before the final output.

Control
Pause for analysis before answering
Add a short analysis pass before the final answer in higher-depth review or synthesis tasks.
Open file
Control
Add a structured analysis pass
Add a deeper analysis and compliance pass for review, debugging, or comparison tasks.
Open file

Policy-backed controls

Use these when you need a reusable ruleset or quality gate that can travel across workflows.

Supporting resources

Use these secondary paths when you need procedural guidance or policy constraints around prompt-based work.

Curated prompt sets

Use these when you need a recommended combination of prompts for a recurring professional task.

Prompt set
Code review — implementation vs official guidance
Use for code review when code or configuration changes must be checked against official framework, library, runtime, API, or platform guidance.
Prompt files (8) Hide prompt files