Borrowing it
Nothing to install: this file belongs to OpenVidu/openvidu.io. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/OpenVidu/openvidu.io/main/.claude/skills/blog-review/SKILL.mdgit clone --depth 1 https://github.com/OpenVidu/openvidu.ioWrote 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/openvidu/openvidu.io/blog-review)<a href="https://agentmods.dev/skills/openvidu/openvidu.io/blog-review"><img src="https://agentmods.dev/badge/skills/openvidu/openvidu.io/blog-review/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/openvidu/openvidu.io/blog-review"><img src="https://agentmods.dev/badge/skills/openvidu/openvidu.io/blog-review.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 | $0.00107 | $0.01200 |
| Opus 5 | $0.00053 | $0.00600 |
| Sonnet 5 | $0.00021 | $0.00240 |
| Haiku 4.5 | $0.00011 | $0.00120 |
Grade A, and why
blog-review 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 11d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenVidu Content Reviewer
Audit a written blog draft and return actionable, evidence-based improvements. Support two modes:
- Full-post review — evaluate the whole article end to end.
- Section review — evaluate only the requested section(s) plus continuity with surrounding context.
Ground rules
- DO NOT rewrite the whole post unless explicitly asked.
- DO NOT invent technical facts, benchmark numbers, or product capabilities.
- DO NOT give vague feedback ("improve flow") without a concrete example and fix.
- Always account for target audience, primary keyword, and buying-journey stage. If not given, infer and state the assumption.
Repo-specific validity checks (do these first — they block publish)
The conventions themselves live in
../blog-write/references/conventions.md — read it,
then verify the draft against each and run ovweb lint <post path> (it mechanically checks
the link forms, the excerpt rule, and the asset mirroring; trust its errors). Severities:
- File, naming & assets agree (per the naming invariant) → any mismatch is High severity.
Do NOT flag the
YYYY/MMplaceholder folders or the temporary date on a draft — that is the documented draft mechanism. DO flag: a published post whosedatedoesn't match its folders, a draft mixing placeholder and real year/month paths, a date-prefixed filename (old convention), or a literaldate: YYYY-MM-DDstring (aborts the build). - Frontmatter complete (all keys of the template).
titleanddescriptionmissing → High (build failure).cover_imagerecommended: raster (not svg) and actually present in the post's asset folder — flag a missing or broken value. - Covered by
llmstxt— a post at the conventional path needs nomkdocs.ymlchange; do not ask for one. A post outside that layout falls out ofllms.txt→ High; the fix is moving the file, never editing the glob. - Categories in
categories_allowed(read the list frommkdocs.yml) — unlisted breaks the build → High. Authors exist indocs/blog/.authors.yml. <!-- more -->— exactly one, right after the intro; missing breaks the build → High.- Poster image follows the H1;
#only-light/#only-darkpaired if used. Every referenced image exists on disk. - Links follow the conventions' link rules — including the excerpt exception (no
.mdMarkdown links before<!-- more -->; raw-HTML URL form there) and the Release-post exception (version-pinned domain-qualified URLs, flaglatestor.mdlinks there). - Admonition syntax —
!!! tip "..."with a space and 4-space-indented bodies.
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.
- 11d ago First seen · 73 lines · 107 tokens per session scan A b5ffd63a548b
blog-review is a skill published in the GitHub repository OpenVidu/openvidu.io (5 stars, last pushed today), licensed Apache-2.0. It adds 107 tokens to every session and 1,200 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
replit-deck
For product and technical management work: turn PRDs, roadmaps, RFCs, architecture reviews, and retros into decision documents. Built around the core query "pm-feature-business-case-deck", with product strategy lead judgment, buyer-ready proof, and this outcome: approve the feature, architecture, roadmap, or incident…
hps-true-blueprint
OpenDesign's engineering blueprint: how the sandbox, sidecar, and daemon fit — the system diagram and the invariants. Built as a decision-grade product management deck for engineering org.
design-critique
Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.
analytics-product
Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.
html-ppt-knowledge-arch-blueprint
OpenDesign's incident retro: the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups. Built as a decision-grade product management deck for engineering, SRE, leadership.
deck-open-slide-canvas
OpenDesign's architecture review: the local daemon + agent-runtime design, the tradeoffs, and the decision to lock. Built as a decision-grade product management deck for staff eng, tech leads, security.