sg-generate-images
Generate slide visuals using Gemini Pro from validated graphics descriptions
What this skill does
# Slide Generator: Generate Images Step Generate slide visuals using Gemini Pro from the validated graphics descriptions in the presentation. Uses a unified prompt builder and async batch generation for efficiency. ## Pre-loaded Context **Working directory:** !`pwd` **Available presentation files:** !`ls -la *.md 2>/dev/null | grep -i pres || echo "No presentation files found"` **Existing images:** !`ls -la images/ 2>/dev/null || echo "No images directory yet"` ## Proactive Triggers Suggest this skill when: 1. User wants to generate slide images/visuals 2. User says "generate images", "create visuals", or "make the graphics" 3. User completed graphics validation and wants to continue 4. User wants to see what the slides will look like ## Prerequisites - `slide-generator` package installed - `GOOGLE_API_KEY` set in environment (Gemini Pro access) - A `presentation.md` file with validated graphics descriptions - Graphics validation should be run first (`.graphics_validated` marker) ## Input Validation **Required:** - `<presentation.md>` - Path to presentation markdown file **Optional:** - `--resolution <level>` - Image resolution: `small`, `medium`, `high` (default: high) - `--image-format <fmt>` - Output format: `png`, `jpg` (default: png) - `--skip-existing` - Don't regenerate images that already exist ## Instructions 1. **Verify prerequisites**: Confirm `GOOGLE_API_KEY` is set and presentation has validated graphics 2. **Run image generation**: ```bash sg generate-images presentation.md --resolution high ``` 3. **Monitor progress**: Image generation takes time (~5-10s per image) 4. **Verify output**: Check that images were created in the `images/` directory 5. **Report results**: Show count of images generated, any failures ## How It Works The image generation step uses: - **Gemini Pro** (`gemini-3-pro-image-preview`): Google's image generation model - **Unified prompt builder**: `prompt_builder.py` constructs optimized prompts from descriptions - **Async batch generation**: Multiple images generated concurrently via `asyncio` - **API key in header**: Authentication via header (not query param) - **Block reason diagnostics**: Clear error messages when generation is blocked ## Error Handling | Error | Cause | Fix | |-------|-------|-----| | `GOOGLE_API_KEY not found` | Missing env var | Set the key | | `Image blocked` | Content policy violation | Review and soften the description | | `Rate limit` | Too many concurrent requests | Built-in rate limiter handles this | | `Generation timeout` | Gemini service slow | Retry; increase `SG_API_TIMEOUT` | ## Cost Estimate - ~$0.10 per image at high resolution - Typical 20-slide deck: ~$2.00 ## Output The step produces: - PNG/JPG images in an `images/` directory (one per slide) - File names correspond to slide numbers (`slide-01.png`, `slide-02.png`, etc.) ## Next Step After images are generated, build the final PowerPoint: ```bash sg build presentation.md --template generic ``` Or use `/sg-build` to continue the pipeline.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.