raymond-ui/dinachi-assistant
skills/dinachi-assistant/SKILL.md
Unified Dinachi skill for fast component integration and plan-first generative UI guidance. Use when users ask to initialize/add Dinachi components, build concrete UI features quickly, map ambiguous product requirements to Dinachi recipes, or validate generated UI plans before implementation.
$ install --global
skillsauthnpx skillsauth add raymond-ui/dinachiui dinachi-assistantInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 11, 2026, 8:35 PM10.6s20 files scanned
SKILL.md
- name:
- dinachi-assistant
- description:
- Unified Dinachi skill for fast component integration and plan-first generative UI guidance. Use when users ask to initialize/add Dinachi components, build concrete UI features quickly, map ambiguous product requirements to Dinachi recipes, or validate generated UI plans before implementation.
Dinachi Assistant
Use one skill with two explicit modes and one automatic router.
Mode: build-now
Use when user asks for concrete implementation quickly:
- explicit component asks (
add dialog + form) - install/integration asks
- direct code edits using known Dinachi components
Primary references:
references/components.mdreferences/intent-map.mdreferences/workflows.md(command generation and verification)references/troubleshooting.md(setup/import/theme diagnosis)references/maintainer-checklist.md(monorepo component/docs/template/test updates)
Primary scripts:
scripts/suggest-components.mjs --json "<prompt>"(when component names are ambiguous)scripts/audit-skill.mjs(maintainer consistency checks)scripts/validate-skill.mjs(skill folder sanity checks)
Maintainer scope:
- When changing Dinachi itself in this monorepo, use
references/maintainer-checklist.md. - Treat
packages/components/src/<slug>as source of truth and keep CLI templates/docs in sync.
Mode: plan-first
Use when user intent is broad/ambiguous or generative:
- "make a good settings flow"
- "design a configurable admin experience"
- "generate a workflow UI from intent"
Primary references:
references/components.registry.jsonreferences/policies.jsonreferences/intent.schema.jsonreferences/recipe.schema.jsonreferences/question-policy.json
Primary scripts:
scripts/resolve-intent.mjs --json "<prompt>"- If
status=clarify, runscripts/clarify-question.mjs --json '<GuidanceDecision JSON>' - If
status=resolved, runscripts/plan-recipe.mjs --json '<GuidanceDecision JSON>' - Validate with
scripts/validate-recipe.mjs --json '<UIRecipe JSON>'
Only proceed to implementation when ValidationReport.valid is true.
Mode: auto-router
Route automatically with:
scripts/route-mode.mjs --json "<prompt>"
Routing policy:
build-nowwhen prompt contains explicit Dinachi slugs or direct install/add verbs.plan-firstwhen prompt is broad, qualitative, or design-oriented without concrete component selection.- If uncertain, choose
plan-first.
Shared Contracts
The plan-first pipeline uses:
IntentEnvelope:{ request_id, intents, ambiguities, confidence }GuidanceDecision:{ status, reason, question?, options?, candidates? }UIRecipe:{ recipe_id, goal, layout, components, actions, bindings, states }ValidationReport:{ valid, errors, warnings, fixes }
Operating Rules
- Use
references/components.registry.jsonas the source of truth for allowed Dinachi slugs and capabilities. - Keep hard guards minimal and safety-focused.
- Keep warnings advisory; do not block on warnings alone.
- Prefer fast path (
build-now) for concrete requests. - Prefer reliable path (
plan-first) for ambiguous or system-level requests.
Related Skills
openclaw/openclaw-secret-scanning-maintainer
development
VerifiedTrustedCommunity
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
357,764SKILL.mdUpdated Apr 15, 2026
openclaw/openclaw-release-maintainer
development
VerifiedTrustedCommunity
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/openclaw-qa-testing
development
VerifiedTrustedCommunity
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/openclaw-parallels-smoke
development
VerifiedTrustedCommunity
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.
357,764SKILL.mdUpdated Apr 10, 2026