Automated summary
This skill provides a structured framework for evaluating the quality of a web presentation before release, combining a validation checklist with a multi-dimensional critique.
Strengths
- Explicit evaluation grid with priority levels (P0, P1, P2) to avoid vague decisions.
- Critique across five dimensions (fit, hierarchy, execution, specificity, restraint) for a balanced assessment.
- Anti-AI-slop audit to catch generic or excessive AI-generated artifacts.
- Clear verdict (PASS, REVISION_NEEDED, BLOCKED) with recommended return path.
Limitations
- Does not replace functional or performance testing.
- Requires a good understanding of the reference documents to be effective.
- Can be perceived as rigid if criteria are not adapted to the context.
Use this skill when a presentation or web page is claimed as complete and needs rigorous validation before sign-off.
Do not use it for pages still in development or for purely aesthetic reviews without a release decision need.
Security analysis
SafeThe skill is purely instructional, describing a review process for presentations. It contains no executable commands, no exfiltration, and no destructive actions. It references only internal reference files, posing no security risk.
No concerns found
How this analysis is madeExamples
I have a redesigned home page for our SaaS product. Run the full presentation critique on it using the checklist and five-dimension rubric. The target is the latest Figma mockup, version 2.1. Provide a verdict and blocking findings.This landing page uses heavy animations and parallax. Apply the anti-slop audit and five-dimension critique. The current build is in staging. Give me a PASS/REVISION/BLOCKED verdict.We have a slide deck exported to HTML for a client demo tomorrow. Use the presentation critique skill to check it. Focus on specificity and restraint. Flag any P0 blockers.description: "Review a WebsitePresent delivery before declaring it ready. Use when an HTML presentation, redesign, or motion-heavy page is about to be called done and needs checklist validation plus a five-dimension critique."
Presentation Critique
Use this skill before claiming a presentation artifact is complete.
This skill exists to make “looks okay” insufficient. It turns review into a real gate grounded in checklist evidence and a short, explicit critique rubric.
Read first
Before reviewing, read:
references/checklist.mdreferences/five-dimensions.mdreferences/anti-ai-slop.md
What this skill does
This skill checks whether a presentation output is:
- directionally faithful,
- structurally speakable,
- visually coherent,
- specific to the actual task,
- restrained enough to stay credible.
It does not replace implementation validation. It sits on top of implementation validation and raises the quality floor.
Workflow
1. Confirm the target being reviewed
Be clear about:
- which task
- which version
- which output surface
- what this round intended to improve
Without that, critique becomes vague and unfair.
2. Run the checklist gate
Use references/checklist.md.
Treat P0 as mandatory. If a P0 item fails, the work is not ready.
P1 items should normally be addressed before release unless the user explicitly accepts them. P2 items are improvement opportunities, not automatic blockers.
3. Run the five-dimension critique
Use references/five-dimensions.md.
Judge the output on:
- Fit
- Hierarchy
- Execution
- Specificity
- Restraint
If any one dimension is clearly weak, call it out directly and recommend where it should be repaired.
4. Run the anti-slop audit
Use references/anti-ai-slop.md.
The goal is not aesthetic purity. The goal is to catch lazy defaults, generic polish, fake specificity, and decorative excess before they ship.
5. Produce a release verdict
End with one of these:
- PASS
- REVISION_NEEDED
- BLOCKED
Do not soften the verdict just to avoid friction.
Output contract
Your review output should include:
- verdict
- blocking findings
- non-blocking risks
- strongest positive traits
- weakest dimension
- recommended return path
The return path should name the right owner when possible:
- SourceStrategist
- NarrativeArchitect
- ExperienceDirector
- MotionDirector
- FrontendProducer
- ReviewGuardian
Principles
- Evidence before vibes.
- P0 means mandatory, not aspirational.
- Specific critique beats broad praise.
- A pass still needs a reason.
- A block still needs a path forward.
What to avoid
- passing work because it is “mostly there”,
- only commenting on aesthetics,
- using generic praise instead of a real verdict,
- ignoring whether the page actually supports live explanation,
- treating anti-slop items as optional style preferences.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/presentation-critique-mrwakexj/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/presentation-critique-mrwakexj' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/presentation-critique-mrwakexj/download' --output '.skill-downloads/presentation-critique-mrwakexj/SKILL.md.part' && mv '.skill-downloads/presentation-critique-mrwakexj/SKILL.md.part' '.skill-downloads/presentation-critique-mrwakexj/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/presentation-critique-mrwakexj/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
ClickHouse Performance Comparison
Testing
Evaluate ClickHouse performance test results, check PR performance changes, compare with history, and assess whether a result is actionable.
Analyze CI Performance Reports
Testing
Analyze CI performance comparison reports for a ClickHouse PR. Cross-references master history to distinguish real regressions from flaky tests.
Santa Method
Testing
Multi-agent adversarial verification with two independent reviewers. Output is checked twice and iteratively fixed until both pass before shipping.