Four-skill presentation system: ingest talks into a rhetoric vault, run interactive clarification, generate a speaker profile, then create new presentations that match your documented patterns. Includes an 88-entry Presentation Patterns taxonomy for scoring, brainstorming, and go-live preparation.
96
93%
Does it follow best practices?
Impact
97%
1.21xAverage score across 30 eval scenarios
Advisory
Suggest reviewing before use
Morgan Lee is a frequent conference speaker who has just finished a first draft of a 45-minute talk for DevRelCon 2025. Morgan wants a structured quality audit of the draft before presenting it to their co-author. The audit should check every standard guardrail category and flag any violations.
Produce a guardrail report saved to guardrail-report.md covering all standard check categories: slide budget, structure balance, branding, profanity, data attribution, time-sensitive content, closing completeness, cut lines, and anti-patterns. Each check should be labeled with a clear pass/warn/fail verdict. Include a pattern score projection (an estimated numeric score).
Use the speaker profile and draft outline provided below.
The following files are provided as inputs. Extract them before beginning.
=============== FILE: inputs/speaker-profile.json =============== { "schema_version": 1, "generated_date": "2025-02-15", "speaker": { "name": "Morgan Lee", "handle": "@mlee_devrel", "shownotes_url_pattern": "speaking.morganlee.io/{slug}" }, "rhetoric_defaults": { "default_duration_minutes": 45, "profanity_calibration": "none", "on_slide_profanity": false, "three_part_close": true, "modular_design": true }, "design_rules": { "footer": { "pattern": "@mlee_devrel | #{conference_hashtag} | speaking.morganlee.io/{slug}" }, "slide_numbers": "never" }, "guardrail_sources": { "slide_budgets": [ {"duration_minutes": 20, "max_slides": 30, "slides_per_min": 1.5}, {"duration_minutes": 30, "max_slides": 45, "slides_per_min": 1.5}, {"duration_minutes": 45, "max_slides": 68, "slides_per_min": 1.5}, {"duration_minutes": 60, "max_slides": 90, "slides_per_min": 1.5} ], "act1_ratio_limits": [ {"duration_minutes": 45, "max_percentage": 45} ], "recurring_issues": [ { "issue": "meme_accretion", "description": "Act 1 accumulates too many meme/image-only slides before the core argument begins", "guardrail": "If Act 1 has more than 60% meme/image-only slides, flag it", "severity": "warn" }, { "issue": "theoretical_framing_delay", "description": "Opens with a long theoretical context section before getting to the practical point", "guardrail": "If the opening framework section exceeds 10% of total slides before any concrete example, flag it", "severity": "warn" } ] } } =============== END OF FILE ===============
=============== FILE: inputs/draft-outline.md ===============
Spec: practitioner | 45 min | DevRelCon 2025 | DevRel professionals and community managers Slide budget: 68 slides (TBD)
Total slides: 60 =============== END OF FILE ===============
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
rules
skills
presentation-creator
references
patterns
build
deliver
prepare
scripts
vault-clarification
vault-ingress
vault-profile