- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add notque/vexjoy-agent --skill domain -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add notque/vexjoy-agent --skill domain -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add notque/vexjoy-agent --skill domain -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add notque/vexjoy-agent --skill domain -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/notque/vexjoy-agent/tree/HEAD/skills/domain/domainDe l'éditeur
Five domains: SAP Converged Cloud (sapcc) Go review, sapcc compliance audit, OpenSearch SIEM detection engineering, WordPress live validation, and enterprise search. Classify the request into one domain, then follow its section.
10-agent domain-specialist review. Each agent masters one rule domain and scans every package. Differs from SAPCC Audit: audit segments by package (generalist), review segments by rule domain (specialist, cross-package).
Verify sapcc project and map the repo.
head -5 go.mod && grep -c "sapcc" go.mod
find . -name "*.go" -not -path "*/vendor/*" | wc -l
find . -name "*.go" -not -path "*/vendor/*" | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn
Check key imports: go-bits, go-api-declarations, gophercloud, gorilla/mux, database/sql.
Gate: Repo mapped. If no sapcc imports, warn but continue.
Load references/sapcc-review-agent-dispatch-prompts.md for the 10 agent specs.
Dispatch all 10 in ONE message via Agent tool. Each agent gets: path to sapcc-code-patterns.md, assigned sections, domain-specific reference, all .go files to scan, finding output format.
Gate: All 10 dispatched in single message.
Run git status --short to capture modified and untracked files. Collect all
findings. Deduplicate by file:line (keep higher severity). Apply severity
boosts:
Mark quick wins (single-line, no behavioral change, low test risk). Write
sapcc-review-report.md with: verdict, scorecard (10 domains x severity),
quick wins, findings by severity, positives, systemic recommendations.
--fix)Create worktree sapcc-review-fixes. Apply quick wins first. After each group:
go build ./... && go vet ./... && make check 2>/dev/null || go test ./....
If fix breaks tests, revert and note. Commit only when the user asked for commits, as one
lowercase sentence in the AGENTS.md writing style, for example
applied 12 sapcc-review fixes across 5 files to close the quick-win findings.
Full-repo compliance scan. Segments by package (generalist per package).
Verify sapcc project (grep "sapcc" go.mod). Map packages:
find . -name "*.go" -not -path "./vendor/*" | sed 's|/[^/]*$||' | sort -u.
Count files per package. Plan 5-8 agents, 5-15 files each.
Gate: Packages mapped, agents planned.
Load references/sapcc-audit-phase-2-dispatch-agents.md for the dispatch prompt
(11 review areas: over-engineering, dead code, error messages, constructors,
interface contracts, copy-paste, HTTP handlers, database patterns, type patterns,
logging, mixed approaches). Dispatch all in one message via Task tool with
subagent_type=golang-general-engineer.
Deduplicate by file:line. Write sapcc-audit-report.md with: verdict,
must-fix/should-fix/nit counts, per-package summary table. Display verdict,
must-fix count, and top 5 findings inline.
Finding format: [MUST-FIX/SHOULD-FIX/NIT]: summary with file:line, current
code, correct code, and rationale.
Audit only: reads and reports. Does not modify code unless --fix.
SIEM detection authoring and validation on OpenSearch Security Analytics: SIGMA rules, query DSL translation, MITRE ATT&CK mapping, anomaly detection, correlation, and SOC incident escalation.
GET {index}/_mapping;
confirm every rule field exists. Absent fields cause silent failure.PUT _mapping, POST _aliases, not
abstract advice.GET {index}/_mapping for each rule field. Check
cardinality for terms aggregations.references/opensearch-detection-engineering.md for translation
patterns. Apply FP suppression (CIDR, service-account prefixes, time windows).references/opensearch-detection-safety-patterns.md for the full checklist.references/opensearch-incident-escalation.md for template and KPIs.After authoring: "Have I verified every field via GET {index}/_mapping?"
After escalation: "Does the package include all 9 fields?"
After chained monitor: "Does this create a new query index per run?"
After MITRE mapping: "Did I include both technique ID and tactic?"
Loads a published WordPress post in a headless browser and verifies rendering matches what was uploaded. The browser is the source of truth.
Browser backend: Playwright MCP (default). Chrome DevTools MCP when the user says "check in my browser" or wants Lighthouse/performance profiling.
Load references/wordpress-phase-checks.md for the 4-step procedure. Navigate
to URL, wait for content area (try selectors: article -> .entry-content ->
.post-content -> main), remove cookie banners.
Gate: HTTP 200, content selector found. If 4xx/5xx or no selector: screenshot, FAIL, STOP.
Load references/wordpress-validation-checks.md for severity rationale and edge
cases. Load references/wordpress-playwright-tools.md for tool signatures.
Run all 7 checks:
Execute each check via browser tools. Do not reason about outcomes -- run the command and report observed results.
Gate: All 7 checks executed with severity and evidence.
Test three viewports: mobile (375x812), tablet (768x1024), desktop (1440x900).
Per viewport: resize, screenshot, check overflow, check container visibility.
See references/wordpress-phase-checks.md for JS snippets.
Output structured report:
LIVE VALIDATION: {url}
CONTENT INTEGRITY: [PASS/FAIL/WARN] per check with evidence
SEO / SOCIAL: OG tags, meta description with values
RESPONSIVE: per viewport with overflow status and screenshot path
RESULT: {PASS | FAIL - N blockers, M warnings}
Search infrastructure: relevance tuning, query understanding, index management, quality measurement, performance optimization. Always specify target platform and version.
Always load references/search-llm-search-failure-modes.md as a guardrail.
Cross-platform traps: OpenSearch diverges from ES 7.10 on security/ML/alerting.
ES _field_caps changed between 7.x and 8.x. Solr edismax != ES multi_match.
Load on demand when a phase needs detailed lookup data.
Domain-specific: SAP Commerce, OpenSearch detection, WordPress validation, enterprise search.
---name: domaindescription: Domain-specific: SAP Commerce, OpenSearch detection, WordPress validation, enterprise search.---# skills/domain/domain/SKILL.mdFAQ
Téléchargez skills/domain/domain/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/notque/vexjoy-agent.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.