Video Platform Reader
Read one or many public-platform or local videos through a portable evidence workflow using available metadata, subtitles, timestamped speech recognition, keyframes, and official-source verification. Use for video summaries, knowledge extraction, comparisons, tutorials, and auditable claims across Bilibili, YouTube, TikTok, Douyin, Xiaohongshu, podcasts, web video, or local media.
Install
$ agentstack add skill-tikazi-tikaz-ai-skills-video-platform-reader ✓ 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-tikazi-tikaz-ai-skills-video-platform-reader) 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
Video Platform Reader
Designed, integrated, independently refactored, and continuously maintained by TIKAZ.
TIKAZ Edition
- Type: clean-room portable workflow.
- TIKAZ contribution: cross-platform source ledger, five evidence levels, claim-type separation, keyframe escalation, partial-failure handling, and cross-video synthesis contract.
- Boundary: do not claim platform access, download support, or visual inspection until the current environment proves it.
Workflow
- Inventory every requested source with platform, stable ID or file hash, author, publication date, duration, access result, and available evidence.
- Acquire evidence with the least invasive available path: native transcript first, then legal metadata/subtitle tooling, timestamped ASR, and selective keyframes.
- Assign
L0metadata,L1native transcript,L2timestamped ASR,L3transcript plus keyframes, orL4media evidence plus primary-source verification. - Label each important statement as source claim, transcript evidence, visual observation, external verification, or inference.
- Create one evidence card per source before comparing sources. Record inaccessible, deleted, private, unsupported, or partially processed items instead of silently dropping them.
- For visual claims, inspect the relevant timestamp or mark the claim unverified. For consequential factual claims, prefer an official primary source.
- Synthesize agreements, conflicts, missing dependencies, confidence, and actionable conclusions only after source-level cards are complete.
Output contract
Return the source ledger, evidence level, timestamped findings, visual checks, unresolved gaps, and synthesis. Never describe metadata or a search snippet as watched content. Never bypass DRM, authentication, paywalls, or platform access controls.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: TIKAZI
- Source: TIKAZI/TIKAZ-AI-Skills
- License: MIT
- Homepage: https://tikazi.github.io/TIKAZ-AI-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.