Borrowing it
Nothing to install: this file belongs to BloomBooks/BloomDesktop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BloomBooks/BloomDesktop/master/.claude/skills/rab-icon-grid-processing/SKILL.mdgit clone --depth 1 https://github.com/BloomBooks/BloomDesktopWrote 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/bloombooks/bloomdesktop/rab-icon-grid-processing)<a href="https://agentmods.dev/skills/bloombooks/bloomdesktop/rab-icon-grid-processing"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/rab-icon-grid-processing/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/bloombooks/bloomdesktop/rab-icon-grid-processing"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/rab-icon-grid-processing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.00758 |
| Opus 5.5 | $0.00028 | $0.00303 |
| Sonnet 5.5 | $0.00014 | $0.00152 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
rab-icon-grid-processing 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 1mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAB icon processing
Outcome
Icon artwork becomes usable Reading App Builder icons: legible at app-icon size, square PNGs with
transparent backgrounds, named bloom-app-icon-<number>.png, stored flat under
DistFiles/appbuilder-icons, and visually checked on a sample before the whole batch is touched.
Before you start, settle these with the user
What the source is (a grid image, a sprite sheet, or already-split PNGs); whether the job is visual only, layout only, or both; whether to pilot on one or two icons first or a full batch is already approved; whether the filenames are already the final ids or need renaming; and what the narrowest validation is once the icons are in place. Unstated answers default to: pilot first, keep existing names, validate with the RAB icon tests.
Workflow
- Inspect the source. A single grid image, a sprite sheet, or already-split PNGs? Decide whether the controlling problem is splitting, transparent padding, or naming.
- Pilot on one or two icons that show the problem clearly, and look at the results before touching the rest. Never batch-transform first.
- Grid or sprite sheet: split into individual transparent PNGs using consistent cell geometry, then evaluate padding on the extracted files.
- Padded PNGs: find the smallest rectangle of pixels above a low alpha threshold, clone it, draw it centred on a transparent 512×512 canvas scaled to leave a consistent margin. Save through a temp file and replace the original only after all source handles are disposed (avoids GDI+ save and file-lock errors on Windows).
- Batch the rest with the same rule once the pilot reads well. Keep the margin consistent across the batch; fail on duplicate destination names instead of overwriting.
- Validate: icons visibly larger and clearer, nothing clipped, still square and transparent,
and Bloom's discovery still finds them — run the RAB icon tests
(
build/agent-dotnet.sh test src/BloomTests/BloomTests.csproj --filter GetAvailableIconChoices). Discovery code and tests live nearsrc/BloomExe/Publish/Rabandsrc/BloomTests/Publish/Rab.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · -92 lines · +9 tokens per session 9f0118c89727
- 2mo ago First seen · 144 lines · 62 tokens per session scan A 911ba96c11da
rab-icon-grid-processing is a skill published in the GitHub repository BloomBooks/BloomDesktop (43 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 758 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.