Extract Short-Video Data and Speech Transcripts
Short-video links often separate useful metadata from spoken content. This skill combines TikHub data queries and Qingdou transcription, then saves transcripts as organized Markdown files.
Copiez cette demande dans votre Agent. Elle contient la page Skill de référence et le manifeste.
Review the Skillstore skill "dbs-video-extract" from https://skillstore.io/skills/dontbesilent2025-dbs-video-extract.md and its manifest at https://skillstore.io/api/skills/dontbesilent2025-dbs-video-extract/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Votre Agent doit toujours présenter son plan et demander toute confirmation exigée par la politique de sécurité.
Utilisez ces liens lorsqu’un Agent IA, un crawler ou un script a besoin d’un contexte propre au lieu de lire toute la page.
Utilisation de « dbs-video-extract ». Check readiness when only TikHub is configured.
Résultat attendu:
TikHub credentials are configured. Metadata queries are available; speech transcription requires Qingdou credentials. This local check does not validate authentication, balance, or service availability.
Utilisation de « dbs-video-extract ». Illustrative successful extraction of a public video titled Morning Routine by Sample Creator.
Résultat attendu:
Utilisation de « dbs-video-extract ». Illustrative combined extraction where metadata succeeds but transcription reports insufficient resources.
Résultat attendu:
Partial success: metadata was retained. Qingdou transcription failed because the provider reported insufficient resources. No transcript file was created.
Most static flags reflect documented credential handling, Markdown syntax, or platform identifiers rather than malicious behavior. Confirmed risks concern credential-bearing redirects, HTTP endpoint overrides, and unrestricted URL resolution; seven static locations cover these three issues. No evidence found of malicious intent or prompt injection in the reviewed files.
Il s’agit de capacités locales réelles qui peuvent être attendues pour cette compétence ; elles nécessitent donc un examen, mais ne sont pas comptabilisées comme comportement malveillant confirmé.
Partagez le rapport d’évaluation versionné, le badge neutre, la carte intégrable et les citations. Skillstore présente les preuves sans décider si ce Skill est sûr.
https://skillstore.io/skills/dontbesilent2025-dbs-video-extract/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/dontbesilent2025-dbs-video-extract?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/dontbesilent2025-dbs-video-extract?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/dontbesilent2025-dbs-video-extract/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/dontbesilent2025-dbs-video-extract.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>dontbesilent2025. (2026). dbs-video-extract security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/dontbesilent2025-dbs-video-extract/audits/1@techreport{dontbesilent2025-dontbesilent2025-dbs-video-extract-2026,
author = {dontbesilent2025},
title = {dbs-video-extract security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/dontbesilent2025-dbs-video-extract/audits/1},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "dbs-video-extract security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "dontbesilent2025"
date-released: "2026-10-17"
url: "https://skillstore.io/skills/dontbesilent2025-dbs-video-extract/audits/1"
identifiers:
- type: other
value: "skillstore:dontbesilent2025-dbs-video-extract:audit:1"
description: "Skillstore immutable audit report identifier"
Save spoken content and source metadata from permitted public videos into an organized Markdown research archive.
Retrieve available engagement statistics and author details without requesting transcription when only metadata is needed.
Extract a transcript from a published video for manual editorial review while retaining the original service output.
Check which credentials are configured for dbs-video-extract. Report available capabilities without showing secrets or making network requests.
Extract only the speech transcript from [video share text]. Save it under [output directory] and report the resulting Markdown path.
Extract metadata and speech from [video share text] into [output directory]. Preserve either successful result if one service fails, and report limitations.
Process [Douyin video share text] in combined mode using stdin. Prefer App data with Web fallback, retain raw metadata, and preserve existing transcripts.
Auteur
dontbesilent2025Licence
MIT
Révision Skillstore
r1
Avis de version
L’auteur n’a déclaré aucune version.
Réf
6d898941f6658de941ea432964f66e3589e26dc5
Récence de maintenance
17/10/2026
Utilisation
0 téléchargements · 0 vues
Structure de fichiers
Decode Why Content Resonates and Gets Shared
Audience reactions can be difficult to explain from engagement numbers alone. This skill uses textual evidence and communication theories to explain emotional responses and sharing motives.
Identify Customer Jobs and Switching Motivations
Requests for features or deliverables can hide the progress customers actually need. This skill uses Jobs to Be Done to clarify context, switching motivations, selection criteria, and next actions.
Convert Markdown to WeChat Article HTML
Markdown articles can lose formatting when pasted into the WeChat editor. This skill guides HTML generation with inline styles and local previews for manual publishing.
Research Conditional Answers Through Theory and History
Complex questions often receive unsupported theories or misleading historical comparisons. This skill combines theory checks, structural case comparisons, and counterexamples to develop answers with clear conditions.
Improve Short Video Script Flow
Abrupt transitions, repetition, and awkward sentences can make short video scripts difficult to follow. This skill identifies specific weaknesses and suggests conversational revisions while preserving your original text.
Check Publication Risks Before Posting
Creators need to distinguish automated moderation signals from substantive publication problems. This skill identifies specific concerns and suggests minimal edits while preserving personal expression.
Créer des lecteurs d’articles bilingues
par Yuan1z0825
Les articles de recherche sont difficiles à étudier lorsque la traduction, les figures, les légendes et les emplacements sources sont séparés. Cette compétence crée un artefact de lecture Markdown complet avec le texte original, la traduction chinoise, les ressources visuelles et des ancres traçables.
Extraire du contenu web propre
par 21pounder
Les pages web incluent souvent de la navigation, des publicités et du contenu dynamique qui masquent les informations utiles. Cette compétence guide Claude, Codex ou Claude Code pour capturer des pages et renvoyer du contenu propre.
Extraire du Markdown web propre
par kepano
Les pages web incluent souvent de la navigation, des publicités et du texte de mise en page qui gaspillent des tokens. Cette skill utilise Defuddle CLI pour extraire un Markdown plus propre pour Claude, Codex et Claude Code.
Track Long Tasks With a Portable State Ledger
par glenskii
Long technical tasks lose decisions, evidence, and next actions across sessions. This skill maintains a concise Markdown state file with reviewed local evidence references.
Générer des quiz de cours interactifs
par 92Bilal26
Les auteurs de cours ont besoin de quiz équilibrés qui évaluent la compréhension plutôt que la mémorisation. Cette compétence crée des évaluations à 50 questions pour le composant Quiz, avec commentaires, liens vers les sources et vérifications de la répartition des réponses.
Générer des mèmes avec Memegen
par softaworks
Les équipes ont souvent besoin d’humour visuel rapide sans ouvrir d’outils de design. Cette compétence génère des URL de mèmes, des intégrations Markdown et des formats de mèmes textuels à partir d’un prompt.