mikeparcewski/wicked-garden-product-imagery-alter
skills/product/imagery/alter/SKILL.md
AI-powered image modification: img2img editing and mask-based inpainting. Requires a provider that supports editing operations. Use when: "edit image", "modify image", "change image", "inpaint", "img2img"
$ install --global
skillsauthnpx skillsauth add mikeparcewski/wicked-garden wicked-garden-product-imagery-alterInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jul 13, 2026, 7:59 AM75.3s2 files scanned
SKILL.md
- name:
- wicked-garden-product-imagery-alter
- description:
- |
- AI-powered image modification:
- img2img editing and mask-based inpainting.
- Use when:
- edit image", "modify image", "change image", "inpaint", "img2img
- phase_relevance:
- ["clarify", "design", "review"]
- archetype_relevance:
- ["*"]
Image Alteration
AI-powered modification of existing images through two primary modes: image-to-image editing (global changes) and mask-based inpainting (local changes).
When To Use This Skill
- Modifying style, lighting, or mood of an existing image
- Replacing or adding specific elements within an image
- Iterating on generated images to reach desired output
- Making targeted local edits while preserving the rest
Modification Modes
Image-to-Image (Global Edits)
Changes the overall style or adds global elements while preserving core composition.
sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" "${CLAUDE_PLUGIN_ROOT}/skills/imagery/scripts/provider.py" edit \
--image ./source.png \
--prompt "Same scene but with a dramatic sunset sky" \
--output ./v2.png
Key control: The strength parameter determines how much the model deviates from the original.
--strength 0.2-0.3— Subtle changes (color grading, minor adjustments)--strength 0.4-0.6— Moderate changes (style transfer, lighting shifts)--strength 0.7-0.9— Dramatic changes (major style overhaul)
Inpainting (Local Edits)
Precise edits to specific regions using a binary mask (white = edit area, black = preserve).
sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" "${CLAUDE_PLUGIN_ROOT}/skills/imagery/scripts/provider.py" inpaint \
--image ./source.png \
--mask ./mask.png \
--prompt "Replace with floating lanterns" \
--output ./v2_inpaint.png
Best practices for masks:
- Clean edges — avoid feathered or anti-aliased mask boundaries
- Include enough context area around the edit target
- For complex shapes, create the mask programmatically or use a drawing tool
Iterative Refinement Loop
When the output is close but not quite right:
1. DIAGNOSE — What specifically is wrong? (color, composition, detail, artifact)
2. ADJUST — Modify the right parameter for the issue:
- Wrong elements → refine prompt, add negative prompt
- Wrong style → adjust strength parameter
- Wrong detail → fix seed, tweak guidance scale
- Local issue → switch to inpainting with a targeted mask
3. REGENERATE — Run with adjusted parameters
4. REVIEW — Use the review sub-skill to validate
Refinement Strategies
| Problem | Solution |
|---------|----------|
| Missing element | Increase weight in prompt with specific adjectives |
| Unwanted artifact | Add to --negative-prompt |
| Good composition, bad detail | Fix --seed, adjust --guidance-scale |
| Almost perfect, one area wrong | Switch to inpainting for that region |
| Too different from original | Lower --strength value |
| Not different enough | Raise --strength value |
Final Polish
Use upscaling as the last step to bring a draft to production quality:
# Upscaling (cstudio only — other providers may not support this)
sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" "${CLAUDE_PLUGIN_ROOT}/skills/imagery/scripts/provider.py" generate \
--provider cstudio \
--prompt "upscale" \
--output ./final_hires.png
Detailed References
- Editing techniques, provider commands, and refinement strategies: refs/editing-reference.md
Integration With Other Sub-Skills
- Use review before altering to understand what needs to change
- Use review after altering to validate the changes
- If starting from scratch is better than editing, hand off to create
- Alteration is the "Execute" and "Refine" steps of the Analyze-Execute-Review-Refine loop
Related Skills
mikeparcewski/wicked-garden-engineering-conformance-reviewer
development
VerifiedTrustedCommunity
Pattern-conformance agent-half: evaluates a produced artifact or diff against a set of architectural/design pattern rules from the conformance-rule store (wicked_governance schema). Returns structured findings with rule ID, severity, and rationale — the deterministic half (mechanical rule recall) is done by the guard pipeline; this is the semantic evaluation step. Triggered by: the guard_pipeline `outgov_pattern` check (session-close), or explicitly by an engineering review when WICKED_OUTGOV_RULES_DIR is populated. NOT a replacement for the full `engineering` review skill — focuses only on conformance to stored Pattern rules; architecture and code-quality checks live in the `engineering` skill. Semantic evaluation reuses `wicked-garden-qe-semantic-reviewer` as the designated agent-half evaluator (per garden#983 spec). This skill is the orchestrating wrapper that loads applicable Pattern rules and delegates the per-rule semantic judgment to qe-semantic-reviewer.
8SKILL.mdUpdated Jul 22, 2026
mikeparcewski/wicked-garden-domain
tools
VerifiedTrustedCommunity
The FOUNDATIONAL domain-model capability: extract a codebase's domain — testable business rules (with confidence + provenance), entities, requirements — as a schema-conformant model on the estate graph. The workers annotate the store; wicked-core reads it and builds the requirements graph, coverage-gating fail-closed. Steers three fork workers. A shared substrate, not a modernization tool. The `modernize` archetype DERIVES from it; build / migrate / review / specify / explore consume the SAME domain model — none OWN it. Understanding a codebase's domain is upstream of almost everything else garden does. Use when: "extract the business rules / domain model from this codebase", "build a requirements graph from the code", "what does this system actually require", "reverse-engineer the domain before we build/port/migrate". Works on ANY codebase (modern or legacy) — the value is the domain model, not the porting. NOT the code transform itself (that is the archetype consuming this model). This skill produces the DOMAIN MODEL, not new code.
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-modeler
development
VerifiedTrustedCommunity
Domain-graph fork worker for the modernize archetype. Groups the estate's Louvain communities into business domains, attaches each requirement to its cluster (advisory cluster_id provenance), and invokes wicked-core's domain-graph build (which reads the annotated estate store, recomputes coverage fail-closed, and builds the requirements graph) — then validates core's output against the vendored schema. Use when: dispatched by wicked-garden-domain after rule extraction to turn a flat rule set into cluster-keyed domains; "group these into domains", "build the requirements graph", "translate clusters into a domain model". NOT for mining the rules themselves (that is domain-extractor) or threat-modeling (that is domain-coverage).
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-extractor
tools
VerifiedTrustedCommunity
Rule-extraction fork worker for the FOUNDATIONAL domain-model capability. Mines testable business rules from a codebase — each with a numeric confidence and a provenance{source, ref, source_kinds} — and annotates them into the estate store so wicked-core can build the domain-model requirements graph (coverage-gated). This is a substrate, not a modernization tool: the `modernize` archetype DERIVES from it, and build / migrate / review / specify / explore can consume the same domain model — none OWN it. Use when: dispatched by wicked-garden-domain to mine the business_rules of a codebase (or a module); "extract the domain rules", "what does this system require", building the requirements half of a domain model. NOT for grouping into domains (that is domain-modeler) or judging coverage (that is domain-coverage — a seat-distinct evaluator).
8SKILL.mdUpdated Jul 15, 2026