critique

critique is a skill for Claude Code, Codex from lucastamoios/skills. It costs 61 tokens per session (808 once invoked), scanned A, original, MIT.

A short-video script critic that checks each line or beat against defined criteria and returns a structured verdict. It can mark a script as approved, needing revision, or needing a rethink.

In plain words
What is it for?
It helps evaluate scripts for Reels, Shorts, and TikTok, score their criteria, identify weak beats, and suggest replacement lines, visuals, or cuts.
Why use it?
It replaces vague feedback such as “make it more engaging” with specific problems and concrete fixes. It also records what already works so revisions do not remove it.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the marketing plugin — 8 skills shipped together

Good fit It helps evaluate scripts for Reels, Shorts, and TikTok, score their criteria, identify weak beats, and suggest replacement lines, visuals, or cuts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lucastamoios/skills/critique
Install

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.

Any agent
npx skills add lucastamoios/skills --skill critique
Clone the repo
git clone --depth 1 https://github.com/lucastamoios/skills

Made for: Claude Code, Codex.

Or install marketing, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

agentmods badge for critique

README.md
[![agentmods](https://agentmods.dev/badge/skills/lucastamoios/skills/critique/github.svg)](https://agentmods.dev/skills/lucastamoios/skills/critique)
Your own site
<a href="https://agentmods.dev/skills/lucastamoios/skills/critique"><img src="https://agentmods.dev/badge/skills/lucastamoios/skills/critique/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.

agentmods 80×15 button for critique

Your own site · 80×15
<a href="https://agentmods.dev/skills/lucastamoios/skills/critique"><img src="https://agentmods.dev/badge/skills/lucastamoios/skills/critique.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 808 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.00808
Opus 5.5 $0.00024 $0.00323
Sonnet 5.5 $0.00012 $0.00162
Haiku 4.5 $0.00006 $0.00081

Measured 4d ago against content hash da0b698bcd38, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

critique 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 4d 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.

plugins/marketing/skills/critique/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Critique

Replace the expert's manual back-and-forth ("better hook", "more visceral", "change these words") with a judgment that a script revision can act on. The expert's experience: the model knows the rules but does not follow them, so this skill checks each rule against the actual lines.

Contract

Follow the marketing contract. Input schema: critique.input. Output schema: critique.output. Output JSON only.

Method

  1. Load the built-in criteria, including its calibration examples. Criteria in input.criteria with the same id replace the built-in ones; new ids are added.
  2. Check every claim and every spoken example against the text of material (and creator.authority, creator.brand), not against the source the script declares. A claim sourced only from offer, angle or another skill's output fails claims_sourced. A spoken example that is not in material fails claims_sourced even when preparation calls it a demo. 2b. Score each criterion 0 (fails), 1 (partly), or 2 (meets), quoting the line or beat as evidence. Do not score from the angle or intentions; score what is written. Do not score length. Count the spoken words yourself (about 2.5 per second) and report the count and seconds in warnings, compared with the reference duration when reference_analysis gives one and with the calibration examples in the criteria. A script is never better for being shorter.
  3. For each failure, write an issue anchored to a beat_id with a concrete fix: a replacement line, a new visual, or a cut. "Make it more engaging" is not a fix. A fix never introduces a fact, number, date or example that is not in material; when one is needed, the fix is a question to the creator.
  4. Severity: blocker when the viewer would scroll away or be misled (no promise in the hook, unsourced claim stated as fact, nothing to show); major when the expert would ask for a change; minor for polish.
  5. List in keep what works, so the revision does not break it.
  6. Verdict:
    • approve: no blocker or major issue.
    • revise: fixable by rewriting lines and visuals.
    • rethink: the problem is upstream: the material is an opinion with no case, the angle has no so-what, or the reference mechanism cannot be executed with the creator's assets. Say which step in rethink_reason.
  7. Write rewrite_brief as direct instructions to marketing:script in revise mode, ordered by impact. 7b. When every blocker and major fix needs a fact only the creator can give (an outcome, a real example, how the thesis connects), return status: "needs_input" with the exact questions in missing_inputs, quoting his words. Keep the full result (scores, issues, verdict) for the record. Another script round without the fact only produces placeholders.
  8. If round equals max_rounds and the verdict would still be revise, return the verdict anyway and add a warning that a human should decide.

Read the full file on GitHub · 31 lines

Files

What ships with it

2 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.

Changes

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.

  1. 4d ago Changed · +2 lines da0b698bcd38
  2. 11d ago First seen · 29 lines · 61 tokens per session scan A 107c2fa39cce

Subscribe to this mod's changes

critique is a skill published in the GitHub repository lucastamoios/skills (0 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 808 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-05.

Related

critique compared with skills from other repositories

critique next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
critiquelucastamoios/skillsSkill05d agoMITA61Claude Code, Codex
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill395ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill80k9d agoMITA200Claude Code, Codex
next-cache-components-adoptionvercel/next.jsSkill144ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex