ai-slide-templates
Use the Cogine AI ai-slide-templates repository to help users create polished slide decks from real content.
Skill by cogine-ai
Chalk Labs
Need help deploying ai-slide-templates?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/cogine-ai-ai-slide-templates
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: presentations, frontend, writing, productivity
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ai-slide-templates
What's inside
- Skill name
ai-slide-templates- Description
- Use the Cogine AI ai-slide-templates repository to help users create polished slide decks from real content. Trigger when the user asks to make slides, a PPT, a presentation deck, an HTML deck, choose a presentation template, use Cogine AI slide templates, or install/use the ai-slide-templates workflow in Codex, OpenClaw, or another agent.
- License
- Apache-2.0
- Instructions
- 179 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# AI Slide Templates Use this skill to turn a user's real material into a finished, browser-openable HTML slide deck using Cogine AI's `ai-slide-templates` repository. The repository is the source of truth: ```txt https://github.com/cogine-ai/ai-slide-templates ``` Always prefer the repository's current `AGENTS.md` over memory or this skill if they disagree. ## Core Workflow 1. Locate or clone the template repository. 2. Read `AGENTS.md` in that repository. 3. Use `INPUT_GUIDE.md` when the user's source material is incomplete, long-form, or scattered. 4. Read template metadata from `templates/*/template.json`. 5. Select the best template for the user's content and audience. 6. Clone the chosen template folder into the user's output workspace. 7. Replace demo content in `template.html` with the user's real content. 8. Open the finished HTML deck in a browser and verify basic rendering. 9. Return the absolute path to the finished `template.html`. If the agent cannot run shell or browser tools, give the user exact commands and file steps instead of claiming the deck was built. ## Repository Setup If the current workspace already contains `AGENTS.md`, `README.md`, and `templates/*/template.json` from `ai-slide-templates`, use that checkout. Otherwise guide the user to clone it: ```sh git clone https://github.com/cogine-ai/ai-slide-templates.git cd ai-slide-templates ``` Then read: ```sh cat AGENTS.md ``` When the user needs help preparing the brief or the input is a long article, script, transcript, memo, report, or scattered notes, also read: ```sh cat INPUT_GUIDE.md ``` Do not rely on a central template index. Scan per-template metadata: ```sh find templates -maxdepth 2 -name template.json ``` ## Template Selection Use `template.json` as the matching surface. Compare the user's brief against: - `mood` - `tone` - `occasion` - `formality` - `density` - `scheme` - `best_for` - `avoid_for` - `content_limits` - `layouts` - `layout_slots` - `slide_count` Templates have tones, not fixed industries. Reuse a template across domains when its mood, content density, and audience fit the user's need. If the user already picked a template or named a clear style, do not force options. Use that template unless it clearly conflicts with the content. If the user has not picked a visual direction, recommend the strongest fit. When multiple directions are plausible, show a short list of two to four choices with one-line reasons. When the source material is longer than the requested slide count, repetitive, or not already organized per slide, synthesize a slide outline before choosing or building the final deck. The outline should include slide titles, key messages, rough visual direction, and any blocking questions. Use `content_limits` to judge whether a template can carry the user's amount of text, bullets, cards, or slide count. If content exceeds the limits, split it across more slides instead of shrinking fonts, removing whitespace, or overfilling a layout. Use `layout_slots`, when present, to map the user's content into named fillable regions before editing HTML. Ask clarifying questions only when the answer changes the template or deck structure. Good questions are about audience, occasion, desired tone, content density, and light/dark preference. ## Deck Assembly After choosing a template: 1. Copy the full `templates/<slug>/` folder to the output location. 2. Keep the folder's `template.html` and `template.json` together. 3. Read `layout_slots` for the chosen layouts, when available. 4. Check `content_limits`, when available, and split overlong content across additional slides. 5. Edit `template.html` slide by slide. 6. Replace all placeholder titles, body copy, bullets, captions, quotes, names, dates, numbers, charts, stats, tables, and image placeholders. 7. If the user needs fewer slides, remove unneeded slides and update any visible counters. 8. If the user needs more slides, duplicate the closest matching layout and replace the content. 9. If a needed layout is missing, add a new slide that follows the same design system. Preserve the template's visual identity: - Fonts and imported font families - Color palette and CSS variables - Layout grid, spacing, and major positioning rules - Slide classes and component structures - Decorative vocabulary, borders, ornaments, textures, illustrations, and icon style - Navigation behavior, keyboard handlers, progress bars, and counters Do not recolor, substitute fonts, strip decoration, merge multiple templates, or redesign the deck unless the user explicitly asks for template maintenance work. ## Preview Mode Use previews when the user is unsure about visual taste, asks to compare options, or the presentation is high-stakes. Use the repository preview tooling: ```sh node scripts/preview.mjs --title "<deck title>" --subtitle "<short context>" <slug...>
From cogine-ai/cogine-dev-skillset, Apache-2.0.
More from cogine-ai/cogine-dev-skillset
- 0.566score
loop-on-pr-review-and-fix
cogine-ai
Monitor ready-for-review GitHub PRs and handle new, still-valid feedback.
SkillBFreshness: B★ 3Claude Code +9 - 0.544score
local-ultra-review
cogine-ai
Use when the user explicitly asks for a deep local code review, PR review, bug hunt, pre-merge review, or Ultra Review style review with high confidence…
SkillBFreshness: B★ 3Claude Code +9 - 0.519score
solus-product-master
cogine-ai
Use when discussing early product ideas, AI or Agent product directions, market observations, MVP scope, wedge markets, non-consensus opportunities, or when…
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
devex-review
cogine-ai
Use when auditing a live or implemented developer experience for APIs, CLIs, SDKs, MCP servers, plugins, integration guides, getting-started docs, or…
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
founder-office-hours
cogine-ai
Use when evaluating early product ideas, founder decisions, AI application concepts, wedge markets, target users, product scope, or design handoff before…
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
get-cookies
cogine-ai
Use when a site under review requires authentication and you need to import cookies from a real browser session into your local browser automation helper.
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
backlog-ready-spec
cogine-ai
Use when turning vague product requests, founder notes, GitHub issues, roadmap bullets, bug reports, or feature ideas into backlog-ready specs or executable…
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
ai-app-security-audit
cogine-ai
Use when auditing AI applications, LLM features, agent workflows, RAG systems, tool-calling code, prompt pipelines, model output handling, AI API keys, cost…
SkillCFreshness: C★ 3Claude Code +9 - 0.494score
gh-issue-priority-handoff
cogine-ai
Use when the user asks to triage GitHub issues, prioritize backlog work, verify issue readiness or staleness, or generate delegation-ready issue briefs for…
SkillCFreshness: C★ 3Claude Code +9 - 0.454score
image2-with-codex
cogine-ai
Route image generation to the local image2-with-codex HTTP service at http://127.0.0.1:4312, which delegates to the user's Codex CLI.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
investigate
cogine-ai
Systematic root-cause debugging.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
clawpacker
cogine-ai
Use when exporting, importing, packaging, cloning, restoring, or moving an OpenClaw agent between machines or instances, especially when the user mentions…
SkillDFreshness: D★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- May 15, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/cogine-ai/cogine-dev-skillset
- Website
- cogine.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cogine-ai
- 0.566score
loop-on-pr-review-and-fix
cogine-ai
Monitor ready-for-review GitHub PRs and handle new, still-valid feedback.
SkillBFreshness: B★ 3Claude Code +9 - 0.558score
feishu-channel-rules
cogine-ai
Lark/Feishu channel output formatting guidance.
SkillAFreshness: AClaude Code +9 - 0.544score
local-ultra-review
cogine-ai
Use when the user explicitly asks for a deep local code review, PR review, bug hunt, pre-merge review, or Ultra Review style review with high confidence…
SkillBFreshness: B★ 3Claude Code +9 - 0.519score
solus-product-master
cogine-ai
Use when discussing early product ideas, AI or Agent product directions, market observations, MVP scope, wedge markets, non-consensus opportunities, or when…
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
devex-review
cogine-ai
Use when auditing a live or implemented developer experience for APIs, CLIs, SDKs, MCP servers, plugins, integration guides, getting-started docs, or…
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
get-cookies
cogine-ai
Use when a site under review requires authentication and you need to import cookies from a real browser session into your local browser automation helper.
SkillCFreshness: C★ 3Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get ai-slide-templates running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
ai-slide-templates skill. Agent Mart. https://agentmart.dev/skills/cogine-ai-ai-slide-templates (last updated 2026-10-24)