Set how your assistant teaches, suggests useful next steps, and helps your skills grow over time.
Add in Personalization → Custom Instructions
Custom instructions, prompts, and reusable skills for doing better work with AI.
Practical prompts and reusable skills for doing better work with AI. Browse by the job you want to do, then copy the resource or save it for later.
Set durable teaching, workflow, and personalization instructions in the AI applications you use.
Set how your assistant teaches, suggests useful next steps, and helps your skills grow over time.
Add in Personalization → Custom Instructions
Set your assistant to notice work worth keeping and recommend a clear place for it in a PARA second brain.
Add in Personalization → Custom Instructions
Review what your conversations reveal about your goals, recurring work, useful AI applications, and reusable skills.
Find 10–20 valuable ways AI could help you, including the prompts, skills, trusted integrations, and context each idea needs.
Find stale or contradictory guidance and update the reusable context that influences your AI tools.
Answer a few simple questions, then get a polished HTML audit with copy-ready context updates for the model you use now.
Update your AI context for a new model through a few plain-English questions and a polished, copy-ready HTML audit.
Research current techniques, decide which ones fit the task, and turn them into prompts and checks that improve model output.
Research current guidance, decide what fits the task, and reject cargo-cult rules that add cost without improving the result.
Set up writing tools that help you develop, critique, and revise prose while preserving your voice and argument.
Install Pilcrow for the writing tools you use, build a source-backed voice profile, and verify its editorial checks without flattening your voice.
Add in Writing project root
Explore visual directions, build front-end interfaces, and check the result against the product's design system.
Create three genuinely different design directions for a requested page, section, or component using raster mockups in Codex or HTML/CSS mockups in Claude.
Turn a live route, screenshot, or accepted mockup into production UI with an asset-first, browser-verified fidelity workflow.
Install Impeccable for the coding tools you use, capture the product's design context, and verify its anti-slop checks.
Add in Project root
Use repeatable coding-agent workflows for handoffs, implementation, review, verification, and clean Git history.
Create a Claude or Claude Code handoff that preserves the goal, directions, files, progress, and remaining work before compaction or a new session.
Turn a mixed working tree into the smallest truthful set of cohesive commits without sweeping unrelated work into the history.
Research, plan, implement, verify, refactor, and explain the work simply.
Available as Prompt and Skill file
Find and fix unclear names, functions, components, modules, and folders in React and TypeScript without changing observable behavior.
Install Codex as a Claude Code reviewer, choose automatic or manual reviews, and verify the setup.
Tell Fable exactly what Codex needs to implement a plan in a fresh context, including contracts, exact copy, actor labels, and runnable checks.
Install analytics, performance, database, error monitoring, and security tools, then use their evidence to improve the application.
Link the right Vercel project, add both official tracking packages, and verify that production traffic and real-user speed data can be collected.
Find the routes users rely on, compare their real-user Web Vitals, and turn the strongest evidence into a prioritized improvement plan.
Install the supported Supabase CLI, link the correct project, and establish read-only access to database linting and advisor evidence.
Translate Supabase Advisor findings into verified risks, context-dependent warnings, safe migrations, and production-ready checks.
Install Lighthouse with the project, create repeatable mobile and desktop commands, and verify JSON and HTML reports on a real page.
Audit the pages real users depend on, separate repeatable findings from run noise, and prioritize fixes without flattening the site's experience.
Scan a public production site, explain each HTTP security finding, and plan compatible header fixes that preserve working user journeys.
Install Sentry and its command-line tool, keep development noise out, preserve intentional staging, and verify production alerts when the app is ready.
Investigate a real production issue, prove its root cause, make the smallest safe fix, and verify the new release without hiding the error.