Install
$ agentstack add skill-pixelcrafts-app-agent-skills-standards-config ✓ 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.
About
Standards Config
standards.json tells verification which skills apply to this project (so it doesn't guess from file types). Lives at /standards.json (.claude//.kimi//.agent//project root); committed to the repo, reviewed in PRs.
Schema
{
"stacks": ["web", "api"],
"features": { "auth": "jwt-refresh", "realtime": false, "i18n": false, "payments": false },
"disabled_rules": []
}
stacks[] — project-mandatory domains: web → web-standards · mobile → mobile-standards · flutter → flutter-standards · api → api-standards. Two+ stacks auto-activate cross-stack-contracts.
features{} — conditional skills: auth (jwt-refresh/oauth/session/true/false) → api-design auth contract · realtime → websockets · i18n → i18n · payments → future. When false, the skill is inactive; if its trigger patterns appear in code anyway, verification emits INFO, not FAIL.
features.aesthetic — the project's declared aesthetic
Universal design rules (platform design R-rules, design-system) are always enforced; per-aesthetic specifics are INFO unless the project commits here. Absent/active:null → only universals enforced (no project ships under an enforced aesthetic by accident).
"aesthetic": {
"active": "soft-clay",
"definitions": {
"soft-clay": {
"bans": ["gradient-text", "neon-accents"] // pattern keys → FAIL on match
},
"alt-considered:utility-brutalist": { "...": "documents alternatives; not enforced" }
}
}
Exactly one active aesthetic enforced; other definitions are an audit trail. Switching is one config edit, not a code change.
disabled_rules[]
Escape hatch — each entry needs a reason: { "rule": "flutter-standards:observability", "reason": "..." }. Every verification report surfaces all disabled rules + reasons (bypasses are never silent); a disabled rule with no reason → WARN: add reason or re-enable. Disabled ≠ deleted.
Auto-generation (when planning finds no standards.json)
Detect stacks (extensions .tsx→web/.dart→flutter, @nestjs→api; manifests) and features (auth guards, socket imports, i18n packages) → present a draft inline → ask "correct?" → write on confirm; if skipped, note absence in the plan and fall back to auto-detection with an INFO notice. Manual review required before the file is authoritative.
Maintenance
Update when a stack/feature is added. Don't delete a removed feature's key — set false so the absence is explicit. Verification reads standards.json in Step 0 as the authoritative source for project-mandatory skills; auto-detection is a fallback.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: pixelcrafts-app
- Source: pixelcrafts-app/agent-skills
- License: MIT
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.