From workflows
Revises workshop presentation slides and speaker notes built with Typst. Activated by phrases like 'revise slides' or 'fix presentation'. Loads conventions, performs edits, and verifies compilation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/workflows:workshop-reviseReaduv run python3 ${CLAUDE_PLUGIN_ROOT}/hooks/image-read-guard.pyEdit|WriteGATE_ARTIFACT=.planning/SOURCES_VERIFIED.md GATE_STATUS=VERIFIED GATE_DESCRIPTION="Phase 1 sources gate" GATE_REMEDY="Return to Phase 1 (workshop skill) and complete source gathering before editing any files" uv run python3 ${CLAUDE_PLUGIN_ROOT}/hooks/phase-gate-guard.pyuv run python3 ${CLAUDE_PLUGIN_ROOT}/hooks/workshop-phase-gate-guard.pyEdituv run python3 ${CLAUDE_PLUGIN_ROOT}/hooks/typst-convention-guard.pyWriteuv run python3 ${CLAUDE_PLUGIN_ROOT}/hooks/typst-convention-guard.pyBashuv run python3 ${CLAUDE_PLUGIN_ROOT}/hooks/overflow-check.py*COMPACT_THRESHOLD=40 COMPACT_INTERVAL=20 uv run python3 ${CLAUDE_PLUGIN_ROOT}/hooks/suggest-compact.pyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Announce:** "I'm using workshop-revise to apply changes to the workshop presentation."
Announce: "I'm using workshop-revise to apply changes to the workshop presentation."
Load ALL Typst conventions before touching any files:
!uv run python3 ${CLAUDE_SKILL_DIR}/../../scripts/load-constraints.py workshop-revise
You MUST have these constraints loaded before any edits. No claiming you "remember" them.
This skill may run in a new session. Load ALL needed context before touching any files.
Check if .planning/HANDOFF.md exists:
[Step 1: Load Context] → [Step 2: Diagnose]
→ [Step 3: Apply edits (+ workshop-verify /goal loop, max 3 turns, for content/structure)]
→ [Step 4: Verify (compile + widow + check-all.py)]
├─ pass → report to user
└─ unresolved after 3 cycles → ESCALATE to user
| Step | Topology | Exit condition |
|---|---|---|
| Step 3 (content/structure change) | serial edit → parallel review (workshop-verify under /goal, max 3 turns) | overallPass=true → Step 4; else escalate |
| Step 3 (formatting-only fast path) | one-shot edit | edit applied → Step 4 |
| Step 4 (verify) | serial (compile → widow → check-all.py) | all pass; else fix (max 3 cycles) then escalate |
The flow diagram above IS the authoritative spec for step order and gating. If prose below conflicts with it, the diagram wins.
After completing each step, IMMEDIATELY proceed to the next step. Do NOT ask "should I continue?" between steps 1–4. Pausing between steps is procrastination: you lose context, the user loses momentum, and the verification gate gets skipped. Pause only at the explicit checkpoints below.
| Point | Type | Behavior |
|---|---|---|
| R4 structural change detected | decision | STOP — present to user, get approval before re-entering Phase 3 |
| Step 3 artifact-review gate (content/structure) | human-verify | Auto-advanceable (independent workshop-verify reviewer) |
| Step 4 revision verified | human-verify | Auto-advanceable; report to user at end |
A revision can itself be multi-turn and context-intensive (especially a content/structure change driving a /goal loop). Before starting Step 3 edits or any /goal loop, check context availability:
| Level | Remaining Context | Action |
|---|---|---|
| Normal | >35% | Proceed normally |
| Warning | 25–35% | Complete the current edit, then write .planning/HANDOFF.md and pause |
| Critical | ≤25% | Write .planning/HANDOFF.md immediately — do not start a new edit or /goal loop |
HANDOFF.md template (same schema as the workshop entry skill):
---
workflow: workshop-revise
status: context_exhaustion
last_updated: [timestamp]
---
## Current State
[Which step; what edit is in progress]
## Completed Work
- [Edits applied so far, files touched]
## Remaining Work
- [Edits left + verification not yet run]
## Decisions Made
[User decisions captured during this revision]
## Rejected Approaches
[Edits tried and reverted, with reasons — so the resume does not retry them]
## Blockers
[Any unresolved blocker the next session must address, or "none"]
## Next Action
[Specific enough to resume immediately]
Pushing through context exhaustion to "finish the revision" ships degraded edits the presenter debugs at the podium. Writing the handoff is the helpful move, not the slow one.
.planning/SOURCES.md — paper metadata (title, authors, affiliations).planning/OUTLINE.md — section structure and timinguv run python3 ${CLAUDE_SKILL_DIR}/../../scripts/load-constraints.py workshop-reviseslides.typ — current slide contentnotes.typ — current speaker notesIf you edited slides.typ or notes.typ WITHOUT first completing Step 1 (loading SOURCES.md, OUTLINE.md, and constraints), DELETE your edits and restart from Step 1. Edits made without context produce inconsistencies that are harder to fix than to redo.
Determine what needs to change based on user's request:
User request
↓
├─ Content change ("add a slide about X", "remove section Y")
│ → Modify slides.typ AND notes.typ → Step 3 → Step 4
│
├─ Style/formatting fix ("fix bullet spacing", "text too small")
│ → Modify affected file only → Step 4
│
├─ Structure change ("move section 2 before section 1", "split into more parts")
│ → Update OUTLINE.md → Regenerate affected sections → Step 3 → Step 4
│ → For full regeneration: Read `${CLAUDE_SKILL_DIR}/../workshop/SKILL.md` Phase 3
│
└─ Metadata fix ("wrong affiliation", "update venue name")
→ Update SOURCES.md → Fix in both files → Step 4
These apply to EVERY edit, no matter how small:
- (NEVER -- as marker)= section / == subsection / === slide title#table() with inset: 10pt minimumqr: none must remain in config-info=== title must not repeat as first body line#align(center)\u{2019}s after ) or ]calc module#callout[] + 3+ #pause on same slide = overflow risk → splitlength: 2em, requires // Storytelling: comment\$ not $_Case v. Party_; em-dash ---; en-dash for ranges --Shipping a "quick fix" with broken formatting means the presenter discovers it at the podium. That's not a fix — it's a trap you set for them.
qr: none in config-info are load-bearing for the secreg theme — removing or "cleaning up" either breaks compilation.Unplanned issues surface mid-revision. Apply the same 4-rule system as the workshop generate phase, adapted to revision:
| Rule | Trigger | Action | Permission |
|---|---|---|---|
| R1: Bug | Typst compile error, syntax error, broken import introduced by the edit | Fix → recompile → verify → track [R1] | Auto |
| R2: Missing Critical | Edit leaves notes out of sync, drops a qr: none, removes a required #align(center), breaks bullet spacing | Add/restore → recompile → verify → track [R2] | Auto |
| R3: Blocking | Missing asset/template the edit depends on, font/package conflict surfaced by recompile | Fix blocker → verify proceeds → track [R3] | Auto |
| R4: Structural | The request implies reordering sections, changing proportions, or regenerating a whole part | STOP → present to user → on approval, re-enter workshop Phase 3 (which re-runs workshop-verify) → track [R4] | Ask user |
Priority: R4 (STOP) > R1-R3 (auto) > unsure = R4. After applying changes, report: Total deviations: N auto-fixed (R1: X, R2: Y, R3: Z).
For content or structural changes (NOT simple formatting fixes), the edited deck is reviewed by the workshop-verify ultracode workflow — the same per-slide fan-out + JS gate the workshop skill uses — scoped to the slides you touched:
slides.pdf reflects the edits: cd [presentation directory] && typst compile slides.typ && typst compile notes.typWorkflow(name="workshop-verify", args={
"projectDir": "[absolute project root]",
"pluginRoot": "${CLAUDE_SKILL_DIR}/../..",
"onlyChecks": [<IDs of the slides you edited, e.g. "S4", "S5">]
})
(Omit onlyChecks to review the whole deck after a large change.)overallPass is false → /goal workshop-verify returns overallPass=true. Stop after 3 turns.; each turn fix the reported findings (main chat owns fixing — the workflow is read-only), recompile, re-invoke selectively, end the turn. If true → proceed to Step 4.The workflow's reviewers are read-only by construction; the JS gate (overallPass) is authoritative. Do not hand-wave the gate to true — fix a finding and let the next run recompute.
After workshop-verify returns, main chat stays on the verification side of this boundary:
| Verification (main chat CAN do) | Investigation (main chat CANNOT do) |
|---|---|
Read the workflow's findings / scoreTable | Re-read slides.typ/notes.typ to "double-check" the gate |
Re-invoke the workflow (selectively, onlyChecks) | Override the JS gate ("the workflow was too strict") |
Dispatch a fix subagent for reported findings | "Quick fix" an issue the workflow did not report |
Proceed to Step 4 once overallPass=true | Declare the revision clean without a passing gate |
The JS gate (overallPass) is authoritative. If you disagree with a result, fix a finding and let the next run recompute — never hand-wave the gate to true.
/goal loop)If the user interjects with an off-topic request while the /goal workshop-verify loop is active:
/goal.Never silently abandon the loop. An off-topic message is not permission to stop verifying.
Compile both files:
cd [presentation directory] && typst compile slides.typ && typst compile notes.typ
Run PDF widow detection (mandatory after every compile):
DETECT_WIDOWS=$(command ls -d ~/.claude/plugins/cache/tinymist-plugin/tinymist/*/skills/typst-widow-orphan/scripts/detect_widows.py 2>/dev/null | sort -V | tail -1) && uv run python3 "$DETECT_WIDOWS" "[presentation directory]/slides.pdf"
Two-leg verification:
Leg 1 — Constraint checks (hard block):
cd [presentation directory] && uv run python3 ${CLAUDE_SKILL_DIR}/../../references/constraints/check-all.py .
Leg 2 — Convention review (judgment): For conventions listed by check-all.py (.md without .py), manually verify against the changed sections.
If compilation fails: Fix and recompile (max 3 attempts).
If convention violations persist after 3 fix-and-recheck cycles: Escalate to user.
qr: none present in config-info-- as marker))'s / ]'s)inset: 10pt minimum#align(center)calc module)length: 2em minimum + // Storytelling: comment (if used)\$)*Label:* before bullets)Report changes to user:
Changes applied:
- [what was changed]
- slides.typ: [compiles ✓/✗]
- notes.typ: [compiles ✓/✗]
- Widow detection: [0 widows / N widows fixed]
- Overflow detection: [clean / N slides fixed]
- Visual-verify: [N diagrams verified / N/A]
- Source fidelity: [verified / N claims flagged]
The midpoint leaves a durable record so a later session can see what changed and so recurring preferences accumulate:
.planning/LEARNINGS.md (create it if absent):
## Revision — [date]
- Request: [what the user asked to change]
- Files touched: [slides.typ / notes.typ / SOURCES.md / OUTLINE.md]
- Deviations: [R1: X, R2: Y, R3: Z]
- Gate: [overallPass / formatting-only fast path]
- Reviewed by: [how the user inspected the result — observe, don't infer]
For structural changes requiring full regeneration, read and re-enter the workshop skill:
Read ${CLAUDE_SKILL_DIR}/../workshop/SKILL.md Phase 3 for regeneration.
npx claudepluginhub edwinhu/workflows --plugin workflowsCreates academic workshop presentation slides and speaker notes from research papers using Typst, with a phased workflow from source gathering through verification.
Creates slide presentations from topics, URLs, PDFs, git repos, or vault notes. Handles research, synthesis, outlining, and editing existing decks. Default output is reveal.js HTML; pptx available on request.
Orchestrates presentation outlines with per-page media decisions and runs a post-render QA loop. Use before generating PPT/HTML slides from raw material.