By Skobyn
Internal toolset that prepares a JSSI board for an architecture review of an app — auto-generates the architecture-vault packet (Mermaid layered, swim-lane, and drill-down diagrams; a hybrid findings report; and a structured review brief) from a copy of the app repo. Orchestrates the five JSSI mappers plus three native engines. Read-only on the codebase; renders no overall verdict — the board owns the thumbs-up.
Use when an architect or CI pipeline has dependency-boundary and user-flow JSON maps and needs Mermaid diagram output — a layered architecture flowchart, a swim-lane sequenceDiagram per journey, and a drill-down flowchart per journey with NO-GO overlays. Trigger phrases include "generate architecture diagrams", "diagram these maps", "produce Mermaid from the boundary map", or "visualize the user flows". Accepts both maps inline. Emits ONLY Mermaid fenced code blocks — zero prose anywhere in output.
Use when an architect, tech lead, or CI pipeline has completed the five JSSI mapper passes (dependency-boundary, user-flow, resilience, performance, contract-inventory) plus a risk profile and standards config and needs a machine-readable findings report — suitable trigger phrases include "run the architecture findings engine", "produce a findings report from these maps", "check the maps against our standards", or "do a pre-JAD findings pass". Accepts all mapper JSON outputs plus risk-profile and standards inline in the prompt. Emits exactly one fenced JSON block with NO-GO/BLOCKING findings (machine-verifiable, grounded evidence required) and ADVISORY/QUESTION findings (board_call=true). Does NOT write code, suggest fixes, run tools, or render an overall verdict.
Use when a developer, tech lead, or CI pipeline needs to execute the full architecture review pipeline from repo path to vault packet — trigger phrases include "run arch-review", "orchestrate the architecture review", "arch-review on an app repo path", or "sequence the architecture mappers and engines". Runs risk-classify first, fans out all five mappers in parallel (dependency-boundary-mapper, user-flow-mapper, resilience-mapper, performance-mapper, contract-inventory-mapper), then drives arch-diagram-engine and arch-findings-engine after mapper outputs land, then calls arch-vault-assembler last. Fail-closed on empty or missing repo path — no sub-skills dispatched. Degraded-not-silent when a mapper errors — pipeline continues and annotates the degraded note. Cap-logged when flow count exceeds drill cap. Emits ONE fenced JSON ORCHESTRATION TRACE, no prose anywhere.
Use when arch-findings-engine has produced a findings object, arch-diagram-engine has produced a Mermaid diagram set, and a risk profile plus conformance summary are available — to assemble the complete architecture-vault packet for a JSSI board review. Trigger phrases include "assemble the vault packet", "produce the 00-brief", "build the architecture review brief", or "package the findings for the board". Accepts all inputs inline. Emits 00-brief.md (seven fixed sections in mandatory order) followed by a fenced manifest block listing every packet file. Never renders an overall verdict — the board owns the thumbs-up.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub skobyn/upskill-me --plugin jssi-architecture-reviewUse when a tech lead, senior developer, or author needs a structured prep briefing before a live synchronous peer code review — given a diff or codebase path, produces intent narrative, correctness questions, design-fit observations, advisory security/standards/performance findings, a verdict suggestion, and a re-review action-item checklist. Read-only; never writes code or mutates anything.
Traxxall author-side delivery skill set. Pull/analyze ADO work items into structured intake briefs (flagging Requires-Specification when under-specified), author implementation specs with blind-QA-ready acceptance criteria, draft/create PBIs and child dev Tasks with compliant users/{short}/{WI#}-… branches, and outline UnitTests.Core/TransactionScope dev tests — all under Traxxall conventions (branch/PR rules incl. VS403660, PBI/Bug/Task model, area Traxxall Solution, AI tags, dual-framework legacy vs modern, egress-safe dev.azure.com auth). Drafts by default; creates ADO items only on explicit go. Never authors QA tests (separate traxxall-delivery-qa plugin) and never runs destructive test projects.
A 'Memory and a Mirror' agentic harness for long-running unattended coding sessions: a prunable structured learnings file read at session start, a proof-discipline gate that blocks 'done' claims without fresh cited evidence, and a fresh-context reviewer subagent that returns only a gap list against spec. Chains into one plan -> act -> prove -> review -> remember loop via /mirror-loop. Model-agnostic by construction.
Traxxall blind, adversarial QA skill set — deliberately isolated from implementation. From the acceptance criteria + the running TEST app ONLY (never the diff, PR, product source, or dev-side tests), authors adversarial Playwright suites covering happy/edge/negative/abuse/cross-module cases with role/text locators, deterministic waits (no hard sleeps), storageState auth, and trace/screenshot/video on failure; records PASS/FAIL/ERROR for the PH QA / Ready-to-Test flow. Refuses any leaked implementation context (isolation gate). Targets TEST only, never prod.
Reviews a target repository and produces two grounded board-review deliverables: a self-contained JSSI-branded interactive HTML viewer (16 diagram tabs, built by editing a copy of the approved reference template verbatim) and docs/architecture/index.md (narrative plus two strictly separate tables — Findings for code-level gaps, Open Decisions for architecture choices needing a human ruling). Supports a silent/autonomous generation mode and a distinct post-complete interview mode that walks a reviewer through Open Decisions one row at a time.
Harness-native ECC operator layer - 60 agents, 232 skills, 75 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
v9.54.0 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).