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).
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
Load this before historical pattern selection or review. Run
pattern_history_status.py below before consuming any catalog-derived historical
field; this file defines what its output authorizes. Intake, CFPs, deck exports,
and QR actions do not run history classification.
"{python_path}" "{speaker_toolkit_root}/skills/presentation-creator/scripts/pattern_history_status.py" \
path/to/speaker-profile.json path/to/rhetoric-style-summary.mdUse - for the profile path in summary-only mode. The command emits
{history_enabled, history_source, profile_schema_version, scored_talk_count, eligible_talk_count, opportunity_rows_available, classification_fields_available, available_classification_domains, policy_semantic_sha256, reason_codes, reasons, warning}.
history_enabled means at least one policy-bound domain is available. It is not
permission to consume every derived field. In JSON, require membership in
available_classification_domains for each use. Python consumers call
domain_available(domain).
| Domain | Authorizes |
|---|---|
mastery_and_novelty | Mastery tiers, strengths, and New-to-You |
underuse | underused_patterns |
signature_combinations | signature_combinations |
antipattern_recurrence | Historical recurrence, consumed only through Phase 4's emitted recurring_antipatterns output |
trends | Pattern and antipattern movements, score/breadth trend, score drivers |
modes | by_mode history |
[NEW] is exactly mastery_levels.never_tried / never_used_patterns. It is
never first detection in the newest talk, and never a not_yet_observed
classification.
A recurrence claim may be available without a trend claim.
A non-null history_source selects the sole catalog-history input. Use the
emitted value without reproducing source-selection logic and without merging
inputs. Source resolution is owned by pattern_history_status.py
resolve_creator_pattern_history(). Surface a disabled result's warning
verbatim and recommend profile regeneration.
Continue using independent non-pattern fields regardless of history status: pacing, visual rules, presentation modes, infrastructure, publishing config, and confirmed intents.
Exact occurrence rows may remain auditable when opportunity_rows_available is
true, but that status never authorizes a classification.
Suppress each catalog-derived historical field when its required domain is absent. Do not collapse the available domains behind the global history flag.
Top-level recurring issues and badges in schema-v4/v5 profiles remain usable only
when their entries explicitly declare source_lane: "non_pattern". Legacy or
ambiguous entries do not authorize history.
Current-taxonomy scans of the new outline remain enabled.
If no profile exists, run in summary-only mode: default guardrail thresholds (1.5 slides/min, 45% Act 1 cap) and ask for template/publishing data interactively.
Section 15 v3 classifications are usable only when its uniquely delimited current
block, a stub binding rhetoric-pattern-history.json beside the summary by sha256,
passes:
"{python_path}" "{speaker_toolkit_root}/skills/vault-profile/scripts/section15_pattern_history.py" assess \
path/to/rhetoric-style-summary.mdplus the same strict pattern-profile assessment. Require the relevant domain just as for profile history. Section 15 v2 is occurrence-only. Ordinary, stale, or occurrence-only Section 15 data authorizes taxonomy-only recommendations, never speaker-history claims.
Compare pattern catalog fingerprints and scoring schemas first. A mismatch is a generation reset — do not call cross-generation pattern differences improvements or regressions.
Raw scores are also incomparable when the baseline reports an unavailable or
changed opportunity_coverage_identity.
Within one catalog/scoring generation, a changed policy_semantic_sha256 is a
classification-comparison reset: do not describe changed tiers, recurrence
classes, combinations, or trends as speaker improvement or regression across that
boundary.
.tessl-plugin
rules
skills
cfp-writer
references
illustrations
presentation-builder
presentation-creator
references
patterns
build
deliver
prepare
scripts
presentation-publisher
screencast-editor
screencast-recorder
shorts-producer
shownotes-publisher
vault-clarification
vault-ingress
references
scripts
vault-profile