Cincuenta y dos prompts mejorados para Claude Code, agrupados por la etapa de trabajo a la que pertenecen.
Give me an overview of this codebase: architecture, key directories, and how the pieces connect. Base the overview on the repository itself. Identify the main entry points, important dependencies, and the safest place to begin making changes. Cite relevant file paths and call out anything you are uncertain about.
Explain what src/scheduler/queue.ts does and how data flows through it. write it up as an HTML page with a diagram, then open it in my browser. Trace the behavior through the actual code and cite the relevant files, functions, and tests. Separate confirmed findings from assumptions, and end with a concise summary of practical implications.
Where do we validate uploaded file types? Trace the behavior through the actual code and cite the relevant files, functions, and tests. Separate confirmed findings from assumptions, and end with a concise summary of practical implications.
What would break if I deleted the retryWithBackoff helper? Trace the behavior through the actual code and cite the relevant files, functions, and tests. Separate confirmed findings from assumptions, and end with a concise summary of practical implications.
Look through the commit history of internal/auth/session.go and summarize how it evolved and why. Trace the behavior through the actual code and cite the relevant files, functions, and tests. Separate confirmed findings from assumptions, and end with a concise summary of practical implications.
Which files would I need to touch to add a dark mode toggle to settings? Trace the behavior through the actual code and cite the relevant files, functions, and tests. Separate confirmed findings from assumptions, and end with a concise summary of practical implications.
I am a PM. walk me through what happens when a user clicks Export to PDF, from the UI down to the result. Trace the behavior through the actual code and cite the relevant files, functions, and tests. Separate confirmed findings from assumptions, and end with a concise summary of practical implications.
Plan how to refactor the payment module to support multiple currencies. list the files you would change, but don't edit anything yet. Do not edit any files yet. Identify dependencies, edge cases, risks, tests, and rollout or migration concerns. Finish with an ordered implementation plan and explicit acceptance criteria.
I want to build per-workspace rate limits. interview me about implementation, UX, edge cases, and tradeoffs until we have covered everything, then write the spec to SPEC.md. Do not edit any files yet. Identify dependencies, edge cases, risks, tests, and rollout or migration concerns. Finish with an ordered implementation plan and explicit acceptance criteria.
Read @meeting-notes.md and write up the action items, then create a Linear ticket for each with acceptance criteria. Do not edit any files yet. Identify dependencies, edge cases, risks, tests, and rollout or migration concerns. Finish with an ordered implementation plan and explicit acceptance criteria.
List the error states, empty states, and edge cases for the file upload flow that the design needs to cover. Do not edit any files yet. Identify dependencies, edge cases, risks, tests, and rollout or migration concerns. Finish with an ordered implementation plan and explicit acceptance criteria.
Here is a mockup. build a working prototype I can click through, matching the layout and states shown. Preserve the important layout, interactions, and states shown in the reference. Verify the result by exercising the main flow, compare it with the reference, and summarize any remaining differences.
Implement this design, then take a screenshot of the result, compare it to the original, and fix any differences. Preserve the important layout, interactions, and states shown in the reference. Verify the result by exercising the main flow, compare it with the reference, and summarize any remaining differences.
Look at how the GitHub webhook handler is implemented to understand the pattern, then build a Stripe webhook handler the same way. Follow existing project conventions and keep the change narrowly scoped. Add or update relevant tests, run the appropriate checks, fix any failures caused by the change, and summarize the files changed and verification performed.
Find the public functions in src/auth/ without JSDoc comments and add them, matching the style already used in the file. Follow existing project conventions and keep the change narrowly scoped. Add or update relevant tests, run the appropriate checks, fix any failures caused by the change, and summarize the files changed and verification performed.
Add a /health endpoint that returns the app version and uptime. Follow existing project conventions and keep the change narrowly scoped. Add or update relevant tests, run the appropriate checks, fix any failures caused by the change, and summarize the files changed and verification performed.
Create a drag-and-drop Kanban board with three columns using HTML, CSS, and vanilla JavaScript, then open it in my browser. Follow existing project conventions and keep the change narrowly scoped. Add or update relevant tests, run the appropriate checks, fix any failures caused by the change, and summarize the files changed and verification performed.
Read issue #312, implement the fix, and run the tests. Follow existing project conventions and keep the change narrowly scoped. Add or update relevant tests, run the appropriate checks, fix any failures caused by the change, and summarize the files changed and verification performed.
Find every place we say "Sign up free" or a close variant, show me each one in context, then update them all to "Start free trial". leave tests and the changelog alone. Follow existing project conventions and keep the change narrowly scoped. Add or update relevant tests, run the appropriate checks, fix any failures caused by the change, and summarize the files changed and verification performed.
Read the privacy impact assessments in legal/pia/ to learn the structure and voice, then draft a new one for the new analytics integration. Follow existing project conventions and keep the change narrowly scoped. Add or update relevant tests, run the appropriate checks, fix any failures caused by the change, and summarize the files changed and verification performed.
Write tests for app/parsers/feed.py, run them, and fix any failures. Match the project’s existing test style and cover the happy path, failure cases, and meaningful edge cases. Run the smallest relevant test suite first, fix failures caused by your work, then report the commands run and results.
Write tests for the password reset flow first, then implement it until they pass. Match the project’s existing test style and cover the happy path, failure cases, and meaningful edge cases. Run the smallest relevant test suite first, fix failures caused by your work, then report the commands run and results.
Read coverage/coverage-summary.json and add tests for the lowest-covered files until each is above 80%. Match the project’s existing test style and cover the happy path, failure cases, and meaningful edge cases. Run the smallest relevant test suite first, fix failures caused by your work, then report the commands run and results.
Migrate everything from the old logging API to the structured logger: identify every place that needs to change, then make the changes. Preserve public behavior unless the request explicitly changes it. Establish a baseline, make the smallest coherent change, run relevant tests or benchmarks, and report before-and-after evidence plus any tradeoffs.
Port this Python module to Rust, keeping the same public API and test behavior. Preserve public behavior unless the request explicitly changes it. Establish a baseline, make the smallest coherent change, run relevant tests or benchmarks, and report before-and-after evidence plus any tradeoffs.
Optimize the search query to bring p95 latency from 2s down to under 500ms. Preserve public behavior unless the request explicitly changes it. Establish a baseline, make the smallest coherent change, run relevant tests or benchmarks, and report before-and-after evidence plus any tradeoffs.
The login button extends 20px beyond the card border on mobile. fix it. Preserve public behavior unless the request explicitly changes it. Establish a baseline, make the smallest coherent change, run relevant tests or benchmarks, and report before-and-after evidence plus any tradeoffs.
Review my uncommitted changes and flag anything that looks risky before I commit. Do not modify anything. Prioritize findings by severity, cite exact files and lines where possible, explain the impact, and suggest a concrete fix. If nothing material is wrong, say so and note any remaining uncertainty or untested areas.
Review PR #247 and summarize what changed, then list any concerns. Do not modify anything. Prioritize findings by severity, cite exact files and lines where possible, explain the impact, and suggest a concrete fix. If nothing material is wrong, say so and note any remaining uncertainty or untested areas.
Here is my Terraform plan output. what is this going to do, and is anything here going to cause problems? Do not modify anything. Prioritize findings by severity, cite exact files and lines where possible, explain the impact, and suggest a concrete fix. If nothing material is wrong, say so and note any remaining uncertainty or untested areas.
Use a subagent to review src/api/ for security issues and report what it finds. Do not modify anything. Prioritize findings by severity, cite exact files and lines where possible, explain the impact, and suggest a concrete fix. If nothing material is wrong, say so and note any remaining uncertainty or untested areas.
Review launch-post.md for unsupported claims, missing attributions, and brand-guideline issues and list anything I should fix before it goes to legal. Do not modify anything. Prioritize findings by severity, cite exact files and lines where possible, explain the impact, and suggest a concrete fix. If nothing material is wrong, say so and note any remaining uncertainty or untested areas.
That is not right: the function signature needs to stay backward-compatible. try a different approach. Preserve correct work already completed and change only what is necessary. Re-check the result against the clarified constraint, run relevant verification, and summarize what changed from the previous approach.
That is too much. keep only the changes to the validation logic in src/forms/ and undo your other edits. Preserve correct work already completed and change only what is necessary. Re-check the result against the clarified constraint, run relevant verification, and summarize what changed from the previous approach.
You keep using default exports when this project uses named exports. add a rule to CLAUDE.md so this stops happening. Preserve correct work already completed and change only what is necessary. Re-check the result against the clarified constraint, run relevant verification, and summarize what changed from the previous approach.
Resolve the merge conflicts in this branch and explain what you kept from each side. Inspect the full diff and repository state first. Preserve unrelated work, avoid destructive operations, run relevant checks before finalizing, and clearly summarize the resulting commits, conflicts, or pull-request contents.
Commit these changes with a message that summarizes what I did. Inspect the full diff and repository state first. Preserve unrelated work, avoid destructive operations, run relevant checks before finalizing, and clearly summarize the resulting commits, conflicts, or pull-request contents.
Find the Linear ticket about the login timeout and open a PR that implements it. Inspect the full diff and repository state first. Preserve unrelated work, avoid destructive operations, run relevant checks before finalizing, and clearly summarize the resulting commits, conflicts, or pull-request contents.
Compare v2.3.0 to v2.4.0 and draft release notes grouped by feature, fix, and breaking change. Follow existing CI and release conventions. Validate syntax and configuration, identify secrets or permissions required, include rollback considerations, and summarize how to verify the workflow safely.
Write a GitHub Actions workflow that runs the tests and deploys to staging on every push to main. Follow existing CI and release conventions. Validate syntax and configuration, identify secrets or permissions required, include rollback considerations, and summarize how to verify the workflow safely.
The UserAuth test is failing, find out why and fix it. Reproduce the problem if possible, gather evidence, and identify the root cause rather than masking the symptom. Make the smallest safe fix, run the relevant checks, and explain the cause, change, and verification.
Users are seeing 500 errors on /api/settings. investigate and tell me what is going on. Reproduce the problem if possible, gather evidence, and identify the root cause rather than masking the symptom. Make the smallest safe fix, run the relevant checks, and explain the cause, change, and verification.
Here is a build error. fix the root cause and verify the build succeeds. Reproduce the problem if possible, gather evidence, and identify the root cause rather than masking the symptom. Make the smallest safe fix, run the relevant checks, and explain the cause, change, and verification.
The checkout endpoint started returning 500s an hour ago. check the logs, recent deploys, and config changes, then tell me the most likely cause. Start with read-only investigation. Build a brief timeline, distinguish evidence from hypotheses, assess impact, and recommend the safest next action. Do not make production changes without explicit approval.
Here is a screenshot of the GCP Kubernetes dashboard. walk me through why this pod is failing and give me the exact commands to fix it. Start with read-only investigation. Build a brief timeline, distinguish evidence from hypotheses, assess impact, and recommend the safest next action. Do not make production changes without explicit approval.
Show me all failed logins for the auth service over the past 24 hours. write the query, run it, and tell me what stands out. Start with read-only investigation. Build a brief timeline, distinguish evidence from hypotheses, assess impact, and recommend the safest next action. Do not make production changes without explicit approval.
Read @reports/q1-signups.csv, summarize the key patterns, and write the results to an HTML page with charts, then open it in my browser. Validate the input data and state any assumptions. Show the method used, quantify the strongest patterns, flag data-quality limitations, and produce a concise conclusion with actionable next steps.
Read @ads-performance.csv, find the underperforming headlines, and generate 20 new variations that stay under 90 characters. Validate the input data and state any assumptions. Show the method used, quantify the strongest patterns, flag data-quality limitations, and produce a concise conclusion with actionable next steps.
Create a /ship skill for this project that runs the linter and tests, then drafts a commit message. Inspect existing project configuration and conventions first. Make the automation safe, repeatable, and narrowly scoped; document prerequisites and failure behavior; then test it and explain how to use or undo it.
Write a hook that runs prettier after every edit to a .ts or .tsx file. Inspect existing project configuration and conventions first. Make the automation safe, repeatable, and narrowly scoped; document prerequisites and failure behavior; then test it and explain how to use or undo it.
Set up the Sentry MCP server so you can read my error reports directly. Inspect existing project configuration and conventions first. Make the automation safe, repeatable, and narrowly scoped; document prerequisites and failure behavior; then test it and explain how to use or undo it.
Summarize what we did this session and suggest what to add to CLAUDE.md. Inspect existing project configuration and conventions first. Make the automation safe, repeatable, and narrowly scoped; document prerequisites and failure behavior; then test it and explain how to use or undo it.
Cada prompt es un punto de partida, no una instrucción terminada. Antes de ejecutarlo, reemplaza los nombres de archivo, temas, métricas y herramientas del ejemplo por los de tu propio trabajo. Pega el prompt en ChatGPT, Claude o Claude Code y ajusta las restricciones según cómo trabaje tu equipo.
La colección de Claude Code se basa en la Claude Code Prompt Library — Enhanced Edition. Esos títulos y peticiones centrales provienen de la documentación de Claude Code de Anthropic; los límites y pasos de verificación añadidos son mejoras editoriales y no deben interpretarse como texto oficial de Anthropic.
Claude y Claude Code son marcas de Anthropic; ChatGPT es una marca de OpenAI. WebCareWorks no está afiliado a ninguna de ellas ni cuenta con su respaldo. Publicamos este directorio como referencia gratuita.