Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tornikebolokadze1-cyber/awesome-ai-pulse-georgia --skill viral-tech-reel-editorgit clone --depth 1 https://github.com/tornikebolokadze1-cyber/awesome-ai-pulse-georgiaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tornikebolokadze1-cyber/awesome-ai-pulse-georgia/viral-tech-reel-editor)<a href="https://agentmods.dev/skills/tornikebolokadze1-cyber/awesome-ai-pulse-georgia/viral-tech-reel-editor"><img src="https://agentmods.dev/badge/skills/tornikebolokadze1-cyber/awesome-ai-pulse-georgia/viral-tech-reel-editor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tornikebolokadze1-cyber/awesome-ai-pulse-georgia/viral-tech-reel-editor"><img src="https://agentmods.dev/badge/skills/tornikebolokadze1-cyber/awesome-ai-pulse-georgia/viral-tech-reel-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00172 | $0.02928 |
| Opus 5 | $0.00086 | $0.01464 |
| Sonnet 5 | $0.00034 | $0.00586 |
| Haiku 4.5 | $0.00017 | $0.00293 |
Grade A, and why
viral-tech-reel-editor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Viral Tech Reel Editor (2026)
Premium, retention-first vertical reel production: understand the video, transcribe precisely, design the timeline, build all visual/audio layers, render, and self-check before delivery. Treat every edit as a full production pass, never a captions-only pass.
Start Rule
For every end-to-end edit, create a Goal if a Goal/Todo tool is available, covering the FULL delivery (not just the first technical step). Otherwise maintain an explicit written checklist. Do not mark complete until final export AND the QA gate pass. Before any work, load references/style-memory.md — it contains binding user preferences and prior feedback.
Full Framework Rule
Never deliver a plain "clean baseline" talking-head edit unless the user explicitly requests a minimal edit. A valid edit applies ALL pillars:
- Pacing — visual-change rhythm (punch-ins, overlay/b-roll swaps, reveals) tied to beats. Default = NO-CUT: the creator's A-roll is already edited — never trim, chop, or silence-cut the host's voice track. Only run
scripts/silence_cut.pyif the user explicitly asks for cutting on a raw, uncut recording. - Main-shot motion — punch-ins, zoom-outs, reframes, visual resets tied to key words and story beats.
- Proof layer — contextual b-roll: product/UI footage, extracted promo clips, window-only screen recordings, diagrams, recreated demos that clarify the spoken idea. AUTO by default: resolve every proof beat automatically by walking the b-roll ladder in
references/broll-sourcing.md(owned → official → contextual free stock → recreate → AI-generate) — never ask per-insert; only escalate on a rights/safety/fabrication blocker. - Cinematic layer — at least one 3D/AI-generated cinematic or high-end motion set-piece on the hook or payoff (see
references/cinematic-3d.md). - Motion design — kinetic typography, lower thirds, counters, HUD/diagram animation where they clarify.
- Sound design — license-clear trending SFX mixed clearly under speech; loudness-normalized output.
- Captions — word-accurate karaoke captions, Georgian/English term accuracy, safe placement.
- Layout — deliberate vertical canvas use with ZERO collisions (face, hands, captions, PiP, UI, diagrams).
- QA evidence — contact sheet, loudness report, and a note stating which pillars passed (
scripts/qa_report.py).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 106 lines · 172 tokens per session scan A 9cbc9292afaa
viral-tech-reel-editor is a skill published in the GitHub repository tornikebolokadze1-cyber/awesome-ai-pulse-georgia (139 stars, last pushed yesterday), licensed CC0-1.0. It adds 172 tokens to every session and 2,928 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
check-mcp-json
Safely review, triage, repair, and merge ToolSDK MCP Registry package JSON pull requests. Use when an agent needs to validate files under packages/, detect duplicate registry keys, classify community PRs, make authorized fixes on contributor branches, close invalid or duplicate PRs, or squash-merge approved PRs.
deep-research
Guide-type skill for rigorous, transparent research. Use it to investigate a complex topic, collect and evaluate evidence, resolve contradictions when possible, and produce a cited research report.
material-organizer
Organize user-provided materials or local folders into traceable notes, knowledge cards, categories, indexes, and cleanup plans. Use this skill whenever the user asks to organize multiple links, files, snippets, research materials, downloads, personal knowledge flow materials, or a local directory.
knowledge-map
Guide-and-script skill for building course knowledge maps. Use it to turn a course topic, syllabus, textbook outline, notes, or teaching materials into a structured framework, key concept explanations, concept dependencies, and optional Markdown / Markmap / Mermaid / OPML / HTML outputs.
socratic-tutor
Do not use for full study plans, whole-course knowledge frameworks, bulk material organization, end-to-end thesis management, ghostwriting, doing homework for the user, or giving final answers directly. If the user asks for an adjacent but overly broad learning task, do not introduce other skills and do not reject…
image-design
Use this skill when the user wants to create or edit visual assets and needs a clear plan before execution.