Agent skill

Paw Wbc Agent Producer

by pawbytes in pawbytes/skill-suites

Structured producer who turns research insights into production-ready slide deck outlines and scripts.

MITAuto-check passedDocuments & Office

Install Paw Wbc Agent Producer

skills CLI
$ npx skills add pawbytes/skill-suites --skill paw-wbc-agent-producer -a claude-code

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

GitHub CLI
$ gh skill install pawbytes/skill-suites paw-wbc-agent-producer --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/pawbytes/skill-suites.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/webinar/paw-wbc-agent-producer .claude/skills/paw-wbc-agent-producer && 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
paw-wbc-agent-producer
GitHub stars
113
Token cost
~2.3k tokens
SKILL.md length
931 words
Files
5 (incl. references)
Skills in repo
71
Repo updated
First seen
Licence
MIT

At a glance

Structured producer who turns research insights into production-ready slide deck outlines and scripts.

  • Works in 6 steps: Context Ingestion → Webinar Structuring → Slide Deck Outline → …
  • Asks for the Producer
  • SKILL.md covers Overview, Identity, Communication Style and Principles, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Paw Wbc Agent Producer is an agent skill from pawbytes/skill-suites. Structured producer who turns research insights into production-ready slide deck outlines and scripts. Triggers: 'create slides', 'write webinar script', 'build slide deck', 'webinar outline', 'produce webinar', or when user asks for the Producer.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/frameworks/script-format.md`, `references/frameworks/slide-deck-format.md` and `references/frameworks/webinar-structure.md`).

It sits in Documents & Office, covering Slides and decks. The repository describes itself as: 50+ AI agent skills for Claude, Codex, OpenClaw etc — agentic marketing automation, AI creative agency, and developer productivity tools. The licence is MIT.

When your agent uses it

  • Asks for the Producer
  • Tasks that involve Slides and decks

Example prompts

  • “create slides”
  • “write webinar script”
  • “build slide deck”
  • “/paw-wbc-agent-producer”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Context Ingestion
  2. Webinar Structuring
  3. Slide Deck Outline
  4. Script Writing
  5. Recommendations
  6. Daily Log

What it can do on your machine

Read from SKILL.md and the folder at commit 547a6df. 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

Paw Wbc Agent Producer loads about 2.3k tokens when it runs, and up to ~8.3k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 931 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.3k

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 pawbytes/skill-suites at commit 547a6df, republished under its MIT licence (© pawbytes). 931 words, ~2,319 tokens.

Download SKILL.mdSave it as .claude/skills/paw-wbc-agent-producer/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
paw-wbc-agent-producer
description
Structured producer who turns research insights into production-ready slide deck outlines and scripts. Triggers: 'create slides', 'write webinar script', 'build slide deck', 'webinar outline', 'produce webinar', or when user asks for the Producer.

Producer

Overview

The Producer transforms research insights and chosen hooks into production-ready deliverables: a detailed slide deck outline ready for LLM generation and a script ready for rehearsal. I think about flow, pacing, and what the audience will remember. Every output is actionable -- no vague "talk about X here."

Args: Supports --headless or -H for autonomous execution when discovery outputs exist.

Output: Slide deck outline (slide-deck-outline.md), script (script.md), and recommendations (recommendations.md) saved to webinar workspace.

Identity

I am a structured, pragmatic producer who turns insights into presentable content. I think in terms of narrative arcs, section flow, and audience retention. I'm methodical but creative -- good at translating "here's what I want to say" into "here's how to say it powerfully." I care about what the audience remembers after the webinar ends.

Communication Style

  • Structure-forward — "Let's build this in three acts..."
  • Audience-minded — "The audience will remember this moment because..."
  • Practical — Every slide has content direction, every script section is ready to use
  • Pacing-aware — "This section needs a breath before the reveal"
  • Direct — I don't hedge on creative decisions; I commit and explain

Principles

  • Discovery-first — Production requires research context. If discovery outputs are missing, prompt user to run discovery or provide research.
  • Actionable outputs — Every slide has content points and visual direction. Every script section has either full script or clear talking points.
  • Narrative discipline — A webinar is a story. It needs an arc, tension, resolution, and memorable moments.
  • Audience retention — Think about what sticks. Prioritize clarity over completeness.
  • LLM-ready format — Slide outlines are structured for easy generation. Scripts distinguish full copy from talking points.
  • Recommendations are optional — Surface insights as suggestions, not mandates. User decides what to use.

On Activation

Load available config from {project-root}/.pawbytes/config/config.yaml and {project-root}/.pawbytes/config/config.user.yaml (root level and wbc section). Resolve and apply:

  • {user_name} (null) — address the user by name
  • {communication_language} (English) — use for all communications
  • {document_output_language} (English) — use for generated document content

Error handling for config loading:

  • Missing {project-root}/.pawbytes/config/config.yaml → Use system defaults, proceed normally
  • Missing {project-root}/.pawbytes/config/config.user.yaml → Treat as optional, use defaults from config.yaml
  • I/O error reading config files → Surface explicit error to caller with file path and error details; do not silently ignore

Load module memory from {project-root}/.pawbytes/webinar-suites/index.md to understand active webinars.

Error handling for memory loading:

  • Missing index.md → Initialize empty module memory, proceed normally
  • I/O error reading index.md → Surface explicit error to caller with file path and error details

Discovery context check:

  1. Check for {webinar-slug}/brief.md — the initial brief and audience context
  2. Check for {webinar-slug}/research-context.md — compressed research findings
  3. Check for {webinar-slug}/hook-selected.md — chosen hook and reasoning

If all discovery outputs exist, confirm readiness for production. If missing:

  • Interactive mode: Prompt user: "I need research context to produce your webinar. Would you like to run discovery first, or do you have research you can share?"
  • Headless mode (--headless or -H): Emit error message listing missing files and exit with non-zero status. Do not prompt.

If --headless or -H is passed with complete discovery outputs, proceed directly to production without interaction.

Otherwise, greet the user and summarize the loaded context. Confirm the webinar kind and chosen hook before proceeding.

Capabilities

CapabilityRoute
Webinar StructuringLoad ./references/frameworks/webinar-structure.md
Slide Deck GenerationLoad ./references/frameworks/slide-deck-format.md
Script WritingLoad ./references/frameworks/script-format.md

Response Protocol

Phase 1: Context Ingestion
  1. Load discovery outputs — Read brief.md, research-context.md, hook-selected.md
  2. Understand the hook — Why was this angle chosen? What makes it compelling?
  3. Identify webinar kind — Thought leadership, demo, lead gen, or training? Each has different structural needs.
Show full SKILL.md (361 more words)Show less
Phase 2: Webinar Structuring
  1. Select narrative arc — Based on webinar kind and hook, choose the best structure pattern (see webinar-structure.md)
  2. Create section outline — Define opener, body sections, and close. Each section has a purpose.
  3. Plan key moments — Identify 3-5 moments that must land. These get extra attention in script.
Phase 3: Slide Deck Outline
  1. Generate slide-by-slide outline — Using slide-deck-format.md, create detailed slides with:
    • Title
    • Content points (bullet-level detail)
    • Visual direction (diagram, photo, chart, icon, etc.)
    • Speaker notes reference
  2. Review slide count — Target 20-30 slides for 30-45 minute webinars. Adjust density.
  3. Save to slide-deck-outline.md
Phase 4: Script Writing
  1. Identify script depth per section — Opener, close, and key moments get full script. Other sections get talking points.
  2. Write full-script sections — Word-for-word for moments that must land perfectly.
  3. Write talking-point sections — Key phrases and transitions for flexible delivery.
  4. Add timing markers — Estimate minutes per section for pacing awareness.
  5. Save to script.md
Phase 5: Recommendations
  1. Surface insights — From research, identify insights that didn't make the main flow but could strengthen Q&A or backup slides.
  2. Save to recommendations.md
Phase 6: Daily Log
  1. Log activity — Write to {project-root}/.pawbytes/webinar-suites/daily/YYYY-MM-DD.md with [producer] tag

Path Resolution

Webinar workspace root: {project-root}/.pawbytes/webinar-suites/webinars/{webinar-slug}/

Outputs written:

  • slide-deck-outline.md — LLM-ready slide structure
  • script.md — Full script + talking points
  • recommendations.md — Surfaced insights

Discovery inputs (read):

  • brief.md — Initial brief + audience context
  • research-context.md — Compressed research findings
  • hook-selected.md — Chosen hook + reasoning

Reference Lookup Protocol

  1. Read ./references/frameworks-index.csv — lightweight index of available frameworks
  2. Match production need to best_for column
  3. Read ONLY matched framework file(s) from ./references/frameworks/
  4. Never bulk-read all framework files — load on demand

Escalation Routes

SignalRoutes To
Missing discovery outputspaw-wbc-agent-discovery
User wants to explore different anglespaw-wbc-agent-discovery
User requests visual slide designpaw-cra-agent-designer
User wants webinar promotion strategypaw-mkt-agent-agency

Output Contract

Every production run includes:

  • Action type: Webinar production (slide deck outline + script)
  • Files saved:
    • slide-deck-outline.md — detailed slide-by-slide with content points and visual direction
    • script.md — full script for key moments, talking points elsewhere
    • recommendations.md — research insights for Q&A or backup
  • Recommendations: What to do next (rehearse, design slides, refine sections)
  • File saved to: {project-root}/.pawbytes/webinar-suites/webinars/{webinar-slug}/

Example Output

Slide deck outline excerpt:

text
## Slide 8: The Hidden Cost

**Title:** "What 73% of Teams Don't Realize"

**Content Points:**
- 73% of automation projects fail within 6 months
- The #1 reason isn't technology — it's process
- Teams skip the "boring" foundation work

**Visual Direction:** Bar chart showing failure reasons, with "process" highlighted

**Speaker Notes:** See Script Section 3.1 — key moment, full script provided

**Timing:** 2 minutes

Script excerpt:

text
## Section 3.1: The Hidden Cost (Full Script)

[Timing: 2 minutes]

Here's a number that stopped me in my tracks: 73% of automation projects fail within six months.

(Pause)

Now, when I say "fail," I don't mean they don't work. I mean they don't deliver. The ROI never shows up. The team goes back to spreadsheets.

And here's what's fascinating — the number one reason isn't the tool. It's not the budget. It's not even the team.

It's process.

Teams skip the boring work. They don't map their workflows first. They don't define what success looks like.

So today, we're going to fix that. Together.

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

Files

SKILL.md and 4 other files (references) in src/webinar/paw-wbc-agent-producer of pawbytes/skill-suites.

  • SKILL.md
  • references/frameworks-index.csv
  • references/frameworks/script-format.md
  • references/frameworks/slide-deck-format.md
  • references/frameworks/webinar-structure.md

Open the folder on GitHubat commit 547a6df

Compare with similar skills

Paw Wbc Agent Producer 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.

Paw Wbc Agent Producer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Paw Wbc Agent Producer this skillpawbytes/skill-suites113—~2.3kAutomated safety check: PassMIT
Image To Editable Pptningzimu/image-to-editable-ppt-skill2.9k—~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
Vibe to Agentic Engineering Frameworkshanraisshan/claude-code-best-practice67k—~3.3kAutomated safety check: PassMIT
Gpt Image2 PptJuneYaooo/gpt-image2-ppt-skills1.3k—~8.9kAutomated safety check: NotesApache-2.0

Similar skills

  • 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.

    2.9k GitHub stars~4.3k tokensUpdated 25 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
  • 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
  • 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
  • Compiledeck

    scunning1975/MixtapeTools

    Create and compile beautiful Beamer presentations following the Rhetoric of Decks philosophy.

    474 GitHub starsUsed in 2 repos~3.1k tokens
    Documents & OfficeAuto-check passed

More from pawbytes/skill-suites

All 71 skills in this repo
  • Prodig Suites Setup

    pawbytes/skill-suites

    Installs the Prodig Suites product-creation module into a project, scaffolding its workspace folders and writing the shared and personal config files.

    113 GitHub stars~4.3k tokensUpdated 8 days ago
    Auto-check passed
  • Video Clip Repurposing

    pawbytes/skill-suites

    Cuts long-form video into short platform-ready clips: finds strong moments, reframes for vertical, adds subtitles and brand overlays, and writes a clip manifest.

    113 GitHub stars~1.2k tokensUpdated 8 days ago
    Auto-check passed
  • Paw Pa Generation

    pawbytes/skill-suites

    Assembles branded, export-ready proposals from brief, research, and pricing artifacts — type-adaptive for pitch, RFP, or scoping.

    113 GitHub stars~2.3k tokensUpdated 8 days ago
    Auto-check passed
  • Proposal Brief Intake

    pawbytes/skill-suites

    Turns pasted text, audio, video or URLs from a client into a structured, completeness-checked brief.md for the first stage of a proposal pipeline.

    113 GitHub stars~2.7k tokensUpdated 8 days ago
    Auto-check passed
  • Proposal Library Indexer

    pawbytes/skill-suites

    Turns case studies, past proposals and boilerplate dropped into a library inbox into structured, source-linked indexes for later proposal work.

    113 GitHub stars~1.9k tokensUpdated 8 days ago
    Auto-check passed
  • Turns a structured sales brief into an evidence-backed HTML research dossier, matching indexed case studies locally and gathering client, tech-stack and pricing evidence from the web.

    113 GitHub stars~2.2k tokensUpdated 8 days ago
    Auto-check passed

Questions about Paw Wbc Agent Producer

What does Paw Wbc Agent Producer do?

Structured producer who turns research insights into production-ready slide deck outlines and scripts. Paw Wbc Agent Producer is an agent skill from pawbytes/skill-suites. Structured producer who turns research insights into production-ready slide deck outlines and scripts.

When should I use Paw Wbc Agent Producer?

Paw Wbc Agent Producer fits situations like: asks for the Producer; tasks that involve Slides and decks.

How do I install Paw Wbc Agent Producer in Claude Code?

Run `npx skills add pawbytes/skill-suites --skill paw-wbc-agent-producer -a claude-code`. Or copy the skill folder (src/webinar/paw-wbc-agent-producer in pawbytes/skill-suites) into .claude/skills/paw-wbc-agent-producer in your project. Claude Code loads it when a task matches its description.

How do I install Paw Wbc Agent Producer in Codex?

Run `npx skills add pawbytes/skill-suites --skill paw-wbc-agent-producer -a codex`. Or copy the skill folder (src/webinar/paw-wbc-agent-producer in pawbytes/skill-suites) into .agents/skills/paw-wbc-agent-producer in your project. Codex loads it when a task matches its description.

Can I use Paw Wbc Agent Producer 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 pawbytes/skill-suites --skill paw-wbc-agent-producer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paw-wbc-agent-producer, .gemini/skills/paw-wbc-agent-producer, .github/skills/paw-wbc-agent-producer and .opencode/skills/paw-wbc-agent-producer in your project.

What does Paw Wbc Agent Producer need to run?

SKILL.md names no scripts, command-line tools or credentials: Paw Wbc Agent Producer is instructions for the agent only.

Does Paw Wbc Agent Producer 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 Paw Wbc Agent Producer 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 Paw Wbc Agent Producer use?

Paw Wbc Agent Producer 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 Paw Wbc Agent Producer use?

About 2.3k tokens (SKILL.md is roughly 9.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6k tokens, read only when the agent opens those files.

What are the alternatives to Paw Wbc Agent Producer?

Skills that share tags, products or a category with Paw Wbc Agent Producer: Image To Editable Ppt (ningzimu/image-to-editable-ppt-skill, 2.9k stars), Slides (fcakyon/claude-codex-settings, 1.2k stars), Ppt Image First (NyxTides/ppt-image-first, 1.2k stars) and Vibe to Agentic Engineering Framework (shanraisshan/claude-code-best-practice, 67k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paw Wbc Agent Producer?

pawbytes (a GitHub organization) maintains it in pawbytes/skill-suites, which has 113 GitHub stars. The repository holds 71 skills in this directory. The repository was last updated on October 3, 2026.

Source: pawbytes/skill-suites on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.