skill-yhbcode000-paper-share-skills-paper-slides-to-video · by Install
$ agentstack add skill-yhbcode000-paper-share-skills-paper-slides-to-video ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-yhbcode000-paper-share-skills-paper-slides-to-video) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Paper Slides to Video
The public entrypoint is:
/paper-slides-to-video/scripts/slides_to_video.pyRun it with the package environment:
uv run --project /paper-slides-to-video python /paper-slides-to-video/scripts/slides_to_video.py Exact CLI
render PDF FRAME_DIR [--dpi 200]plan TEXnarrations FRAME_DIR TEX --annotated-tex ANNOTATED_TEXtts FRAME_DIR [--lang zh]assemble FRAME_DIR OUTPUT [--pad-sec 0.5] [--speed 1.25]cover FIRST_FRAME OUTPUTmetadata TEX COVER OUTPUTfull PAPER_DIR --annotated-tex ANNOTATED_TEX
Required full workflow
- Compile
slides-beamer/main.pdfbefore invoking this package. - Copy
slides-beamer/main.textovideo/main_with_narration.texand add one nonempty% NARRATION:annotation for every rendered physical page. This per-physical-page contract is what keeps landscape and portrait renders in sync: both orientations are assembled from the same PDF pages, so narration/audio cardinality gates apply equally to each orientation. - Run
fullwith the annotated TeX path.
uv run --project /paper-slides-to-video python /paper-slides-to-video/scripts/slides_to_video.py full "" --annotated-tex "/video/main_with_narration.tex"full removes any stale narrated output before processing. It requires exact PNG/TXT/MP3 cardinality, nonempty narration and audio, probeable positive audio durations, and an assembled MP4 containing both video and audio streams. A missing narration or MP3 exits nonzero and cannot leave a narrated result.
Tool discovery
PDFTOPPMorPOPPLER_DIR(directory containingpdftoppm), thenPATHFFMPEG, thenPATHFFPROBE, thenPATHEDGE_TTS_BIN, thenPATH
Silence is never implicit. Programmatic callers may create a deliberately silent page only by calling encode_slide(..., require_audio=False). The public default is require_audio=True.
Outputs are written under /video/: video_frames/, _narrated.mp4, cover.png, frames_data.json, narrations.json, and video_meta.json.
Related skills
- skill://batch-papers-single-omp-full-pipeline
- skill://batch-slides-to-video
- skill://blog-to-bilibili
- skill://edge-tts-retry-video-driver
- skill://index-tts-fallback
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: yhbcode000
- Source: yhbcode000/paper-share-skills
- License: Apache-2.0
- Homepage: https://blog.yhbcode000.tech/paper-share-skills/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.