Build a claim-to-source evidence matrix
Map each claim to the supplied document passages and expose unsupported conclusions.
Browse reusable instructions for your AI tools. Copy and customize a prompt, or download a skill for a supported agent.

Map each claim to the supplied document passages and expose unsupported conclusions.
Explain where supplied reports disagree and which differences may come from scope or method.
Compare two supplied document versions for changes in obligations, scope, and meaning.
Derive a bounded style guide from supplied writing samples and show supporting examples.
Group interview observations into themes without erasing minority views or inventing quotes.
Find missing states, unclear acceptance criteria, and contradictory requirements in a supplied brief.
Improve labels and messages while preserving the actual behavior and available recovery paths.
Reorganize supplied onboarding material around prerequisites, steps, and verifiable completion.
Create explanations and practice questions bounded by a learner's goal and provided sources.
Group tickets by issue and urgency using explicit criteria and traceable ticket IDs.
Turn a feature request into scope, invariants, acceptance criteria, and concrete completion evidence.
Translate an issue report into a reproducible engineering task without inventing missing evidence.
Give Codex a bounded test failure with a behavior contract and limits on implementation changes.
Define a measurable performance question with workload, baseline, and comparison rules.
Draft migration requirements covering mixed versions, existing data, rollback, and validation.
Describe CLI behavior across arguments, streams, exit codes, and machine-readable output.
Frame a review around concrete failure modes, invariants, and affected behavior.
Create a concise repository guide using supplied structure and verified development commands.
Create fixture requirements that isolate behavior and include meaningful boundary cases.
Ask Codex to trace error propagation, cleanup, and caller-visible behavior.
Compare supplied calendar items for overlap and missing preparation time without changing events.
Turn selected messages into prioritized response drafts without sending or changing inbox state.
Describe event inputs, validation, deduplication, and intended actions before integration work.
Package a bounded objective, authorized sources, deliverable, and verification for another agent.
Try another platform, a broader search, or fewer filters.
Explore all resourcesResource formats: Prompts are ready to copy into a conversation. Skills install into the compatible agent shown on their page.
How it worksInclude the instructions, intended platforms, author, and license. Submissions are reviewed before publication.