manishiitg

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Back up the family's learning workspace to the parent's own private Hugging Face Hub dataset repo — the ONE destination this family uses, via the hf CLI.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Build a designed, self-contained HTML academic map of the child's subjects, topics, and materials, plus real coaching notes for the parent on how to teach them better.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Build a designed, self-contained HTML progress report for the child — how she's actually doing, and what to work on next — surfaced in the Progress tab for both parent and child.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Create clear, child-ready study material (notes, worked examples, a revision sheet) for a topic, matched to the child's level and their own uploaded materials, packaged as one activity.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Create a practice test for the child from their materials and progress — child-facing questions with a separate parent-only answer key, packaged as one activity.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

A fun, off-syllabus "something new to explore" activity for the child — a light cover page plus a chat-driven discovery, tailored to grade and interests learned over time. Parent-initiated, handed off like any other activity.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Send the parent a notification at the right moments — the child finished a session, a test/report is ready, a backup completed, or a decision is needed.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Read a newly uploaded file from the inbox, classify it, move it into the right subject/topic folder, and write a metadata JSON.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Publish a family artifact (a progress report or the academic map) to a shareable destination — a shared folder, a static host, Google Drive, or GitHub Pages — tracking config vs status in files.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Extract the actual text/content from a file of ANY format — PDF, Word, PowerPoint, Excel, images, scans, archives. The canonical "how do I read this file" reference, reused by process-file, Pulse ingestion, and browser downloads.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Age/grade-appropriate approach for a coding/programming subject — read this BEFORE create-study-material or create-test when the topic is coding/programming, in addition to that skill.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Extract genuine interest signals from the child's own conversations and keep memory/interests.md current — a Pulse-only skill, not triggered by a direct parent request.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Extract durable things the parent has said in chat and keep memory/preferences.md current — a Pulse-only skill, not triggered by a direct parent request.

manishiitg/coding-agent-loop

Command

Handle character work for this production — designing a new one, reviewing what exists, or revising a character already in use. Figure out which of these I mean from what follows, and if it's genuinely ambiguous, ask.

manishiitg/coding-agent-loop

Command

Re-run the quality checks on the current cut.

manishiitg/coding-agent-loop

Command

Show me the plan before you build it.

manishiitg/coding-agent-loop

Command

Start a new video production.

manishiitg/coding-agent-loop

Command

Revise one shot without rebuilding the video.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Create and present the user-approved visual evidence that a cinematic sequence needs before video generation: subject reference packs, locations, wardrobe, props, lighting, camera language, and start/exit/bridge frames. Use before an anchor or follow-up clip.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Generate AI video, image, voice/TTS, and music clips via fal.ai's Node.js client for cinematic video productions. Use when a brief calls for footage, reference imagery, narration, or a music bed that cannot come from uploaded assets or a selective deterministic HyperFrames insert.

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Plan and generate or edit video effectively with Google Gemini Omni Flash through current fal.ai endpoints. Use when a production selects or considers Gemini Omni, Google Omni, or Gemini Omni Flash for text-to-video, image-to-video, reference-to-video, conversational video editing, localized revisions, multimodal…

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Check AI-generated footage for the failure modes generation causes rather than deterministic editing -- identity drift, generation artifacts, motion that breaks physics, temporal discontinuity at stitch points, lip-sync drift, and prompt adherence. Use alongside video-quality for any candidate assembled from fal-ai or…

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Generate AI video, image, and narration (text-to-speech) via Google's own Gemini API (Node.js client) -- Gemini image models (publicly nicknamed "Nano Banana"), Veo video models, and Gemini TTS. Use instead of fal-ai when the brief calls for a Google-native model, or when Google is the only provider configured -- this…

manishiitg/coding-agent-loop

Skill Claude CodeCodex

Design and render video frames as HTML/CSS, then assemble them into a video with headless Chrome and ffmpeg. Use when building an infographic, product explainer, stat card, title sequence, or any piece whose visuals are laid-out typography, charts, and shapes rather than photographic footage.