AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

EnrichPrompts

skill-cg-shmoop-claude-skills-enrichprompts · by cg-shmoop

Enrich structural image prompts with rich visual descriptions using Claude's own capabilities. USE WHEN user says enrich prompts, enrich image prompts, fill in prompts, write visual descriptions, describe assets, OR wants to add descriptions to empty/structural prompt files in StoryProductionVault.

↗ Repository
— No reviews yet
0 installs
40 views
0.0% view→install

Install

$ agentstack add skill-cg-shmoop-claude-skills-enrichprompts

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-cg-shmoop-claude-skills-enrichprompts)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of EnrichPrompts? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

EnrichPrompts

Reads story scene descriptions, visual language rules, and style seed to generate cinematographically-informed visual descriptions and video motion layer for each image prompt file (characters, backgrounds, symbols). Writes both image and video layer descriptions directly into prompt files in a single pass using Claude Code's Max subscription — no external API needed.

This skill operates on the StoryProductionVault production pipeline. It fills the gap between GenerateImagePrompts (structural templates) and GenerateAssets (image generation) by adding rich, specific visual descriptions that an image generator can use.

Customization

Before executing, check for user customizations at: ~/.claude/skills/PAI/USER/SKILLCUSTOMIZATIONS/EnrichPrompts/

Customizable elements:

  • PREFERENCES.md — Default style seed, description length, tone preferences
  • Additional style constraints or aesthetic rules

Workflow Routing

| Workflow | Trigger | File | |----------|---------|------| | EnrichPrompts | "enrich prompts", "enrich [story] prompts", "fill in prompt descriptions" | Workflows/EnrichPrompts.md |

Quick Reference

  • Input: Asset manifest path OR story folder path
  • Reads: Story scenes file (shot Visual: lines), visual language rules, style seed
  • Writes: Image descriptions + Video Layer section into each char_*.md, bg_*.md, symbol_*.md prompt file
  • Provenance: Adds enriched_by: claude-code-opus and enriched_at to frontmatter
  • Idempotent: Safe to re-run — overwrites previous enrichment with fresh descriptions
  • Single pass: Both image and video layers generated together from the same story context

Examples

Example 1: Enrich all prompts for a story

User: "enrich prompts for Gutei"
-> Reads 310_001_gutei_scenes.md for visual context
-> Finds 16 prompt files (4 chars, 7 backgrounds, 5 symbols)
-> Generates visual descriptions for each
-> Writes back with provenance

Example 2: Re-enrich after story edits

User: "I changed the Gutei scene descriptions, re-enrich the prompts"
-> Re-reads story context
-> Regenerates all descriptions to match updated scenes
-> Overwrites previous enrichment

Output Layers

Each enriched prompt file contains two layers:

| Layer | Section | Purpose | |-------|---------|---------| | Image | Description paragraph (after header) | Static image generation (Flux, Nano Banana, Imagen) | | Video | ## Video Layer (before Lineage) | Video AI platforms (Grok, Leonardo AI, RunwayML) — motion, timing, transitions |

Both layers are generated in a single pass from the same story context.

File Conventions

| Pattern | Location | Example | |---------|----------|---------| | Story scenes | 300_stories/310_story/[id]/[id]_scenes.md | 310_001_gutei_scenes.md | | Asset manifest | 300_stories/310_story/[id]/[id]_assets.md | 310_001_gutei_assets.md | | Prompt files | 300_stories/310_story/[id]/prompts/*.md | char_gutei.md, bg_title.md | | Style seed | 000_config/020_ai_prompts/visual/style_seed_*.md | style_seed_zen_ink_v1.md | | Meta-prompt | 000_config/020_ai_prompts/visual/enrich_prompt_v1.md | Reference template |

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Content & Media