sanand0

ALWAYS follow this style when writing Python / JavaScript code

To select, design, annotate, and verify a data visualization (chart, map, or table).

ALWAYS follow this design guide for any front-end work

Use this for non-trivial analysis, design, diagnosis, review, strategy, or judgment. Skip it for simple lookups, mechanical rewrites, and pure tone tasks.

For CloudFlare development, deployment, e.g. Python CloudFlare Workers

Use when creating demos or POCs

Navigate LinkedIn via Chrome DevTools Protocol (CDP) using `uvx rodney` connected to an existing logged-in browser session. Use for extracting profile information, discovering people by city/role/interest, finding people who can help with specific tasks, and surfacing interesting posts and content.

Workflows for melt, the MLT Framework CLI video editor, to edit, transcode, composite, stream, or automate video/audio. Covers multitrack composition, color grading, batch processing, encoding, streaming, and server-side pipelines.

To write in Anand's style for blog posts, emails, talk summaries, interview questions, conversations, ...

Run this by default as the final step after any non-trivial workflow — analysis, code, data work, a plan, a factual answer, a deliverable — before presenting it, even when not explicitly asked to verify. Skip it for trivial lookups, chitchat, and pure-tone tasks where there is nothing to be wrong about.

The user's question may be a DRAFT of their real need. For substantive requests, check if a better question changes what's solved and serves them better. If so, reframe, explain why (in 1 line), THEN answer. Most questions need no reframe; skip precise, mechanical, tightly specified, or already-sharp requests and simply answer.

Apply to any substantive answer for Anand - strategy, design, build, analysis, teaching, writing, research - to steer it toward his goals (compounding assets, durable skills, the surprising read). Skip for trivial lookups, mechanical edits, focused tasks. Shapes HOW to answer, never overrides WHAT was asked.

Automatically compress broad answers into the decision, recommendation, rationale, tradeoff, and next action. Use for recommendations, prioritization, research synthesis, strategy, planning, reviews, rankings, and large-context requests.

Brainstorm creative, novel, non-obvious ideas or options for an open-ended problem and narrow them to a recommendation. Not for writing prose, research, explanation, summaries, or questions with one right answer.

Apply relevant mental models for strategy, forecasts, recommendations, or advice. Skip for execution, lookups, and mechanical edits.

Use when creating REALISTIC synthetic data leading to actionable business hypotheses.

Generate an engaging narrative HTML story page for a conference talk or workshop. Use when the user asks for a "narrative story" about a talk, typically pasting a prompts.md-style brief for a talk directory containing transcript.md. Handles context gathering, PDF-to-slide conversion, screenshots, chunked HTML generation in Malcolm Gladwell narrative style, and a quality/fact-check pass. Invoke as /talk-story <talk-dir> or when the user's prompt names the talk directory.