video-source-verification
Use this skill for fast, traceable internet-source verification of claims from videos/articles (especially YouTube claims) before acting on them.
Best use case
video-source-verification is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use this skill for fast, traceable internet-source verification of claims from videos/articles (especially YouTube claims) before acting on them.
Teams using video-source-verification should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/video-source-verification/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How video-source-verification Compares
| Feature / Agent | video-source-verification | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use this skill for fast, traceable internet-source verification of claims from videos/articles (especially YouTube claims) before acting on them.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Video Source Verification Use this skill when a user gives a specific claim from a video (especially YouTube) and asks for quick verification, evidence extraction, and archival notes. ## Quick Start 1) Pull direct evidence first: ```powershell node C:/Users/issda/.codex/skills/hydra-node-terminal-browsing/scripts/hydra_terminal_browse.mjs \ --url "<claim-article-or-video-page-url>" \ --out "C:/Users/issda/SCBE-AETHERMOORE/docs/research/evidence/<slug>.json" ``` 2) Verify with at least one independent source: ```powershell node C:/Users/issda/.codex/skills/hydra-node-terminal-browsing/scripts/hydra_terminal_browse.mjs --url "https://www.toi.com/..." --out "C:/Users/issda/SCBE-AETHERMOORE/docs/research/evidence/<slug>/source_2.json" node C:/Users/issda/.codex/skills/hydra-node-terminal-browsing/scripts/hydra_terminal_browse.mjs --url "https://www.other-source.com/..." --out "C:/Users/issda/SCBE-AETHERMOORE/docs/research/evidence/<slug>/source_3.json" ``` 3) If claim source is JS-driven (YouTube/watch pages, dynamic embeds), run a Playwright pass: ```powershell $env:PWCLI="C:/Users/issda/.codex/skills/playwright/scripts/playwright_cli.sh" "$env:PWCLI" open <url> --headed "$env:PWCLI" snapshot "$env:PWCLI" screenshot ``` 4) Summarize and archive in markdown: ```powershell # Save as one deterministic claim note Set-Content -Path C:/Users/issda/SCBE-AETHERMOORE/docs/research/<slug>.md -Value @" # Claim: ... - Source A: - Source B: - Evidence quality: low|medium|high "@ ``` 5) Optional: for multi-hop internet-workflow runs, trigger the pipeline tuner after baseline checks: ```powershell python C:/Users/issda/.codex/skills/scbe-internet-workflow-synthesis/scripts/run_e2e_pipeline.py --repo-root C:/Users/issda/SCBE-AETHERMOORE --profile training/internet_workflow_profile.json ``` ## Evidence Contract (required) Each claim should emit JSON artifacts with these keys: - `url` - `resolved_url` - `status` - `title` - `text_excerpt` - `links` - `metrics` - `fetched_at` ## Standard Confidence Rubric - `high`: original source + direct source of claim + at least one independent corroborating source - `medium`: direct claim source + 1 secondary source, but no direct benchmark details - `low`: only rumor/aggregate reposting, no direct source or contradictory signals ## Safety Rules - Prefer primary/near-primary sources over re-posts. - Never store secrets or API keys in research artifacts. - Keep outputs deterministic and timestamped. - If claim is impactful, add a short `docs/research/<slug>.md` note with explicit uncertainty language. ## Integration Notes - For repo-level training workflows, route notable verified claims to: - `docs/research/` - `docs/notes/` if you need a long-term cross-agent index - Use this skill when you want reusable, repeatable research steps that can be performed by any local AI agent with your skill registry.
Related Skills
scbe-voice-render-verification
Govern and verify SCBE voice rendering work that maps Langues weighting into breath, phase, and Layer 14 audio-axis packets. Use when implementing or reviewing `scripts/voice_gen_hf.py`, emitting sidecar voice packets, validating canonical tongue ordering, tuning breath planning or phase timing, or keeping voice docs and code aligned with `docs/LANGUES_WEIGHTING_SYSTEM.md` and `docs/specs/SCBE_VOICE_EMOTIONAL_TIMBRE_SYSTEM.md`.
scbe-manhwa-video-picture-research
Research manhwa recap video and image workflows and emit story-first, source-traceable scene packets for production, narration, and publishing.
scbe-training-pair-authoring
Create prompt and response and metadata training pairs from SCBE documents, repair traces, terminal sessions, and operational workflows using the repository's canonical dataset contract and provenance rules.
scbe-spin-conversation-engine
Generate SFT training data via radial matrix conversation pivots with D&D-style combat research mode. Produces diverse, cost-effective training pairs with Sacred Tongue encoding, golden spiral problem distribution, and harmonic re-attunement.
scbe-research-training-bridge
Stage arXiv evidence and Obsidian markdown into source-grounded Hugging Face training bundles for research, review, and later SFT runs.
scbe-document-management
Consolidate overlapping docs, classify files by authority, and keep SCBE repo documents aligned with runtime truth. Use when the repo has drift between canonical docs, public docs, proposal notes, research branches, and generated evidence.
scbe-colab-bridge
Control Google Colab notebooks from Claude Code via Chrome extension. Execute cells, run terminal commands, read outputs, and manage GPU compute remotely.
scbe-claim-to-code-evidence
Map SCBE Notion technical claims, proof pages, and patent-facing architecture notes to concrete repository evidence such as code paths, tests, demos, and docs. Use when Codex needs to build a due-diligence packet, claim-to-code audit, implementation crosswalk, patent support note, or proof summary from local Notion exports and repo artifacts.
scbe-autonomous-worker-productizer
Turn SCBE automation, autonomous worker, and revenue-system notes into concrete offers, workflow packs, pilot plans, or SaaS-facing product packets. Use when Codex needs to package Notion automation pages into buyer-ready offerings, n8n/Zapier workflow designs, flock-backed worker systems, or implementation roadmaps tied to existing SCBE repo surfaces.
multi-agent-cloud-offload
Deterministically sort, bundle, verify, and offshore local files through multiple AI/model lanes while capturing training rows and method evidence. Use when Codex needs to inventory folders, batch-process files, upload them to cloud targets such as rclone-backed Google Drive, Hugging Face, or GitHub, and only delete sources after the configured number of verified targets succeed.
long-form-work-orchestrator
Run long-form engineering work in checkpointed phases with deterministic artifacts, resilience handling, and end-of-run reliability reporting.
scbe-code-scanning-ops
Operate GitHub code scanning and CodeQL remediation for SCBE repositories. Use when triaging code-scanning alerts, mapping alert classes to fix patterns, validating targeted regressions, or wiring dedicated CodeQL workflows and runbooks into the repo.