agentleFS
samulee003samulee003/agentic-ppt-skills/skills/presentation-story-grill/SKILL.md

presentation-story-grill

Skill0 starsChanged 24 days agoMITView on GitHub

Pressure-tests an approved story against audience relevance, evidence interpretation, counter-cases, repeated slides, and conclusion quality. Use when the story-grill gate is current for a presentation project or when a router asks for a story opposition pass that may return passed, needs_revision: product-grill, or needs_revision: evidence.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use when story-grill is the current gate.

    line 8
  2. Very specific:

    Read repo instructions, PRESENTATION-BRIEF.md, EVIDENCE-LEDGER.md, STORY.md, STORYBOARD.md, and cited source files before judging the story.

    line 10
  3. Distinctive:

    Always explore the files instead of asking the user for discoverable facts.

    line 11
  4. Distinctive:

    Use an interactive question path when a live consequential decision still needs human judgment.

    line 12
  5. Very specific:

    Use references/opposition-review.md for the autonomous opposition-review fallback when the user is unavailable or the remaining challenge …

    line 15
  6. Very specific:

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

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Grill the story

Use when story-grill is the current gate.

  • Read repo instructions, PRESENTATION-BRIEF.md, EVIDENCE-LEDGER.md, STORY.md, STORYBOARD.md, and cited source files before judging the story.
  • Always explore the files instead of asking the user for discoverable facts.
  • Use an interactive question path when a live consequential decision still needs human judgment.
  • Grill in rounds per ../make-presentation/references/grilling-rounds.md when consequential story decisions are unresolved: ask the whole frontier in one round.
  • Include a recommended answer with each question, worded so "yes" accepts it.
  • Use references/opposition-review.md for the autonomous opposition-review fallback when the user is unavailable or the remaining challenge is clear from the files.
  • State the strongest reasonable case against the story and what the opposition must concede.
  • Pressure-test why the audience should care, whether the thesis answers the right problem, whether the evidence supports the interpretation, what counter-evidence is missing, whether slides repeat or decorate, and whether the conclusion really follows.
  • Sort every finding into Act on, Consider, Noted, or Dismissed using ../make-presentation/references/review-buckets.md. An unresolved Act on finding blocks passed.
  • Return needs_revision: product-grill when the story exposes the wrong audience, problem, outcome, promise, or success test.
  • Return needs_revision: evidence when the story needs unsupported claims, missing counter-evidence, or weaker wording.
  • Return passed only when the remaining story is still useful, accurate, and distinctive after the strongest reasonable opposition.

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 product or stage decisions.
  • Log only decisions that materially change the brief, evidence, story order, prototype scope, or stage language.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.