reviewing-presentation
Reviews a slide deck for factual accuracy and sourcing, language, legibility, accessibility, timing, and how the rendered slides look, and reports what to fix…
Skill by ken-guru
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ken-guru-reviewing-presentation
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, presentations, frontend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/reviewing-presentation
What's inside
- Skill name
reviewing-presentation- Description
- Reviews a slide deck for factual accuracy and sourcing, language, legibility, accessibility, timing, and how the rendered slides look, and reports what to fix where. Use when someone asks to check, review, proofread, or critique a presentation or slide deck, in Marp, HTML, PDF, or PowerPoint.
- License
- MIT
- Metadata
- version: 3.1.0 · changelog: https://github.com/ken-guru/skills/blob/main/skills/presentation/CHANGELOG.md
- Instructions
- 34 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (7)
- SKILL.md
- accessibility-bar.md · references/
- deck-folder.md · references/
- findings.md · references/
- deck.mjs · scripts/
- reviewing-presentation.mjs · scripts/
- reviewing-presentation.test.mjs · tests/
SKILL.md (first lines)
# Reviewing a presentation Find what would embarrass the speaker or exclude part of the audience, and say which stage fixes each problem. Review the deck as it is; change nothing unless the person asks. Script paths below are relative to this skill's folder. Run each as one command with the folder's absolute path in front, never chained with `&&`, `$(…)`, or heredocs. ## What you can review - **A Deck Folder** (see [references/deck-folder.md](references/deck-folder.md)): the full review, using `deck.md`, `sources.md`, `brief.md`, and the rendered `dist/`. - **Any other deck** (Marp, HTML, PDF, or PowerPoint): review what the format exposes. Look at rendered pages as images. For a PPTX, read the slide and notes XML inside the file. Say which checks the format did not allow (for example: no speaker notes in a PDF, no sources to trace). ## Workflow ``` - [ ] 1. Scripted checks run - [ ] 2. Facts and sources traced - [ ] 3. Language read - [ ] 4. Rendered slides looked at - [ ] 5. Accessibility judged - [ ] 6. Timing estimated - [ ] 7. Findings reported ``` 1. **Scripted checks.** If `rendering-slides` is installed, run its `check` command on the Deck Folder and include its findings. If it is not, check the Accessibility Bar's scripted rules yourself from [references/accessibility-bar.md](references/accessibility-bar.md). 2. **Facts and sources.** Every factual claim in the slides and notes cites a Source Set entry that actually supports it, with the same numbers and wording. Flag claims with no citation, citations that do not support the claim, and numbers that differ from the source. Opinions and personal experience must be labelled as such. 3. **Language.** Read every heading, body, and note. If `unslop` is installed, use it to find prose problems, with the Brief's tone, prefer, and avoid preferences. Otherwise look for filler, inflated claims, jargon the audience will not know, inconsistent terms, typos, and a voice that does not match the speaker. 4. **Rendered slides.** Look at every slide image (`dist/slides/`, or render them): text overflowing or too small to read, overlapping elements, unreadable contrast, a visual that does not make its point, a missing "AI-generated illustration" label. 5. **Accessibility judgement.** The scripts cannot judge these; you must: headings that say what the slide is about, alt text that says what matters in the image, a reading order that makes sense, colour never the only way to tell things apart, no text inside images, and link text that is clear in context. 6. **Timing.** Run `node scripts/reviewing-presentation.mjs timing --deck <folder>`. It estimates speaking time from the notes, compares it with the Brief's length, and says when the talk runs over or well short. 7. **Report** the Findings in the conversation, using [references/findings.md](references/findings.md): grouped by the stage that owns each fix, most serious first, each with the slide, the problem, and the fix. An unsupported claim goes back to Research: say what evidence is missing, and that `researching-sources` (if installed) can find it, rather than suggesting the claim simply be deleted.
From ken-guru/skills, MIT.
More from ken-guru/skills
- 0.592score
drafting-slides
ken-guru
Drafts a slide deck as one editable Marp Markdown file, with a heading and speaker notes on every slide, citations for every factual claim, and a plan for…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
creating-charts
ken-guru
Creates static, accessible data charts (bar, line, scatter, area, and more) from a data file with Vega-Lite, checks their text is readable at final size, and…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
creating-diagrams
ken-guru
Creates legible diagrams from D2 source (flows, architectures, sequences, decision paths) and checks they stay readable at their final size.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
generating-images
ken-guru
Generates illustrations and photos with an AI image provider (Gemini or OpenAI) after the person approves the cost, and marks every result as AI-generated.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
planning-presentation
ken-guru
Plans a presentation with the person: interviews them until the audience, goal, and premises are clear, records the Brief, and builds an approved storyline…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
rendering-slides
ken-guru
Renders a Marp slide deck to HTML, a tagged PDF, and a speaker-notes script with a polished theme, installing the pinned tools it needs and checking the result.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
researching-sources
ken-guru
Finds, vets, and organises credible sources for a question into a Source Set, judging each source's credibility and turning conflicting claims into explicit…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
setup-devcontainer
ken-guru
Generate a shared devcontainer (Ubuntu base image, Node, GitHub CLI, one persistent config volume) in the current repo — one container every AI CLI installs…
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
setup-copilot-devcontainer
ken-guru
Install GitHub Copilot CLI into an existing shared devcontainer generated by the setup-devcontainer skill — its own install step, optional YOLO guidance, and…
SkillAFreshness: A★ 1Claude Code +9 - 0.583score
setup-codex-devcontainer
ken-guru
Install Codex into an existing shared devcontainer generated by the setup-devcontainer skill — its own install step, sandbox capability grant, optional YOLO…
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
unslop
ken-guru
Load when the user asks to edit prose for a more natural voice while preserving meaning, tone, technical precision, and structured output.
SkillBFreshness: B★ 1Claude Code +9 - 0.543score
setup-antigravity-devcontainer
ken-guru
Install Antigravity into an existing shared devcontainer generated by the setup-devcontainer skill — its own install step, optional YOLO alias, optional link…
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 6
- Last commit (this folder)
- Oct 21, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 3.1.0
- License
- MIT
- Repository
- github.com/ken-guru/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ken-guru
- 0.592score
creating-charts
ken-guru
Creates static, accessible data charts (bar, line, scatter, area, and more) from a data file with Vega-Lite, checks their text is readable at final size, and…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
creating-diagrams
ken-guru
Creates legible diagrams from D2 source (flows, architectures, sequences, decision paths) and checks they stay readable at their final size.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
generating-images
ken-guru
Generates illustrations and photos with an AI image provider (Gemini or OpenAI) after the person approves the cost, and marks every result as AI-generated.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
planning-presentation
ken-guru
Plans a presentation with the person: interviews them until the audience, goal, and premises are clear, records the Brief, and builds an approved storyline…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
rendering-slides
ken-guru
Renders a Marp slide deck to HTML, a tagged PDF, and a speaker-notes script with a polished theme, installing the pinned tools it needs and checking the result.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
drafting-slides
ken-guru
Drafts a slide deck as one editable Marp Markdown file, with a heading and speaker notes on every slide, citations for every factual claim, and a plan for…
SkillAFreshness: A★ 1Claude Code +9
Cite this page
reviewing-presentation skill. Agent Mart. https://agentmart.dev/skills/ken-guru-reviewing-presentation (last updated 2026-10-24)