Skip to content

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

fix(topic-research): load research artifacts into main context

hugohe383b6cbc73eb9
diff --git a/skills/ppt-master/workflows/stages/topic-research.md b/skills/ppt-master/workflows/stages/topic-research.md
index 1bf4035d..3d8d77e7 100644
--- a/skills/ppt-master/workflows/stages/topic-research.md
+++ b/skills/ppt-master/workflows/stages/topic-research.md
@@ -64,7 +64,7 @@ confirmation stage.
| Main agent | Supply the topic/outcome, baseline or relevant source paths, declared gaps, output language, two exact unused output paths, and this stage's absolute path as execution authority; use paths instead of pasting source bodies when possible |
| Research worker | Read the supplied stage file completely, then follow Steps 2–3 using the brief and declared source paths as its baseline; limit project writes to the two output artifacts; acquire no images and make no deck-planning or design decisions |
-**Hard rule — isolated hand-off**: Raw page content and fetch transcripts stay in the worker context. In at most 250 words, return only `status`, exact artifact paths, covered/unresolved gap counts, external-fact count, and material conflicts; do not return page excerpts or duplicate the research narrative in chat. The two saved artifacts are the hand-off.
+**Hard rule — isolate retrieval, not research**: Raw page content and fetch transcripts stay in the worker context. The 250-word limit applies only to its chat receipt: return `status`, exact artifact paths, covered/unresolved gap counts, external-fact count, and material conflicts. It does not cap or replace the two artifacts. After validation and import, the active content owner reads the complete imported research supplement and fact-provenance JSON into the main context before planning or direct SVG authoring; never use the receipt or validation summary as content.
**Validation**: Before import, the main agent verifies both exact files exist, the Markdown contains `## Research Brief` and `## Sources`, the JSON parses with schema `ppt-master.fact-provenance.v1` and unique sequential IDs, and the two files agree. Return an invalid pair to the research worker for owning-artifact repair; use main-context web research only when isolated execution is unavailable.
@@ -142,12 +142,11 @@ Import the research supplement and provenance alongside any user-supplied source
python3 ${SKILL_DIR}/scripts/project_manager.py import-sources projects/<project_name> [<source_paths...>] projects/<research_slug>.md projects/<research_slug>.facts.json
```
-The Research Brief remains evidence-facing context, not a locked presentation
-contract. Default Generate has Strategist read the imported material, confirm
-the complete contract, and select the content, page roster, and image resource
-plan before Step 5 acquisition. Quick Generate has the current agent read the
-same facts, decide those routine details in active context, and continue to its
-resource-preparation phase.
+The imported pair remains evidence-facing context, not a locked presentation
+contract. Default Generate has Strategist read both files completely before
+confirmation and use them to select the content, page roster, and image resource
+plan. Quick Generate has the current agent read both completely before its
+active-context content, design, and resource decisions.
```markdown
## ✅ Topic Research Complete
@@ -156,5 +155,5 @@ resource-preparation phase.
- [x] Fact provenance: `projects/<research_slug>.facts.json` (N external facts)
- [x] Artifact contract validated: `## Research Brief`, `## Sources`, `ppt-master.fact-provenance.v1`, unique sequential IDs, and Markdown/JSON agreement
- [x] No images acquired inside this factual-research stage
-- [ ] **Next**: return to [`generate-pptx`](../generate-pptx.md) Step 1, then import all source artifacts in Step 2
+- [ ] **Next**: return to [`generate-pptx`](../generate-pptx.md), import all source artifacts in Step 2, then fully read the imported research pair before planning or direct SVG authoring
```