Agent skill

Deck Pipeline

by sruthir28 in sruthir28/enterprise-ai-skills

Multi-agent pipeline that builds a polished presentation deck from a single topic.

MITAuto-check passedDocuments & Office

Install Deck Pipeline

skills CLI
$ npx skills add sruthir28/enterprise-ai-skills --skill deck-pipeline -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sruthir28/enterprise-ai-skills deck-pipeline --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sruthir28/enterprise-ai-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/deck-pipeline .claude/skills/deck-pipeline && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deck-pipeline
GitHub stars
148
Token cost
~2.2k tokens
SKILL.md length
1,004 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Multi-agent pipeline that builds a polished presentation deck from a single topic.

  • You need a presentation that survives senior audiences
  • SKILL.md covers The Four Agents, Agent 1: Strategist, Agent 2: Builder and Agent 3: Critic, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Slides and decks

What it does

Deck Pipeline is an agent skill from sruthir28/enterprise-ai-skills. Multi-agent pipeline that builds a polished presentation deck from a single topic. Four agents work in sequence — Strategist defines the narrative, Builder creates the deck, Critic reviews it like a McKinsey EM, Fixer applies the top fixes. Use when you need a presentation that survives senior audiences.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Documents & Office, covering Slides and decks. The repository describes itself as: Open-source AI skills for enterprise professionals. McKinsey consulting frameworks, PM workflows, and practical tools. Currently for Claude, expanding to other LLMs. The licence is MIT.

When your agent uses it

  • You need a presentation that survives senior audiences
  • Tasks that involve Slides and decks

Example prompts

  • “/deck-pipeline”

What it can do on your machine

Read from SKILL.md and the folder at commit ae8fe60. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deck Pipeline loads about 2.2k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 1,004 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sruthir28/enterprise-ai-skills at commit ae8fe60, republished under its MIT licence (© sruthir28). 1,004 words, ~2,210 tokens.

Download SKILL.mdSave it as .claude/skills/deck-pipeline/SKILL.md (or your agent's skills folder).
name
deck-pipeline
description
Multi-agent pipeline that builds a polished presentation deck from a single topic. Four agents work in sequence — Strategist defines the narrative, Builder creates the deck, Critic reviews it like a McKinsey EM, Fixer applies the top fixes. Use when you need a presentation that survives senior audiences.

Deck Pipeline

A 4-agent pipeline that transforms a topic into a critique-proof presentation deck. Each agent has a distinct role — the output of one feeds the next. The result is a deck that has been strategically structured, built, reviewed, and fixed before you ever touch it.

The Four Agents

Topic
  │
  ▼
┌─────────────┐    ┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│ STRATEGIST  │───▶│   BUILDER   │───▶│   CRITIC    │───▶│    FIXER    │
│             │    │             │    │             │    │             │
│ Defines the │    │ Creates the │    │ Reviews like│    │ Applies the │
│ narrative   │    │ actual deck │    │ a McKinsey  │    │ top 3 fixes │
│ and outline │    │             │    │ EM at 2am   │    │             │
└─────────────┘    └─────────────┘    └─────────────┘    └─────────────┘

Agent 1: Strategist

Role: Define the audience, governing thought, and full slide outline before anything gets built.

What it does:

  • Identifies the target audience and what they care about
  • Defines the governing thought (the one sentence the whole deck proves)
  • Creates a 10-12 slide outline using Situation → Complication → Resolution structure
  • Each slide title is a claim, not a label ("RTD market will reach $42.5B by 2028" not "Market Overview")
  • Groups slides into clear narrative blocks

Output: A structured outline with:

  • Audience definition
  • Governing thought
  • Slide-by-slide titles with supporting points
  • Narrative flow markers (Situation / Complication / Resolution)

Why this matters: A deck without a strategy is just a collection of slides. The strategist ensures every slide earns its place in the argument.


Agent 2: Builder

Role: Convert the strategist's outline into an actual presentation.

What it does:

  • Takes the outline and creates the full deck content
  • Writes slide body text, data points, and supporting evidence
  • Structures visual elements: comparison tables, stat callout boxes, framework diagrams
  • Maintains consistent formatting and tone throughout
  • Ensures each slide has a clear "so what"

Output: A complete deck as a native .pptx (via python-pptx) with editable text and editable charts. Optional: markdown or formatted text as an intermediate artifact for review.

  • Claim-based titles on every slide
  • Data points with sources where available
  • Visual structure suggestions (tables, callout boxes, charts)
  • Section transitions between narrative blocks

Tools the Builder uses:

  • mckinsey-charts for native editable charts — bar+callout for single-number stories, stacked column for mix over time, waterfall for bridges. The audience can right-click → Edit Data inside PowerPoint. Use this instead of pasting chart images.
  • python-pptx for native text, tables, and layout. No screenshots, no image-based content — everything stays editable.

Tips for the Builder:

  • Stat callout boxes work well for key numbers (large font, contrasting color)
  • Comparison tables > bullet lists when presenting options
  • Keep body text to 3-5 points per slide maximum
  • Every data slide needs at least one source
  • Every quantitative slide uses a chart from mckinsey-charts, not a screenshot

Agent 3: Critic

Role: Review the deck like a senior engagement manager would — find every structural problem, weak argument, and missing element.

What it does:

  • Grades the overall deck (Green / Yellow / Red)
  • Reviews each slide with a status and specific issue
  • Identifies the top 3 fixes ranked by impact
  • Calls out one thing that works (to protect it)

Grading:

GradeMeaning
GreenReady for stakeholders
YellowFixable overnight, do not send as-is
RedCore argument broken, needs rework

What it checks:

  • Narrative flow and structure
  • Data rigor (sources, specificity, comparisons)
  • "So what" on every slide
  • Financial framing where needed
  • Claim-based titles vs topic titles
  • Frameworks vs bullet lists

Output: A critique document with section-by-section grades and top 3 prioritized fixes.

See the McKinsey Critic skill for the full review framework.


Agent 4: Fixer

Role: Apply the critic's top 3 fixes to produce the final deck.

What it does:

  • Takes the critic's specific fix instructions
  • Applies each fix to the deck
  • Documents what changed and why
  • Produces the final, polished version

Common fixes the Fixer applies:

  • Adding source footnotes to data slides
  • Rebuilding bullet lists as comparison tables (columns = options, rows = evaluation dimensions)
  • Adding financial frames (market size × share = revenue, margin analysis, investment required)
  • Sharpening headlines from descriptions to claims
  • Naming competitors instead of describing them generically
  • Linking disconnected slides back to the core argument

Output: The final deck with all fixes applied, plus a change log showing before → after for each fix.


Show full SKILL.md (383 more words)Show less

How to Use

Quick Start
"Build me a deck on [topic] for [audience]. Use the full pipeline — 
strategist, builder, critic, fixer."
With More Context
"I need a deck for [audience] arguing that [governing thought].

Key data points I have: [list any data, stats, or sources you want included]

Run the full pipeline: outline it, build it, critique it, fix it."
Step by Step (if you want control between stages)
Step 1: "Act as the strategist. Define the audience, governing thought, 
        and 10-slide outline for [topic]."

Step 2: "Now act as the builder. Turn this outline into a full deck."

Step 3: "Now act as the McKinsey critic. Grade this deck and give me 
        the top 3 fixes."

Step 4: "Now act as the fixer. Apply the top 3 fixes."

Example: What Each Agent Produces

Topic: "Should a premium coffee company enter the RTD (Ready-to-Drink) market?"

Strategist output:

  • Audience: Board of directors + CEO
  • Governing thought: "The premium RTD market offers a $425M revenue opportunity that plays to our existing capabilities — but only if we move within 12 months."
  • 10 slides: 3 Situation (market size, specialty growth, RTD growth) → 3 Complication (consumer shift, competition, first-mover window) → 4 Resolution (path comparison, RTD recommendation, sustainability, roadmap)

Builder output: Full deck with data, stat callouts, comparison tables

Critic output:

  • Grade: YELLOW
  • Fix 1: Cite every number (no source footnotes on any slide)
  • Fix 2: Slide 7 is a bullet list — needs comparison table (3 paths × 5 dimensions)
  • Fix 3: No financial frame — add $425M revenue at 1% share, $15-25M Phase 1 investment

Fixer output: Final deck with all sources added, comparison table rebuilt, financial frame on recommendation slide


When to Use

  • Board presentations and investor updates
  • Strategy recommendations to leadership
  • Product launch proposals
  • Market entry analysis
  • Any deck that needs to survive tough questions

What replaced the old Gamma path

Earlier versions of this repo paired the storyline with the Gamma API to generate finished decks. The current version uses native python-pptx + the mckinsey-charts skill instead. Reasons:

  • Editable, not generated. Charts are real PowerPoint chart objects, not images. The audience can change colors, edit data, copy to their own deck.
  • No third-party dependency. No Gamma account, no API key, no per-deck credit cost.
  • Better defaults. Single highlight color, no gridlines, claim-shaped titles — already wired into mckinsey-charts. The Gamma path required prompt-engineering the look every time.

The gamma-automation/ folder is preserved for reference but is deprecated.

Why a Pipeline Instead of One Prompt

A single "build me a deck" prompt produces mediocre work because it tries to think strategically AND write content AND self-critique simultaneously. By separating the roles:

  • The strategist focuses purely on narrative architecture
  • The builder focuses on content and visuals, with a clear brief
  • The critic is adversarial — it's not trying to protect what was built
  • The fixer has specific, prioritized instructions — not vague "make it better"

The result is a deck that has been through the equivalent of a junior consultant → senior associate → engagement manager review cycle.

© sruthir28, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in deck-pipeline of sruthir28/enterprise-ai-skills.

Open the folder on GitHubat commit ae8fe60

Compare with similar skills

Deck Pipeline next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deck Pipeline compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deck Pipeline this skillsruthir28/enterprise-ai-skills148—~2.2kAutomated safety check: PassMIT
Vibe to Agentic Engineering Frameworkshanraisshan/claude-code-best-practice67k—~3.3kAutomated safety check: PassMIT
Coauthor Briefpedrohcgs/claude-code-my-workflow1.7k—~2.9kAutomated safety check: NotesMIT
Image To Editable Pptningzimu/image-to-editable-ppt-skill2.8k—~4.3kAutomated safety check: PassMIT
Slidesfcakyon/claude-codex-settings1.2k1 repos~1.1kAutomated safety check: PassMIT
Ppt Image FirstNyxTides/ppt-image-first1.2k—~1.6kAutomated safety check: PassApache-2.0

Similar skills

  • Vibe to Agentic Engineering Framework

    shanraisshan/claude-code-best-practice

    Explains the conceptual model behind a presentation on moving from unstructured vibe coding to fully configured agentic engineering, including its 4-level scoring system and slide conventions.

    67k GitHub stars~3.3k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Coauthor Brief

    pedrohcgs/claude-code-my-workflow

    Generate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed since the last brief (git delta), the current state of each artifact…

    1.7k GitHub stars~2.9k tokensUpdated 11 days ago
    Documents & OfficeAuto-check: notes
  • Image To Editable Ppt

    ningzimu/image-to-editable-ppt-skill

    Rebuild slide images, scanned or image-based PPT/PPTX files, and PDF decks into object-level editable PowerPoint (.pptx), preserving speaker notes when supplied.

    2.8k GitHub stars~4.3k tokensUpdated 23 days ago
    Documents & OfficeAuto-check passed
  • Slides

    fcakyon/claude-codex-settings

    Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities.

    1.2k GitHub starsUsed in 1 repo~1.1k tokens
    Documents & OfficeAuto-check passed
  • Ppt Image First

    NyxTides/ppt-image-first

    Build presentation plans for PPT / slides / decks through a conversation-first workflow, then propose multiple visual directions with preview images before writing deck specs.

    1.2k GitHub stars~1.6k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Gpt Image2 Ppt

    JuneYaooo/gpt-image2-ppt-skills

    Generate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<collection/STYLEID.md or mimic a user-supplied .pptx template; outputs high-res slide PNGs and a 16:9 .pptx.

    1.3k GitHub stars~8.9k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check: notes

More from sruthir28/enterprise-ai-skills

All 14 skills in this repo
  • Storyline Builder

    sruthir28/enterprise-ai-skills

    McKinsey-style storyline framework for building presentation decks.

    148 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • AI Use Case Scorer

    sruthir28/enterprise-ai-skills

    Score and prioritize AI use cases for your own job. An agent skill from sruthir28/enterprise-ai-skills.

    148 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Decision Memo Builder

    sruthir28/enterprise-ai-skills

    Builds a 1-page decision memo (context → options → recommendation → risks → ask) enforcing McKinsey memo DNA — brutal brevity, SCP storyline clarity, decision-forcing output, evidence density.

    148 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Issue Tree Builder

    sruthir28/enterprise-ai-skills

    McKinsey-style issue tree framework for breaking down complex problems into MECE (Mutually Exclusive, Collectively Exhaustive) components.

    148 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Mckinsey Charts

    sruthir28/enterprise-ai-skills

    Generate McKinsey-style consulting charts as native python-pptx objects (editable inside PowerPoint).

    148 GitHub stars~999 tokensUpdated 1 mo ago
    Auto-check passed
  • Scpr Framework

    sruthir28/enterprise-ai-skills

    SCPR (Situation-Complication-Problem-Recommendation) framework for structured problem solving and executive communication.

    148 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Deck Pipeline

What does Deck Pipeline do?

Multi-agent pipeline that builds a polished presentation deck from a single topic. Deck Pipeline is an agent skill from sruthir28/enterprise-ai-skills. Multi-agent pipeline that builds a polished presentation deck from a single topic.

When should I use Deck Pipeline?

Deck Pipeline fits situations like: you need a presentation that survives senior audiences; tasks that involve Slides and decks.

How do I install Deck Pipeline in Claude Code?

Run `npx skills add sruthir28/enterprise-ai-skills --skill deck-pipeline -a claude-code`. Or copy the skill folder (deck-pipeline in sruthir28/enterprise-ai-skills) into .claude/skills/deck-pipeline in your project. Claude Code loads it when a task matches its description.

How do I install Deck Pipeline in Codex?

Run `npx skills add sruthir28/enterprise-ai-skills --skill deck-pipeline -a codex`. Or copy the skill folder (deck-pipeline in sruthir28/enterprise-ai-skills) into .agents/skills/deck-pipeline in your project. Codex loads it when a task matches its description.

Can I use Deck Pipeline in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sruthir28/enterprise-ai-skills --skill deck-pipeline -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deck-pipeline, .gemini/skills/deck-pipeline, .github/skills/deck-pipeline and .opencode/skills/deck-pipeline in your project.

What does Deck Pipeline need to run?

SKILL.md names no scripts, command-line tools or credentials: Deck Pipeline is instructions for the agent only.

Does Deck Pipeline access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deck Pipeline safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deck Pipeline use?

Deck Pipeline is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deck Pipeline use?

About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deck Pipeline?

Skills that share tags, products or a category with Deck Pipeline: Vibe to Agentic Engineering Framework (shanraisshan/claude-code-best-practice, 67k stars), Coauthor Brief (pedrohcgs/claude-code-my-workflow, 1.7k stars), Image To Editable Ppt (ningzimu/image-to-editable-ppt-skill, 2.8k stars) and Slides (fcakyon/claude-codex-settings, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deck Pipeline?

sruthir28 (a GitHub user) maintains it in sruthir28/enterprise-ai-skills, which has 148 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 1, 2026.

Source: sruthir28/enterprise-ai-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.