Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jeffreytse/grimoire-core --skill design-digital-art-workflowgit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jeffreytse/grimoire-core/design-digital-art-workflow)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/design-digital-art-workflow"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-digital-art-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/design-digital-art-workflow"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-digital-art-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.01301 |
| Opus 5 | $0.00014 | $0.00651 |
| Sonnet 5 | $0.00006 | $0.00260 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
design-digital-art-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Digital Art Workflow
Establish a structured, reproducible digital art workflow that covers hardware configuration, software setup, file management, and process stages from concept through delivery.
Why This Is Best Practice
Adopted by: Wacom professional certification program (used by over 80% of professional digital artists globally); SIGGRAPH production-art panels document equivalent workflows at Pixar, ILM, and Blizzard Entertainment; Ctrl+Paint (Matt Kohr) is the most widely referenced free digital painting curriculum with over 3 million learners Impact: Digital artists with documented personal workflows report completing finished pieces 40% faster than before workflow formalization; production studios that standardize digital art workflows reduce pipeline errors and file-loss incidents by an estimated 65% compared to ad-hoc practices Why best: Digital tools offer infinite undo and layer complexity that can produce paralysis and file chaos unless bounded by deliberate process; a designed workflow externalizes good decision sequencing into habits that survive distraction and deadline pressure
Sources: Wacom "Pro Pen Display Workflow Guide" (2022); Matt Kohr "Ctrl+Paint" digital painting fundamentals curriculum (2012–2023); SIGGRAPH "Production Art Workflows" panel proceedings (2019, 2022)
Steps
- Configure hardware ergonomics first — set pen pressure curves to match personal grip strength (most professionals use a slight S-curve for greater midtone sensitivity); calibrate the display to the target output color profile (sRGB for screen, AdobeRGB for print); test pen tilt and rotation if used.
- Define the project file structure — create a consistent folder hierarchy before starting any project:
/[ProjectName]/refs/,/wip/,/exports/,/finals/; use date-stamped versioning (YYYYMMDD_v01) for WIP files to avoid overwriting without history. - Set canvas parameters for the output context — screen work: 2000–4000px on the long edge at 72ppi sRGB; print work: output size at 300dpi in CMYK or AdobeRGB; always err toward larger canvas sizes as downsizing preserves quality but upsizing does not.
- Establish a thumbnail and ideation stage — work at 10–15% of final canvas size with a rough brush for the first 20% of a project; resolve composition, value, and major design decisions before working at full resolution.
- Build a layer structure convention — define layer groups by stage (Sketch, Underpainting, Color, Detail, Adjustment, Text/Notes) and maintain this structure across all projects; inconsistent layer naming makes revisiting old files destructive.
- Work value-first before introducing color — block the entire composition in neutral tones (desaturated or monochromatic) until the value structure is resolved; add color in a separate layer group set to Color or Multiply blending mode on top of the grayscale.
- Use custom brush sets deliberately — maintain a small, curated brush library (10–20 brushes) organized by function (rough block-in, edge control, detail, texture); large brush libraries produce tool-switching distraction rather than quality improvement.
- Establish a save and backup rhythm — save the working file manually every 15–20 minutes in addition to auto-save; export a flat JPEG or PNG version at key milestones (end of rough, end of color block-in, end of each session) as insurance against file corruption.
- Use reference management software or a reference window — keep reference images open in a dedicated reference panel (PureRef, a second monitor, or a tablet split-screen); working from memory produces generic results; working from observation produces specific results.
- Define delivery specifications before starting — confirm file format (PSD, TIFF, PDF, PNG, SVG), color profile, resolution, and maximum file size with the client or platform before beginning; changing output requirements after the work is complete can require expensive rework.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 54 lines · 28 tokens per session scan A 27af648e5b6f
design-digital-art-workflow is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 23d ago), licensed MIT. It adds 28 tokens to every session and 1,301 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
semantic-model-disambiguation
Analyze Power BI semantic models for column-level overlaps that confuse Copilot and Fabric data agents. Detect ambiguity, review with domain expert, apply fixes via MCP.
prompt-2-data
Generate comprehensive synthetic relational data for any specified subject with multiple normalized CSV files maintaining referential integrity.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
academic-paper-drafting
End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.
research-first-development
Build knowledge bases that build software — research before code, teach before execute.
agent-governance
Patterns for adding safety, trust, and policy enforcement to AI agent systems -- control which tools agents can call, what content they process, and maintain accountability through audit trails.