Menu
SoNash project context injected into agent definitions via skills: field
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
| name | sonash-context |
| description | SoNash project context injected into agent definitions via skills: field |
SoNash-specific stack, architecture, and security context consumed by agent
definitions via the skills: field. Provides versioned facts that should NOT be
flagged as invalid (stack is newer than model training cutoff).
skills: [sonash-context]Explore agentlib/, functions/src/docs/ or README.mdlib/firestore-service.ts — add new queries to
service files, not inline in componentstypes/ or functions/src/schemas.tsuseState local, Context global, Firestore serverjournal, daily_logs, inventoryEntries — use
httpsCallable via Cloud Functionssonner toastssanitizeError() from scripts/lib/sanitize-error.js
— never log raw error.message/^\.\.(?:[\/\\]|$)/.test(rel) NOT startsWith('..')httpsCallable, NOT direct Firestore writes/g flag REQUIRED (no /g = infinite loop)functions/src/functions/src/schemas.tsapp/ (Next.js App Router)types/scripts/.claude/agents/.claude/skills/scripts/health/checkers/tests/anymigrateAnonymousUserData handles merges — don't merge manuallyfirebase.jsonsetInterval: define useCallback before effectfile_path:line_number citationssanitizeError(), never raw error.message| Version | Date | Description |
|---|---|---|
| 1.1 | 2026-04-15 | Session #283 ecosystem fix — added required sections (H1 title + When to Use / When NOT to Use / Version History) per SKILL_STANDARDS.md. |
| 1.0 | — | Initial creation (inline stack version facts + security boundaries + return format). |
Structured discovery-first planning for complex tasks. Ask exhaustive categorized questions, build a standalone decision record, then produce a step-by-step implementation plan with audit checkpoints and convergence-loop verification of diagnosis and plan claims for user approval before any code is written.
Multi-agent research engine that decomposes questions, dispatches parallel searcher agents, synthesizes findings with citations and confidence levels, runs mandatory contrarian/OTB challenges, gap-pursuit verification, and cross-model verification via Gemini CLI, and produces structured output with downstream adapters, research index, and management commands.
Pre-flight checklist for work sessions — loads context, runs health scripts, surfaces warnings, and gates on acknowledgment before work begins.
PR Review Retrospective -- actionable analysis of a PR's review cycle with convergence-loop deliverable verification, interactive findings walkthrough, and dashboard for missing retros
Process external PR code review feedback (CodeRabbit, Qodo, SonarCloud, Gemini) through a structured 8-step protocol. Parses all items, categorizes by severity and origin, fixes in priority order, tracks deferred items to TDMS, and captures learnings. This skill processes review feedback — it does not generate reviews.
Query the Content Analysis System (CAS) knowledge base. Search extraction candidates, filter by tags/type/source, search across all analyzed sources.