frontend-architecture-review
Skill10 starsChanged 37 days agoMITView on GitHub
Review a frontend architecture at scale, gating micro-frontend adoption BEFORE building (default: modular monolith until 3 or more independently deploying teams and real coordination pain exist). Do not use to design one system (use frontend-system-design), to review a GraphQL or REST contract (use graphql-contract-review or api-contract-review), or with no active task folder (run task-init first).
In this repository98 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11y-auditSkill
- ai-feature-eval-harnessSkill
- api-contract-reviewSkill
- api-runtime-verifySkill
- apply-sweep-triageSkill
- approve-planSkill
- approve-proposedSkill
- app-runtime-verifySkill
- atom-audit-fleetSkill
- atom-auditSkill
- autonomous-boardSkill
- autonomous-readinessSkill
- autonomous-runSkill
- backend-system-designSkill
- branch-commitSkill
- capture-observationSkill
- capture-referencesSkill
- code-context-mapSkill
- code-locateSkill
- color-contrast-architectSkill
- compact-task-memorySkill
- component-specSkill
- contract-signoffSkill
- db-context-postgresSkill
- db-context-supabaseSkill
- decision-interviewSkill
- delivery-assetSkill
- design-bootstrapSkill
- design-spec-reviewSkill
- direction-adjustSkill
- external-research-fleetSkill
- external-researchSkill
- extract-foundations-from-screensSkill
- feature-library-scout-fleetSkill
- feature-library-scoutSkill
- foundation-auditSkill
- frontend-system-designSkill
- godot-runtime-verifySkill
- godot-scene-planSkill
- graphql-contract-reviewSkill
- harvest-session-learningsSkill
- image-to-specSkill
- impact-analysisSkill
- implement-approved-sliceSkill
- implementation-planSkill
- implement-fleetSkill
- implement-slice-complementSkill
- im-stuckSkill
- incident-triageSkill
- invariants-and-non-goalsSkill
- inventory-snapshotSkill
- journey-mapSkill
- jtbd-switch-interviewerSkill
- mcp-server-vetSkill
- migration-safety-stewardSkill
- pattern-docSkill
- performance-budgetSkill
- portfolio-reviewSkill
- post-deploy-verifierSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. About 0 are common, 12 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
Read these sections in WORKFLOW_OPERATING_SYSTEM.md first:
- Distinctive: line 31
Read additional sections only when relevant to this command's role.
- Distinctive: line 42
Do not implement code. This command reviews architecture only.
- Very specific: line 43
Capability-routed: Read the stack from SOURCE_OF_TRUTH.md or DECISIONS.md.
- Distinctive: line 45
Step 2: Boundaries by team and domain: Check that splits (modules or micro-frontends) are aligned to team ownership and business domains, …
- Distinctive: line 46
Step 3: Independent deployability: When micro-frontends are in scope, check that there is no build-time npm coupling of remotes into the …
- Distinctive: line 47
Step 4: Shared dependencies are governed: Check for a singleton policy on framework runtimes, declared version ranges and a defined …
- Distinctive: line 48
Step 5: Design-system sharing: Check that primitives ship as a versioned UI-kit and tokens (so visual consistency does not depend on …
- Distinctive: line 49
Step 6: Style and runtime isolation: Check the style-scoping strategy (CSS modules, scoped CSS, Shadow DOM) prevents cross-app cascade, and …
- Distinctive: line 50
Step 7: Cross-app communication: Check that communication across boundaries is minimal and indirect (custom events, container callbacks, …
- Distinctive: line 51
Step 8: Routing contract and composition tier: Check that URL-space ownership is defined, deep-links and browser history work across …
- Distinctive: line 52
Step 9: Rendering strategy at scale: Check that the rendering strategy is chosen per route, not per app (SSG or ISR for cacheable, SSR or …
- Distinctive: line 53
Step 10: State management at scale: Check the split between local UI state, global app state, and server-cache state is deliberate, and …
- Very specific: line 57
Treat task-memory write policy per WORKFLOW_OPERATING_SYSTEM.md: write the file and mark it APPLIED.
- Very specific: line 86
Follow ## Global output contract in WORKFLOW_OPERATING_SYSTEM.md for APPLIED / PROPOSED / SKIP rules.
- Distinctive: line 97
If the architecture is sound, the assessment says so clearly (no invented findings).
- Very specific: line 99
Before declaring this output done, confirm it satisfies the shared Definition of done (command outputs) and Gate conditions in …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Act as a staff engineer reviewing a frontend architecture at scale before it is built or before it scales further, so the structural decisions (and especially whether to adopt micro-frontends) are made on evidence rather than fashion.
Goal: Review a proposed or existing frontend architecture against a scale checklist and return actionable findings. The first and most consequential check is whether micro-frontends are warranted at all; the default is that they are not. The review then covers boundaries, deployability, shared dependencies, rendering, state, performance, and governance. Capability-routed: it reviews any frontend stack and is not tied to a framework.
Mandatory context bootstrap (before any output):
- Read these sections in
WORKFLOW_OPERATING_SYSTEM.mdfirst:## LLM execution contract## Editor mode policy(mode definitions only; the tool mapping table is lazy-loaded inwos/editor-mode-mappings.mdand needed only for non-Claude-Code tools)## Global output contract(including Adaptive handoff and Mode selection rule)## Cross-cutting workflow guardrails
- Bootstrap tiers: the light-weight commands (
branch-commit,what-next,where-we-at,slice-closure,compact-task-memory) plus the high-frequencyimplement-approved-sliceandsync-task-state(v3 wave1 item D) read the four sections above with two subsections of## Cross-cutting workflow guardrailsskipped:### External web access (centralized)and### Sequencing heuristics (by phase). Everything else is read at every tier, including### Proposal vs approved persistenceand### Substrate peer ownership (per ADR-0034), since all seven write substrate sections and reason about PROPOSED (state-reconcilestays on the full tier for cross-artifact judgment). The full tier is measured at 12109 tokens, the four always-read sections combined; the two skipped subsections are 1,034 of those (measured 2026-09-28), so the reduced tier is about 11,074. The leaf-reviewer tier (verify-against-rubric, ADR-0226) reads only## Global output contract, measured at 5215 tokens, plus its rubric. - Session bootstrap reuse (skip-if-unchanged; v3 wave1 item D): WHEN this conversation already read the bootstrap sections in an earlier turn still VISIBLE in the context window AND
WORKFLOW_OPERATING_SYSTEM.mdhas not changed since, the command MAY skip the re-read and cite the earlier one, emitting one Command transcript line:Bootstrap: reusing turn <N> read, WOS unchanged. Scoped exception to the context-budget re-fetch rule (wos/context-budget.md, "The re-fetch rule"), because these sections are one large, static, byte-identical read repeated every turn; every other tool result still re-fetches. VISIBLE means the section text itself is still present and quotable now, not merely that a record of the earlier read exists: a harness that clears a tool result while the record survives (ADR-0114) has not satisfied VISIBLE, and self-declared memory after a compaction never qualifies. A stateless-per-turn harness is excluded. The transcript line is mandatory; a silent skip is invalid output. - Resolving the spec and
wos/<topic>.md: canonical repository FIRST. Otherwise use active-adapter docs:~/.claude/workflow-docs(CLAUDE_WORKFLOW_DOCS_DIR),~/.cursor/workflow-docs(WORKFLOW_DOCS_DIR; project.cursor/workflow-docson project installs),~/.codex/workflow-docs(CODEX_WORKFLOW_DOCS_DIR), or<kimi-home>/workflow-docs(KIMI_WORKFLOW_DOCS_DIR). Nonempty overrides win. Kimi home:KIMI_CODE_HOME, else existing~/.kimi-code, else existing~/.kimi, default~/.kimi-code. Use one root for both paths; try other adapters if absent or unknown. Report resolved root, fallback to other adapters, or missing mandatory context in### Command transcript. Installed snapshots refresh and prune retired topics only on sync. - Read additional sections only when relevant to this command's role.
- Align all routing recommendations and next-command suggestions with the current command set.
- Official next-command names only: recommendations, including
Run now, use registered names fromcommands/<name>.mdorcommands/<name>/SKILL.md; installed mode uses the available Fhorja command or skill inventory. No invented aliases.Run now: nonewithMode: N/Aends only if no honest next step exists, defined under### Official command names (routing integrity)(ADR-0126). Required inputs: - active task folder path
- TASK_STATE.md, DECISIONS.md, IMPLEMENTATION_PLAN.md (the proposed architecture lives here)
- optional: the existing repo layout, build tooling, and team boundaries (for grounding the review)
- optional: captured references in
projects/<client>__<project>/REFERENCES.mdfor the chosen stack and any micro-frontend tooling
Operating rules:
- Handoff: end with the adaptive
### Handoffblock perWORKFLOW_OPERATING_SYSTEM.md## Global output contract(Mode A compact or Mode B full). - Do not implement code. This command reviews architecture only. If the architecture is sound, say so clearly; do not invent findings.
- Capability-routed. Read the stack from SOURCE_OF_TRUTH.md or DECISIONS.md. Name a framework or a federation tool only when the task already chose it.
- Step 1: Micro-frontend adopt-or-don't-adopt gate (do this first). Default to "you probably do not need micro-frontends." Recommend adopting them only when all hold: 3 or more teams that genuinely need to deploy independently, real cross-team coordination pain today, and boundaries that fall on business domains (Conway's law), not technical layers. When they are not warranted, say so plainly, recommend a modular monolith, and skip the federation-specific checks (steps 4, 6 isolation, 8 composition tier, governance manifest) as not applicable.
- Step 2: Boundaries by team and domain. Check that splits (modules or micro-frontends) are aligned to team ownership and business domains, with a named owner per boundary, not split by technical layer (a "forms team", a "styling team").
- Step 3: Independent deployability. When micro-frontends are in scope, check that there is no build-time npm coupling of remotes into the host that forces lockstep releases; runtime integration (module federation remotes, web components, import maps) is what buys real independent deploy.
- Step 4: Shared dependencies are governed. Check for a singleton policy on framework runtimes, declared version ranges and a defined behavior on version mismatch, and a documented upgrade path so one team's bump does not break others. Flag duplicated framework copies inflating the payload.
- Step 5: Design-system sharing. Check that primitives ship as a versioned UI-kit and tokens (so visual consistency does not depend on copy-paste), while domain-specific components stay local to their owner.
- Step 6: Style and runtime isolation. Check the style-scoping strategy (CSS modules, scoped CSS, Shadow DOM) prevents cross-app cascade, and that a failing or slow remote is isolated by an error boundary and degrades gracefully rather than crashing the whole page.
- Step 7: Cross-app communication. Check that communication across boundaries is minimal and indirect (custom events, container callbacks, the URL as a contract), with no shared mutable global state recreating the coupling the split was meant to remove.
- Step 8: Routing contract and composition tier. Check that URL-space ownership is defined, deep-links and browser history work across boundaries, and the composition tier (client app shell, server-side, or edge) matches the routing and the first-paint and SEO needs.
- Step 9: Rendering strategy at scale. Check that the rendering strategy is chosen per route, not per app (SSG or ISR for cacheable, SSR or streaming for personalized, client-side for app shells, server components to cut shipped JS), with a stated TTFB, SEO, or personalization rationale.
- Step 10: State management at scale. Check the split between local UI state, global app state, and server-cache state is deliberate, and that the real-time transport (WebSocket, SSE, polling) is chosen per use case rather than defaulted.
- Step 11: Performance budget across the composition. Check there is no unbounded runtime waterfall of remote fetches, that LCP and total-blocking-time budgets exist, that duplicated dependencies are measured, and that remotes are lazy-loaded with CDN-cached entries. Compose with
performance-budgetfor the numeric per-metric table rather than re-deriving it. - Step 12: Governance and failure handling. Check that cross-cutting concerns (auth, observability and tracing across boundaries, error reporting) are centralized and consistent, that a versioned integration manifest resolves remotes and permissions without coordinated redeploys, and that each boundary has a blast-radius-bounded rollback story (canary or blue-green per remote, a defined fallback for a broken remote).
- Ground external claims. When a check depends on a specific tool or pattern (a module-federation directive, an edge-composition product), ground it in a captured
REFERENCES.mdentry; when it is not captured, name the gap and route tocapture-referencesrather than asserting it from memory. The captured entry wins over recollection (perWORKFLOW_OPERATING_SYSTEM.md## Evidence priority). - Treat task-memory write policy per
WORKFLOW_OPERATING_SYSTEM.md: write the file and mark itAPPLIED.
Required output:
- Architecture summary (the surfaces, the proposed boundaries, the stack and any federation tooling, the team topology)
- Micro-frontend verdict (adopt / do not adopt) with the reason, stated up front
- Findings per check (steps 2 through 12), each referencing the specific boundary, route, or concern, with federation-only steps marked not applicable when micro-frontends are not adopted
- Overall assessment (sound / needs revision / has blocking issues)
- Recommended next command
Claim grounding (active epistemic humility)
Claim grounding (active epistemic humility). This block governs what you may assert and how you record it. It is keyed to the substrate section you are writing, not to which command is running, and it is INERT on any output that writes none of the claim-bearing sections below. Full contract and rationale: wos/active-epistemic-humility.md.
- When this applies. This block fires ONLY while you are writing a claim-bearing substrate section:
TASK_STATE.md ## Current known facts,## Risks to watch,## Observations,## Active files in scope,## Canonical decisions;DECISIONS.md ## Locked decisions;IMPLEMENTATION_PLAN.md ## Current gaps,## Risks and mitigations;IMPACT_ANALYSIS.md;EXTERNAL_RESEARCH.md;REFERENCES.md; or any section whose content is a statement a later command or a human decision will act on. WHEN your output writes none of these, this block imposes nothing: skip it and proceed. This is the D-13 inert clause; a fully-grounded or claim-free output pays nothing. - The unit is the load-bearing claim. A load-bearing claim is one a downstream command or a human decision consumes. A passing aside is not load-bearing; a statement someone will act on is. Apply the rest of this block per load-bearing claim, not per sentence.
- Ground it or abstain. Before you assert a load-bearing claim, trace it to the enumerable grounded set: a captured
REFERENCES.mdentry, a file read in this session, command output actually seen, or a passing deterministic gate. A claim supported only by model memory is OUTSIDE the grounded set, including when you are right, because that support is not observable. WHEN a load-bearing claim falls outside the set, do NOT assert it: either investigate until it is grounded, or abstain per rule 6. - Status records provenance, never confidence. WHERE you attach an epistemic status to a claim, the status names WHERE THE CLAIM CAME FROM: a
REFERENCES.mdentry title, a file path plus line, or the gate output it came from. It SHALL NOT express a degree of certainty. Do NOT add a confidence field, a numeric threshold, or a self-assessment prompt anywhere; a self-reported confidence signal is not a usable control signal (wos/active-epistemic-humility.mdPart 1.3). A status whose referent slot is empty is read as UNKNOWN, not as a weak yes. - Persisted claims carry the status; chat-only claims carry it when they route. Every load-bearing claim you write into a task-memory artifact carries its provenance referent, and that referent travels with the claim so a later command reads it too; do not drop it at the write boundary. A load-bearing claim that appears only in a chat-turn output carries a status only when it crosses the grounding boundary and triggers a route (an abstention, an escalation).
- Abstain as a routed continuation, never a bare refusal. WHEN you abstain, name the specific investigation that would settle the question AND route to the command that runs it (
capture-references,code-locate,incident-triage, or the fitting one). A withholding that stalls the work is invalid output. Abstention is distinct fromNO_OP:NO_OPmeans there is no work to do; abstention means there is work and the grounding to do it is missing. - An unfired gate is not evidence. The absence of a fired check does not mean grounding existed. Do not read silence here as a pass.
Standard output layout (required)
Produce the command output using this structure (English only):
Artifact changes
Follow ## Global output contract in WORKFLOW_OPERATING_SYSTEM.md for APPLIED / PROPOSED / SKIP rules. Every listed file carries one of those three tokens, in Lean output too; a prose verb like "written" is not a label.
Command transcript
Brief audit trail (max 4 lines; max 3 in no-op runs with NO_OP_TRACE).
Handoff
Use the adaptive ending format of WORKFLOW_OPERATING_SYSTEM.md ## Global output contract. Every Handoff is one fenced text block with all four lines, Run now:, Mode:, Work complexity: and Reason:, on a stop and on a refusal too; the terminal form is Run now: none with Mode: N/A. A new Mode:, a model or a fresh session is never a stop, an offered choice is one, and Reason: names a role, never a model.
Definition of done (command output)
- The micro-frontend adopt-or-don't-adopt verdict is stated first, with the reason, and defaults against adoption unless the three conditions hold.
- Findings reference the specific boundary, route, or concern and the check that failed; federation-only steps are marked not applicable when micro-frontends are not adopted (no findings manufactured for an architecture that does not use them).
- Claims about a specific federation tool or pattern are grounded in a captured reference, not asserted from memory.
- If the architecture is sound, the assessment says so clearly (no invented findings).
- Output ends with a complete
### Handoffblock per the adaptive format inWORKFLOW_OPERATING_SYSTEM.md## Global output contract. - Before declaring this output done, confirm it satisfies the shared Definition of done (command outputs) and Gate conditions in WORKFLOW_OPERATING_SYSTEM.md.
Quality bar: A reviewer gets an honest adopt-or-don't verdict on micro-frontends and findings that name the boundary or route and the rule they break, with no structure prescribed that the team's scale does not justify.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

