agentsclimarketplace

Presentation stage grill

Skill samulee003/agentic-ppt-skills/skills/presentation-stage-grill

Agent skills that route a presentation from source to stage-ready through an 8-gate pipeline. Extracted from open-slide.

Install
npx -y skills add samulee003/agentic-ppt-skills --skill presentation-stage-grill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Tests a live prototype or deck as a talk by grilling actual renders, current notes, timing, transitions, and audience challenges, then produces a speaker script. Use when the stage-grill gate is current for a presentation project or when a router asks for speakability, trimming, audience-risk review, and `SPEAKER-SCRIPT.md`.

SKILL.md

2.5 KB, as published. Nobody here has run it

Grill the talk on stage

Use when stage-grill is the current gate.

  • Read repo instructions, PRESENTATION-BRIEF.md, STORY.md, STORYBOARD.md, GRILL-LOG.md, current speaker notes, and actual page renders before judging the talk.
  • Always explore the files instead of asking the user for discoverable facts.
  • Ask one question at a time when a consequential stage decision is unresolved.
  • Include a recommended answer with each question.
  • Use references/autonomous-stage.md for the autonomous fallback when the user is unavailable (headless run) or the remaining stage decisions are resolvable from the deck and upstream artifacts — apply references/stage-questions.md yourself, resolve each finding with a concrete change and confidence level, and flag any low-confidence load-bearing edit for later human review instead of silently rewriting it.
  • When the user refers to the page they're currently viewing without naming it, resolve it through the engine's "current page" mechanism (e.g. current-slide for open-slide) before judging.
  • Use actual renders and current speaker notes, not outline-only summaries.
  • Apply references/stage-questions.md to representative prototype pages first, then to the full deck when available.
  • Enforce presenter-language constraints, timed trimming, and existing-versus-remaining distinction.
  • Separate what the audience can see immediately from what only works after narration.
  • Produce SPEAKER-SCRIPT.md from templates/SPEAKER-SCRIPT.md with approved wording, timing, likely audience challenge, and Q&A risk.
  • Return pages for revision when density, wording, transition logic, or defensibility breaks the live talk.
  • Return passed only when the talk is readable, speakable, timed, defensible, and audience-appropriate.

Write only consequential decisions to GRILL-LOG.md from ../presentation-product-grill/templates/GRILL-LOG.md.

  • Append new decisions without deleting or rewriting entries from other grill phases or earlier runs.
  • Preserve existing decisions when revisiting the stage-grill gate.
  • Log only changes that materially affect wording, timing, page order, trims, likely objections, or presenter language.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.