Install
$ agentstack add skill-mrstev3n-balise-skills-balise-affinity ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Affinity Design Literacy
Use this skill for Affinity reasoning before automation. It helps choose the right Affinity concept, object type, workflow, and verification method. It is complementary to balise-affinity-mcp, which executes changes through the MCP.
Core Posture
Treat Affinity as a unified creative environment with vector, pixel, and layout capabilities in one document. Before recommending an action, identify the user's intent:
- create or edit vector artwork
- retouch or manipulate pixels
- structure a layout or publication
- build reusable design systems
- prepare exportable assets
- diagnose a visual or UI-state issue
- automate through MCP
Do not reduce Affinity work to poster recreation. Posters are only one possible composition use case.
Reference Routing
- Read
references/affinity-mental-model.mdfor architecture, Studios, object model, and workflow decisions. - Read
references/affinity-decision-matrix.mdfor concrete object and verification choices. - If the answer requires live document manipulation, switch to
balise-affinity-mcpand follow its SDK-first workflow.
Reasoning Rules
- Separate what is artwork from what is Affinity UI state.
- Prefer non-destructive workflows unless final flattening is explicitly requested.
- Prefer reusable systems for repeated design elements: symbols, text styles, global colors, assets, and named groups.
- Choose text mode deliberately: Artistic Text for display fragments, Frame Text for layout containers.
- Use artboards/pages/spreads for variants, screen states, and multi-page work instead of separate files when a shared system matters.
- Treat exact feature names, AI tools, shortcuts, and version-specific behavior as verify-first details.
- When the user wants a detailed synthesis, prefer HTML over long Markdown.
Output Expectations
For audits or strategy:
- classify findings by concept area
- explain practical impact
- recommend the safest Affinity-native approach
- identify what should be verified through MCP or visual render
For automation planning:
- name the relevant Affinity concepts
- describe the object model to inspect
- identify the narrowest safe edit
- state the visual verification method
For learning capture:
- extract durable lessons
- mark volatile claims
- suggest which reference file should absorb the lesson
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mrstev3n
- Source: mrstev3n/balise-skills
- License: Apache-2.0
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.