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.
Ask OpenClaw to answer from a defined set of documents with traceable evidence.
Specify a repeatable task's schedule, inputs, output, and failure handling before scheduling it.
Define a browser research question with source quality, freshness, and evidence requirements.
Classify supplied documents into a reviewable routing plan without moving or exposing files.
Ask OpenClaw to inventory skills and instruction files while protecting private configuration.
Document a proposed integration's data needs, actions, credentials, and review boundaries.
Go from a fuzzy idea to a practical build plan with milestones and clear acceptance criteria.
Make a draft clearer and tighter while preserving its meaning and personality.
Connect a product’s value to a specific audience and write a clear first-screen message.
Explore a business idea’s assumptions, alternatives, and cheapest useful validation steps.
Turn an open question into a bounded research plan with credible sources and decision criteria.
Give a design project a clear purpose, audience, scope, and way to judge the result.
Build a realistic weekly plan around capacity, priorities, and existing commitments.
Find missing values, inconsistent formats, duplicates, and questions that could invalidate results.
Build a learning path that connects fundamentals, examples, and practice.
Turn a responsibility into a specific, truthful accomplishment using evidence you provide.
Explore distinct creative directions, then develop the strongest ideas into something usable.
Plan practical meals using your ingredients, time, preferences, and leftovers.
Investigate a reproducible bug with hypotheses, a minimal fix, and a focused regression check.
Get a focused review of correctness, maintainability, and edge cases, grounded in your code.
Map a product workflow into predictable endpoints, validation rules, and error responses.
Choose meaningful tests around a feature’s actual risks and expected behavior.
Build a useful map of a repository and identify where a specific change belongs.
Turn scattered notes into an email with a clear purpose, useful context, and a specific next step.
Build a useful article structure around a reader’s real question, with room for evidence.
Explain a technical passage in everyday language without flattening important distinctions.
Get editorial feedback that separates structural issues from sentence-level polish.
Condense a longer document into decisions, evidence, implications, and next steps.
Plan a month of useful content connected to audience needs and a realistic production schedule.
Review whether a page answers the query people actually bring to it.
Create a short onboarding sequence that helps new subscribers reach a useful first result.
Prioritize reachable audiences and concrete launch actions without an oversized campaign.
Adapt an existing piece into distinct social posts that each stand on their own.
Put a project’s purpose, audience, offer, and operating assumptions on one clear page.
Make a decision matrix that exposes real tradeoffs and missing information.
Write neutral interview questions that reveal past behavior and concrete needs.
Trace a customer’s path from first need to repeat use, including friction and unanswered questions.
Turn a recurring process into a clear checklist with ownership and exception handling.
Combine supplied sources while keeping evidence, disagreement, and uncertainty visible.
Evaluate how well a supplied argument is supported and what would strengthen it.
Organize supplied papers into themes, methods, findings, and research gaps.
Create clear, neutral questions that produce data you can actually use.
Translate evidence into practical options with traceable reasoning and uncertainty.
Find confusing steps, missing states, and opportunities to make a task easier.
Write labels, hints, and error messages that help people complete a task.
Review supplied markup or descriptions for practical accessibility issues and fixes.
Define a coherent palette, type scale, spacing, and component rules for a specific product.
Create realistic tasks and neutral prompts to learn where an interface confuses people.
Extract decisions, open questions, and next steps without inventing ownership or deadlines.
Find a manageable first step and a sequence of concrete actions.
Transfer context, current state, decisions, and next actions to another person.
Organize notes around retrieval and reuse rather than endless collecting.
Decide what to do, defer, or stop using explicit criteria and realistic capacity.
Match a chart to the question, data types, and comparison people need to make.
Understand a formula’s inputs, intermediate steps, assumptions, and possible failure cases.
Check a query’s joins, aggregation, null handling, and expected row counts.
Write a concise performance narrative that separates changes, explanations, and next steps.
Define a measurable hypothesis, comparison, and decision rule before collecting results.
See the same idea explained for a beginner, a practical learner, and a more technical reader.
Turn a deadline and a syllabus into a realistic practice and review schedule.
Generate questions that test understanding, application, and common misconceptions.
Design an engaging lesson with a clear objective, realistic timing, and checks for understanding.
Use a tutor-style conversation that gives hints, checks your reasoning, and lets you do the work.
Practice questions grounded in a role, with feedback on evidence and clarity.
Connect your real experience to a role with a concise letter that sounds like a person.
Prepare a focused agenda around progress, blockers, feedback, and support.
Write specific feedback requests that produce actionable observations.
Organize accomplishments, evidence, lessons, and next goals without exaggeration.
Build a character with motivations, contradictions, relationships, and room to change.
Turn a premise into a focused narrative with stakes, turning points, and an earned ending.
Generate naming directions tied to an audience and identity, with a practical shortlist.
Plan a short video around a useful takeaway, strong sequence, and realistic production needs.
Describe a visual direction clearly enough to collect references or brief a designer.
Organize your supplied travel ideas into an itinerary with room to rest and adapt.
Break a practical home organization project into manageable, reversible steps.
Choose between supplied products based on your needs, total cost, and tradeoffs.
Organize a welcoming event with a realistic schedule, clear roles, and practical contingencies.
Turn a frustrating situation into a calm message with facts and a practical request.
Give OpenClaw a bounded task with explicit sources, outputs, and approval boundaries.
Specify a coding task with repository context, acceptance criteria, and a verifiable finish line.
Structure a document-analysis request for Claude around evidence and traceable conclusions.
Keep a Cursor edit focused on one behavior with clear boundaries and a regression check.
Give ChatGPT useful background, a specific goal, and an output format in one tidy prompt.
Ask Gemini to compare supplied material while keeping evidence and assumptions visible.
Save a resource with its bookmark button. It stays in this browser.
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.