Menu
Benchmark GSP token budget — capture snapshots, compare between versions/PRs, track improvements over time
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Add reference material to a project — use when: add a reference, save inspiration, attach examples, link this site as reference, drop in a moodboard
Craft ASCII art interactively — you direct, the artist creates — use when: make ASCII art, terminal art, decorative banner, splash screen, hero ASCII
Audit an existing brand before evolving it — use when: audit our brand, what do we have, before a rebrand, brand health check, current brand state, brand inventory
Sync brand to match a project's shipped state — tokens, voice, visual patterns, personality — use when: brand drifted from the app, reverse-engineer the brand, the code is ahead of the brand docs, sync brand to shipped, update brand from production
Design color systems — palettes, contrast, semantic mapping, dark mode — use when: pick colors, build a palette, semantic tokens, dark mode pairings, brand color, accent color
Design icon systems — library selection, sizing, containers, custom SVG direction — use when: pick an icon library, icon sizing rules, icon containers, custom SVG direction, swap icons, icon strategy
| name | gspdev-benchmark |
| description | Benchmark GSP token budget — capture snapshots, compare between versions/PRs, track improvements over time |
| allowed-tools | ["Read","Bash","Glob","Grep","AskUserQuestion"] |
| argument-hint | [capture|compare|trend|pr] default: capture |
Snapshots live in dev/benchmarks/ as JSON files. The workflow is release-centric:
benchmark.sh release → {version}.release.jsonbenchmark.sh capture [label]benchmark.sh compare (auto-selects release baseline)This measures the cumulative impact of changes heading into the next release.
## Step 0: Parse modeRead $ARGUMENTS to determine the mode:
| Input | Mode |
|---|---|
| (no args) | Capture + auto-compare against release baseline |
capture [label] | Capture with optional label |
release | Capture as the release baseline for this version |
compare [v1] [v2] | Compare two snapshots (default: release vs latest) |
trend | Show trajectory across all snapshots |
bash dev/scripts/benchmark.sh capturebenchmark.sh compareThis is the most common invocation — "where are we vs the last release?"
Run bash dev/scripts/benchmark.sh capture [label].
After capture, read the JSON from dev/benchmarks/ and present a summary:
Run bash dev/scripts/benchmark.sh release.
This is part of the publish flow — capture the definitive baseline for this version. All future compare calls will diff against this baseline until the next release.
Remind the user: "Add benchmark.sh release to your /gspdev-publish checklist."
Run bash dev/scripts/benchmark.sh compare [v1] [v2].
Default (no args) compares release baseline → latest capture. After the table output, analyze:
Run bash dev/scripts/benchmark.sh trend.
After the table, identify:
Based on the results, suggest relevant actions: