CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

jbaruch/speaker-toolkit

Twelve skills for conference speakers covering rhetoric analysis, talk authoring, deck building and export, CFP submissions, publishing, illustrations, shownotes, screencast production, and vertical shorts, informed by a 113-entry Presentation Patterns taxonomy (83 observable: 64 patterns + 19 antipatterns; 30 unobservable: 21 patterns + 9 antipatterns).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

SKILL.mdskills/presentation-creator/

name:
presentation-creator
description:
Develop or adapt a speaker's talk from an idea through an approved outline, narrative, and speaker notes, grounded in their rhetoric vault. Use for new talks, audience adaptations, rhetorical architecture, outline revisions, and outline-schema repair. Coordinate deck building and publishing when requested.
user_invocable:
Yes

Presentation Creator

Process steps in order. Do not skip ahead.

Resolve the absolute path of this loaded SKILL.md, then set speaker_toolkit_root to the plugin root two directories above the directory containing this file. Never derive it from the consumer working directory. Treat {speaker_toolkit_root} as absolute in every toolkit-owned command; talk, vault, and output paths remain consumer-owned. In an ACR install this skill's directory is named acr__jbaruch__speaker-toolkit__<skill>; there, read every {speaker_toolkit_root}/skills/<name>/ path and every relative link into another skill's <name>/ as sibling acr__jbaruch__speaker-toolkit__<name>/.

Step 0 — Select Entry

A new talk starts here. For an adaptation, also read adapting.md. Resume an existing outline at its first unfinished phase; preserve confirmed metadata and approvals.

Forward independent requests with the talk directory and requested action:

  • Build, edit, or export a deck: Skill(skill: "presentation-builder").
  • Resources, QR, or publishing coordination: Skill(skill: "presentation-publisher").
  • CFP or sessions catalog: Skill(skill: "cfp-writer").
  • Thumbnail or illustration: Skill(skill: "illustrations").
  • Shownotes or recording update: Skill(skill: "shownotes-publisher").

Finish here after a forwarded single task. An outline repair handoff reads outline-handoff.md, repairs only that outline, and returns to the caller; finish here.

For authoring, read runtime-and-context.md and resolve the read-only outline runtime. Load the rhetoric summary and speaker profile; open slide design guidance when a visual decision needs it. Read editorial-review.md before drafting or revising text. Apply it in each authoring phase before presenting a draft. Read phase0-intake.md to capture topic, audience, venue, and constraints. The vault's confirmed speaker intents govern style. Proceed immediately to Step 1.

Step 1 — Distill Intent

Read phase1-intent.md. Ask about missing context, one question at a time. Author the talk: metadata in outline.yaml, with root schema_version: 3; metadata fields live in phase3-content.md.

Use the profile's presentation-directory and live slug conventions. The outline is the source of truth; do not create a separate presentation spec. Review the title, thesis, and TL;DR before generating the partial narrative. Use outline-artifacts.md to generate partial narrative.md. Read it before presenting the TL;DR and metadata for approval. After the author confirms, proceed immediately to Step 2.

Step 2 — Architect the Talk

Read phase2-architecture.md. Select the rhetorical instruments jointly with the author. Record engine/theme, architecture, patterns, chapters, timing, and argument beats in the same outline.

Use pattern-menu.md to find relevant patterns. Before historical recommendations, read pattern-history-authorization.md and run its status command; require the domain for each historical claim. With no authorized history, use a flat current-taxonomy menu.

For requested AI illustrations, invoke Skill(skill: "illustrations") for strategy and the approved style anchor; resume here when it returns. Review the chapter titles and argument beats. Regenerate and read the partial narrative.md. Obtain approval of the argument and architecture before writing per-slide content. Proceed immediately to Step 3.

Step 3 — Develop Content

Read phase3-content.md. Fill slides[], interludes[], speaker notes, callbacks, builds, and typed placeholders in outline.yaml. Use the owner narration-rate contract linked there.

Review the slide copy, spoken lines, and production text. Validate and regenerate the four derived artifacts using outline-artifacts.md. Read the outputs before delivering the draft. Proceed immediately to Step 4.

Step 4 — Revise the Outline

Read phase4-guardrails.md. Apply feedback, review changed prose, regenerate artifacts, and run both structural and speaker-aware checks. Preserve emitted recurrence records. Keep current-outline warnings contextual. Flag intentional guardrail overrides without blocking them.

After the author declares the outline done, invoke Skill(skill: "cfp-writer") only to save approved submission materials if the catalog lacks this talk; resume here after the catalog update. Proceed immediately to Step 5.

Step 5 — Hand Off Approved Work

An outline-only request finishes here with the outline and derived artifact paths. For an authorized deck build, invoke Skill(skill: "presentation-builder") with the talk directory, approved outline, build-sheet, and chosen engine. Resume here after the author declares the slides done.

When publishing is in scope, invoke Skill(skill: "presentation-publisher") with the approved deck and talk directory. It returns a publishing report after verification. Finish here. Post-event requests enter the existing thumbnail or shownotes skill directly.

skills

presentation-creator

SKILL.md

README.md

tile.json