adobe/spectrum-design-data is a monorepo containing the design tokens, component schemas, specifications, and related datasets that define Adobe's Spectrum design system; a monorepo keeps these related packages in one repository. It is for Adobe Spectrum SDK and tooling developers who need canonical design-system data and validation artifacts. The catalogue add-ons provide workflows and integrations for working with this design data.
Borrowing it
Nothing to install: this file belongs to adobe/spectrum-design-data. 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/adobe/spectrum-design-data/main/.ai/skills/enhance-sync-pr/SKILL.mdgit clone --depth 1 https://github.com/adobe/spectrum-design-dataWrote 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/adobe/spectrum-design-data/enhance-sync-pr)<a href="https://agentmods.dev/skills/adobe/spectrum-design-data/enhance-sync-pr"><img src="https://agentmods.dev/badge/skills/adobe/spectrum-design-data/enhance-sync-pr/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/adobe/spectrum-design-data/enhance-sync-pr"><img src="https://agentmods.dev/badge/skills/adobe/spectrum-design-data/enhance-sync-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 14 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 61 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 64 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 66 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 67 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 68 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 61 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 61 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 63 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 64 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 66 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 66 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 67 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 68 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 68 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00099 | $0.01608 |
| Opus 5.5 | $0.00040 | $0.00643 |
| Sonnet 5.5 | $0.00020 | $0.00322 |
| Haiku 4.5 | $0.00010 | $0.00161 |
Grade A, and why
enhance-sync-pr 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 20d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enhance sync PR (Tokens Studio → spectrum-design-data)
When this applies
- PR opened by
mrcjhicksfromtokens-sync/patch-spectrum2-from-main(or similar sync branch). - Body links to
github.com/adobe/spectrum-tokens-studio-data/actions/runs/…. - CI red after sync (validation, snapshot, component props, wireframe, etc.).
- Changeset missing; title still
feat: updates from spectrum-tokens-studio-dataor duplicatedfeat: Feat:.
Repo and tools
- Monorepo root: workspace root (
spectrum-design-data). - Changeset generator:
tools/token-changeset-generator— fetches source PR motivation, runstdiff, infers semver bump. - Automation:
.github/workflows/enhance-sync-pr.ymland.github/actions/extract-source-pr-info.
1. Resolve source PR
From the design-data PR body, take the spectrum-tokens-studio-data Actions run URL or the Tokens Studio PR link.
gh pr view <N> --repo adobe/spectrum-design-data --json body,title,headRefName,url
If only the run URL exists, resolve merged PR from that run (same logic as extract-source-pr-info).
Record:
- Source PR URL (e.g.
https://github.com/adobe/spectrum-tokens-studio-data/pull/297) - Source author (
user.loginfrom that PR) for attribution
gh api repos/adobe/spectrum-tokens-studio-data/pulls/<num> --jq '{title, author: .user.login, body}'
2. Diagnose CI (suggest fixes; user approves edits)
Check out the PR branch with full history (fetch-depth: 0) so tdiff can compare to main.
Run in order:
moon run tokens:validateDesignData
moon run tokens:verifyDesignDataSnapshot
cd packages/tokens && pnpm ava
Or full graph: moon ci (same as GitHub Actions).
Failure map (what to suggest)
| Symptom | Likely cause | Suggestion | ||
|---|---|---|---|---|
checkComponentProps lists token names |
Missing or wrong component on entries in color-component.json, layout-component.json, or icons.json |
Set component to match token name prefix (see packages/tokens/test/checkComponentProps.js). |
||
Schema / color-set errors |
sets missing light, dark, or wireframe |
Align with schemas/token-types/color-set.json. |
||
verifyDesignDataSnapshot / snapshot mismatch |
Validation report changed vs golden file | Paths in the snapshot are relative to packages/tokens/. After moon run sdk:build, run migrate snapshot from packages/tokens/ so paths match moon run tokens:verifyDesignDataSnapshot: cd packages/tokens && ../../sdk/target/debug/design-data migrate snapshot ./src --output ./snapshots/validation-snapshot.json --schema-path ./schemas --exceptions-path ../design-data/naming-exceptions.json. |
||
Token file / $schema / uuid |
Invalid token shape | Fix per token-file.json and failing AVA tests. |
||
| Alias / renamed / manifest | Broken refs or manifest drift | Fix aliases; run moon run tokens:buildManifest. |
||
| Changeset lint on PR | Bad frontmatter | Valid --- / "@adobe/spectrum-tokens": patch | minor | major / body. |
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.
- 20d ago Changed 35133781e400
- 2mo ago First seen · 136 lines · 99 tokens per session scan A 1c29b912734d
enhance-sync-pr is a skill published in the GitHub repository adobe/spectrum-design-data (157 stars, last pushed today), licensed Apache-2.0. It adds 99 tokens to every session and 1,608 once invoked, about $0.0004 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 2026-09-03.
enhance-sync-pr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| enhance-sync-pradobe/spectrum-design-data | Skill | 157 | today | Apache-2.0 | A | 99 | Claude Code, Codex |
| design-tokens-versioningalmasumdev/awesome-mobile-design-system-agent-skills | Skill | 2 | 6mo ago | none | A | 34 | Claude Code, Codex |
| extract-designManavarya09/design-extract | Skill | 4.8k | yesterday | MIT | A | 140 | Claude Code |
| designlang-tokensManavarya09/design-extract | Skill | 4.8k | yesterday | MIT | A | 30 | Claude Code |
| ss-learnbitjaru/styleseed | Skill | 1.0k | yesterday | MIT | A | 73 | Claude Code, Codex |
| omd-applykwakseongjae/oh-my-design | Skill | 567 | yesterday | MIT | A | 129 | Claude Code, Codex |
| design-dnazanwei/design-dna | Skill | 2.1k | 2mo ago | MIT | A | 192 | Claude Code, Codex |