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 ErickRamirezAU/claude-skills --skill youtube-video-evaluatorgit clone --depth 1 https://github.com/ErickRamirezAU/claude-skillsWrote 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/erickramirezau/claude-skills/youtube-video-evaluator)<a href="https://agentmods.dev/skills/erickramirezau/claude-skills/youtube-video-evaluator"><img src="https://agentmods.dev/badge/skills/erickramirezau/claude-skills/youtube-video-evaluator/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/erickramirezau/claude-skills/youtube-video-evaluator"><img src="https://agentmods.dev/badge/skills/erickramirezau/claude-skills/youtube-video-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00133 | $0.02821 |
| Opus 5.5 | $0.00053 | $0.01128 |
| Sonnet 5.5 | $0.00027 | $0.00564 |
| Haiku 4.5 | $0.00013 | $0.00282 |
Grade A, and why
youtube-video-evaluator scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
it (you have vision) — never re-fetch thumbnails by hand with curl, and How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Idea Evaluator
Takes video candidates (usually from youtube-idea-finder) and produces an
actionable diagnostic report per video: what its thumbnail and editing
actually look like and why, what topics/tech/format it covers, and a
concrete "replicate this, fix that, do this for your own calendar" brief.
This skill does not search YouTube or apply any pass/fail filter — every candidate handed to it gets a full write-up. The point isn't to find gaps to exploit, it's to reverse-engineer what worked (and what didn't) well enough to turn it into a content calendar entry.
Do not modify youtube-idea-finder. It stays a standalone skill. This
skill only consumes its output (or a manually supplied list of video IDs/URLs).
Inputs
- A JSON output file from
youtube_idea_finder.py(has acandidatesarray withvideo_idper entry), or - A plain list of YouTube video IDs or URLs the user pastes in directly
If the user hasn't run the finder yet and asks for both in one request, run the finder first, show its table, then feed its candidates into this skill. The finder needs a search term/niche to run — if the user hasn't given one (e.g. they just said "find me some video ideas and evaluate them"), ask for it before invoking the finder. Don't guess a query on their behalf.
If a --finder-json file is supplied instead (e.g. from an earlier
session, or handed off without restating the query in this conversation),
read the search term for the output filename directly from that file's
top-level query field rather than relying on conversation context —
youtube_idea_finder.py always writes it there.
Scope
- In scope: thumbnail quality, editing/pacing quality, topics covered, tech/tools named, format/framing, and what's replicable vs. what needs fixing.
- Out of scope: audio quality (no way to assess it reliably without actually listening, so don't guess at it or even flag it as unassessed, just leave it out entirely). Captions are also out of scope — nearly every candidate tested turns out to lack them, which makes it a non-differentiating, arbitrary check rather than a real signal; don't fetch, check, or mention captions anywhere in the workflow or report. Don't gate or rank candidates into skip/green-light tiers — every candidate gets the full write-up regardless of how good or bad its packaging is, since the goal is proven-demand topics to build a calendar from, not a shortlist of "easy wins."
What ships with it
3 files 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.
- 1mo ago First seen · 256 lines · 133 tokens per session scan A 3b1f51d08a0f
youtube-video-evaluator is a skill published in the GitHub repository ErickRamirezAU/claude-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 133 tokens to every session and 2,821 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Git Commit Helper
Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.
contract-and-proposal-writer
Generate professional, jurisdiction-aware business documents: freelance contracts, project proposals, SOWs, NDAs, and MSAs. Structured Markdown output with docx conversion instructions. Covers US (Delaware), EU (GDPR), UK, and DACH (German law) jurisdictions. Not a substitute for legal counsel — use as strong starting…
vpe-advisor
VP of Engineering advisory for startups: delivery throughput (DORA 4 metrics + bottleneck identification), engineering hiring funnel (sourcing → screen → onsite → offer conversion + time-to-fill + pipeline gap), engineering team structure (squad/tribe/chapter design + tech-lead manager-trigger thresholds), and…
chief-data-officer-advisor
Chief Data Officer advisory for startups: AI training data rights and consent provenance, data product strategy (warehouse vs lakehouse vs mesh, build-vs-buy), B2B customer-data-as-asset valuation and M&A readiness, data team org evolution. Use when deciding whether to train models on customer data, choosing data…
strategic-alignment
Cascades strategy from boardroom to individual contributor. Detects and fixes misalignment between company goals and team execution. Covers strategy articulation, cascade mapping, orphan goal detection, silo identification, communication gap analysis, and realignment protocols. Use when teams are pulling in different…