skill-deck
Generate slide deck presentations from briefs — use when you need slides, pitch decks, or visual summaries
Skill by mhdxbilal
Chalk Labs
Need help deploying skill-deck?
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/mhdxbilal-skill-deck
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
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/skill-deck
What's inside
- Skill name
skill-deck- Description
- Generate slide deck presentations from briefs — use when you need slides, pitch decks, or visual summaries
- License
- MIT
- Instructions
- 172 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Slide Deck Generator Generate professional slide decks from briefs with optional research, outline approval, and PPTX export. ## Prerequisites The `document-skills` plugin MUST be installed for PPTX rendering: ``` /plugin list | grep document-skills ``` If not installed, tell the user: ``` The document-skills plugin is required for PPTX generation. Install it with: /plugin install document-skills@anthropic-agent-skills ``` ## Pipeline (4 Steps) ### Step 1: Gather Brief Parse the user's topic and description. Use **AskUserQuestion** to clarify: **Question 1 - Audience:** - Executives / Board - Engineers / Technical - Investors / Fundraising - General / Mixed **Question 2 - Slide count target:** - Short (5-10 slides) - Standard (10-20 slides) - Extended (20+ slides) **Question 3 - Tone:** - Formal / Business - Technical / Detailed - Casual / Conversational If the user already provided clear context (e.g., "10-slide investor pitch deck about our Series A"), skip questions where the answer is obvious. ### Step 2: Research (Optional) If the topic needs external research or context gathering: - Use the **Task tool** with `Explore` or `general-purpose` subagent to gather relevant information - For deeper multi-AI research, suggest: "For comprehensive multi-provider research, run `/octo:discover [topic]` first, then `/octo:deck` to build slides from the results" - If the user provides their own content, notes, or a research file, skip this step entirely This step is OPTIONAL. Many decks are built from the user's own knowledge or existing documents. ### Step 3: Generate Outline Build a slide-by-slide outline in markdown format. Structure: ```markdown ## Slide 1: [Title Slide] - Presentation title - Subtitle / Date / Author ## Slide 2: [Agenda / Overview] - Key topics to cover ## Slide 3: [First Content Section] - Bullet point 1 - Bullet point 2 - Bullet point 3 ## Slide N: [Summary / Next Steps] - Key takeaways - Call to action ``` **IMPORTANT:** Present the outline to the user for approval using **AskUserQuestion**: - "Looks good, generate PPTX" — Proceed to Step 4 - "Add more slides" — Expand specific sections - "Change focus" — Restructure around different themes - "Start over" — Return to Step 1 This is the **wireframe gate** — the user MUST approve the outline structure before PPTX generation. ### Step 4: Render PPTX Once the outline is approved: 1. Use the `document-skills:pptx` skill to convert the approved markdown outline to PowerPoint 2. Each `##` heading becomes a slide 3. Bullet points under each heading become slide content 4. Save the PPTX file to the current working directory with a descriptive filename Example filename: `Series-A-Pitch-Deck-2026-02-14.pptx` ## Slide Structure Best Practices Apply these when generating outlines: - **Title slide**: Presentation name, subtitle, date, presenter - **Agenda slide**: 3-5 key topics (for decks > 7 slides) - **One idea per slide**: Keep slides focused - **5-7 bullets max**: Per slide for readability - **Summary slide**: Key takeaways at the end - **Next steps / CTA**: Final slide with clear actions ### By Audience Type **Executives / Board:** - Lead with business impact and metrics - Use "So what?" framing for every slide - Include financial implications - End with decisions needed **Engineers / Technical:** - Include architecture diagrams (describe for slides) - Show trade-offs and alternatives considered - Include implementation timelines - Reference technical specifications
From mhdxbilal/Ai, MIT.
More from mhdxbilal/Ai
- 0.496score
flow-spec
mhdxbilal
NLSpec authoring — use when you need a structured specification from multi-AI research and consensus
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
skill-decision-support
mhdxbilal
Present options with trade-offs for informed decision-making — use when choosing between approaches
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
skill-debug
mhdxbilal
Debug issues methodically — use when stuck on errors, test failures, or unexpected behavior
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
skill-cost-projections
mhdxbilal
Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
skill-copilot-provider
mhdxbilal
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
skill-code-review
mhdxbilal
Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
skill-claw
mhdxbilal
OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
skill-context-detection
mhdxbilal
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
skill-coverage-audit
mhdxbilal
Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
skill-extract
mhdxbilal
Reverse-engineer design systems, tokens, and components from live products or screenshots
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
octopus-architecture
mhdxbilal
System architecture and API design with multi-AI consensus — use for design reviews and new subsystems
SkillCFreshness: C★ 1Claude Code +9 - 0.482score
skill-content-pipeline
mhdxbilal
Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- May 19, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mhdxbilal/Ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mhdxbilal
- 0.496score
skill-decision-support
mhdxbilal
Present options with trade-offs for informed decision-making — use when choosing between approaches
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
skill-debug
mhdxbilal
Debug issues methodically — use when stuck on errors, test failures, or unexpected behavior
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
flow-spec
mhdxbilal
NLSpec authoring — use when you need a structured specification from multi-AI research and consensus
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
skill-context-detection
mhdxbilal
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
skill-claw
mhdxbilal
OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
skill-code-review
mhdxbilal
Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis
SkillCFreshness: C★ 1Claude 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 skill-deck 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
skill-deck. Agent Mart. https://agentmart.dev/skills/mhdxbilal-skill-deck (last updated 2026-10-24)