ext/hyperframes
2
0
Fork 0
mirror of https://github.com/heygen-com/hyperframes.git synced 2026-09-12 15:20:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(skill): all file paths use capture/ subfolder prefix (#345)

Browse Source 
* fix(skill): all file paths use capture/ subfolder prefix

Step-1 was updated to capture into <project-dir>/capture/ but all
file-read instructions across steps 1-6 still used bare paths
(extracted/tokens.json, assets/hero.png). Agents following the skill
looked for files in wrong locations, producing broken compositions
with 404'd images and fonts.

- step-1: all 12+ file-read paths prefixed with capture/
- step-2: tokens.json and asset-descriptions.md paths fixed
- step-3: visible-text.txt path fixed
- step-4: asset-descriptions.md, asset examples, directory tree expanded
  to show capture/ children (screenshots/, assets/, extracted/)
- step-5: minor cleanup
- step-6: asset-descriptions.md path fixed, composition examples already
  correct (../capture/assets/)
- techniques.md: Lottie, video, font paths all prefixed

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(skill): address Copilot review — font comment path, add videos/ to tree

- techniques.md: comment says ../capture/assets/fonts/ (matches composition context)
- step-4 file tree: add videos/ under capture/assets/

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ular Kimsanov
2026-04-20 05:01:25 +02:00
committed by GitHub
co-authored by Claude Opus 4.7
parent 479e6c3f81
commit a78ec5ec76
7 changed files with 49 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/website-to-hyperframes/references/step-5-vo.md
+1 -1
View File
@@ -14,7 +14,7 @@ Pick the voice that sounds most natural and conversational. Listen for pacing
Generate the full script as `narration.wav` (or `.mp3`) in the project directory.
**Also save the exact spoken text** — with pronunciation substitutions applied (e.g., `API` → `A P I`, `$2T` → `two trillion`) — as `narration.txt` in the same directory. This is the string passed to TTS, distinct from `SCRIPT.md` which is the human-readable creative doc. Having `narration.txt` makes it trivial to regenerate the audio later with a different voice without re-deriving the substitutions. Name it exactly `narration.txt` — not `narration-input.txt` or variations.
**Also save the exact spoken text** — with pronunciation substitutions applied (e.g., `API` → `A P I`, `$2T` → `two trillion`) — as `narration.txt` in the same directory. This is the string passed to TTS, distinct from `SCRIPT.md` which is the human-readable creative doc. Having `narration.txt` makes it trivial to regenerate the audio later with a different voice without re-deriving the substitutions. Name it exactly `narration.txt`.
## Transcribe for word-level timestamps