Analyze a lifting set locally and turn pose measurements into a technique report, per-rep data, keyframes and an optional annotated video.
Codex
Claude CodeFitness Form Coach analyzes one recorded squat, deadlift or bench-press set on the user’s computer. Its local pose pipeline estimates 17 body landmarks, rep phases, joint angles and view-dependent technique findings. It produces HTML and Markdown reports, structured per-rep data, keyframes and an optional annotated skeleton video. The exercise must be confirmed before analysis. The bundled proprietary knowledge library supports targeted follow-up questions. Python packages and pose models must be downloaded before they are available locally; missing models may also be downloaded when analysis starts. The source contains no video-upload implementation. AI assistant access may have its own cost; the local analysis engine does not require a service API key. The original supplied source package and third-party notices are preserved. The proprietary knowledge library is supplied for use within this Skill.
ipfs://bafkreic2h5gk2dvnzwijhkqeufem67dv7fgmzdql36o6gc4hwbyaia7bx4
v1 · Original user-supplied Fitness Form Coach ZIP preserved without core-source changes. No detail HTML is included in this publication scope.
The primary-document hash is the SHA-256 of the plaintext primary Markdown file. The content-commitment hash covers the verified SkillRoot structure, or plaintext ZIP for older Skills; it is not the hash of the downloaded file.
Opaque identifiers and fingerprints are hidden from the primary experience but remain available for exact verification.
0x4d8da0682b5cef60207608409954fc846d45b37a26378ad22ef9d27214ca44e60xe57e5787fb0cfd0af2116fc1bad68bffd1c2720070a363dfef24972cafd18b42