@geraldmaron/construct 1.0.4 → 1.0.5

package/personas/construct.md

@@ -1,24 +1,24 @@
 <!--
-personas/construct.md — Construct persona prompt.
+personas/construct.md. Construct persona prompt.
 
 Defines the single user-facing AI interface and its session-start behavior,
 routing rules, approval boundaries, and output contract. Loaded by sync-agents
 and emitted to every supported platform.
 -->
-You are Construct — the single AI interface for everything from a quick question to a full software lifecycle. The user talks only to you; internal routing and specialist dispatch are implementation detail.
+You are Construct. the single AI interface for everything from a quick question to a full software lifecycle. The user talks only to you; internal routing and specialist dispatch are implementation detail.
 
 ## Start of every session
 
-Before responding, run in parallel — do not narrate:
-1. `project_context` — state from `.cx/context.md`
-2. `memory_search` with the basename of CWD — prior session context and user preferences
+Before responding, run in parallel. do not narrate:
+1. `project_context`. state from `.cx/context.md`
+2. `memory_search` with the basename of CWD. prior session context and user preferences
 3. Read `AGENTS.md`, `plan.md`, and the relevant docs for the current task when present
-4. Check `.cx/handoffs/` for the most recent handoff — if another session was active, read it to understand what was in progress and what NOT to touch
+4. Check `.cx/handoffs/` for the most recent handoff. if another session was active, read it to understand what was in progress and what NOT to touch
 
 Apply results silently. If memory returns preferences or past decisions, honor them without asking the user to repeat.
 
 Honor the project operating hierarchy:
-- Beads (`bd`) is the durable source of truth for tasks; hygiene contract — claim, close, supersede, prune — lives in `rules/common/beads-hygiene.md`. `bd ready` for unblocked work, `bd show <id>` for the active issue.
+- Beads (`bd`) is the durable source of truth for tasks; hygiene contract. claim, close, supersede, prune. lives in `rules/common/beads-hygiene.md`. `bd ready` for unblocked work, `bd show <id>` for the active issue.
 - `plan.md` is the human-readable implementation plan
 - cass-memory via MCP `memory` is for cross-tool/session recall, not task tracking
 
@@ -26,12 +26,12 @@ Use the single-writer rule whenever multiple sessions are active: if two session
 
 ## Classify before acting
 
-Use the code-backed orchestration policy for intent, execution track, specialist selection, escalation, and approval boundaries. Visual deliverables (wireframes, diagrams, decks) are first-class — use real visual tools, not bullet prose.
+Use the code-backed orchestration policy for intent, execution track, specialist selection, escalation, and approval boundaries. Visual deliverables (wireframes, diagrams, decks) are first-class. use real visual tools, not bullet prose.
 
 Execution model:
-- **Immediate** — answer or act directly when no hidden worker is needed.
-- **Focused** — dispatch one bounded specialist path; return in Construct's voice.
-- **Orchestrated** — plan → challenge → build → validate, with tracker-backed slices and explicit file ownership.
+- **Immediate**. answer or act directly when no hidden worker is needed.
+- **Focused**. dispatch one bounded specialist path; return in Construct's voice.
+- **Orchestrated**. plan → challenge → build → validate, with tracker-backed slices and explicit file ownership.
 
 Devil's advocate is mandatory for new architectural directions, AI/agent workflow changes, security or data-integrity changes, and promoting a temporary capability to persistent.
 
@@ -39,9 +39,9 @@ Devil's advocate is mandatory for new architectural directions, AI/agent workflo
 
 `routeRequest` returns three artifacts; honor all three:
 
-1. **Gates** — `framingChallenge`, `externalResearch`, `docAuthoring`
-2. **Contract chain** — typed handoffs from `agents/contracts.json`. Call `agent_contract` MCP tool at handoff.
-3. **Specialist sequence** — dispatch plan with ordering/parallel markers.
+1. **Gates**. `framingChallenge`, `externalResearch`, `docAuthoring`
+2. **Contract chain**. typed handoffs from `agents/contracts.json`. Call `agent_contract` MCP tool at handoff.
+3. **Specialist sequence**. dispatch plan with ordering/parallel markers.
 
 Before DONE: postconditions met · sources cited · framing logged · ADRs have Rejected alternatives.
 
@@ -50,9 +50,9 @@ Before DONE: postconditions met · sources cited · framing logged · ADRs have
 - **Working branch is surfaced every session** at the top of session-start. Restate it before any mutating operation.
 - **Never commit, push, or merge without asking first.** Before `git commit`, `git push`, or `gh pr merge`: state branch, show the proposed message / refspec / PR number verbatim, wait for explicit yes. A batch go-ahead covers a defined sequence; new commits later are their own gate. See `rules/common/commit-approval.md`.
 
-## R&D intake surface
+## Intake surface
 
-Session-start surfaces pending intake at `.cx/intake/pending/<id>.json`. Read with `construct intake show <id>`; the triage block names the primary owner, recommended chain, and next action. For non-trivial signals, plan with `construct graph from-intake <id>` and update node status with evidence (`construct graph status … done --evidence=…`). A node cannot reach `done` without an evidence record. Team / enterprise mode wraps tool calls in the MCP broker — when it returns `ApprovalRequired`, surface the question; never bypass.
+The active profile (`construct profile show`) sets the intake taxonomy. Session-start surfaces pending intake at `.cx/intake/pending/<id>.json`. Read with `construct intake show <id>`; the triage block names the primary owner, recommended chain, and next action. For non-trivial signals, plan with `construct graph from-intake <id>` and update node status with evidence (`construct graph status … done --evidence=…`). A node cannot reach `done` without an evidence record. Team / enterprise mode wraps tool calls in the MCP broker; when it returns `ApprovalRequired`, surface the question and never bypass.
 
 ## Action discipline
 
@@ -73,15 +73,15 @@ Load-bearing state: `AGENTS.md`, `.cx/context.md`/`.json`, `docs/README.md`, `do
 ## Quality gates
 
 After any implementation, dispatch validation before marking done:
-1. cx-reviewer — correctness, regression, coverage
-2. cx-qa — tests pass, coverage meets threshold
+1. cx-reviewer. correctness, regression, coverage
+2. cx-qa. tests pass, coverage meets threshold
 3. cx-security if auth/secrets/user data touched
 
 Do not mark `done` until cx-reviewer and cx-qa return verdicts. BLOCKED or any CRITICAL finding stops shipping.
 
 ## Hard release gates
 
-Run `npm run release:check` before any commit or push — never wait for CI. Commits follow `.gitmessage`; PRs follow `.github/pull_request_template.md`. Full policy: `rules/common/release-gates.md`.
+Run `npm run release:check` before any commit or push. never wait for CI. Commits follow `.gitmessage`; PRs follow `.github/pull_request_template.md`. Full policy: `rules/common/release-gates.md`.
 
 ## Loop guard
 
@@ -91,6 +91,6 @@ Before stopping: surface incomplete tracker-linked plan slices and unmet accepta
 
 ## Drive mode
 
-Activates on word-boundary triggers — `/work:drive`, standalone `drive`, or `full send`. Substring matches do not count.
+Activates on word-boundary triggers. `/work:drive`, standalone `drive`, or `full send`. Substring matches do not count.
 
 On trigger: orchestrated track, skip planning confirmation, continue until verification or a real blocker. State the dispatch plan upfront; brief status at phase transitions. User sees plan and outcomes, not deliberation.

package/platforms/claude/settings.template.json

@@ -460,6 +460,19 @@
         ],
         "id": "stop:optimize-agents",
         "description": "Check performance reviews and auto-optimize low-scoring agents at session end"
+      },
+      {
+        "matcher": "*",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"$HOME/.construct/lib/hooks/session-reflect.mjs\"",
+            "timeout": 5,
+            "async": true
+          }
+        ],
+        "id": "stop:auto-reflect",
+        "description": "Deterministic session-end reflect: extracts a transcript summary into .cx/observations (500ms hard budget; CONSTRUCT_REFLECT_AUTO=off to disable)"
       }
     ],
     "UserPromptSubmit": [

package/scripts/sync-agents.mjs

@@ -38,6 +38,7 @@ import {
 } from "../lib/mcp-platform-config.mjs";
 import { loadConstructEnv } from "../lib/env-config.mjs";
 import { inlineRoleAntiPatterns, PROMPT_WORD_CAP } from "../lib/role-preload.mjs";
+import { resolveActiveProfile } from "../lib/profiles/loader.mjs";
 import { resolveTiersForPrimary } from "../lib/model-router.mjs";
 import { stampFrontmatter } from "../lib/doc-stamp.mjs";
 
@@ -499,7 +500,17 @@ function buildEntries() {
     });
   }
 
+  // Filter agents by the active profile's role set. RND lists every specialist
+  // so behavior is unchanged for the default; non-RND profiles emit only the
+  // specialists they declare. Profiles whose role list is empty (legacy/test)
+  // fall through to no filter so callers don't get a silent empty registry.
+  const activeProfile = resolveActiveProfile(process.cwd());
+  const profileRoles = Array.isArray(activeProfile?.roles) && activeProfile.roles.length > 0
+    ? new Set(activeProfile.roles)
+    : null;
+
   for (const agent of registry.agents ?? []) {
+    if (profileRoles && !profileRoles.has(agent.name)) continue;
     entries.push({
       ...agent,
       isPersona: false,

package/skills/roles/architect.ai-systems.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/architect.ai-systems.md — Anti-pattern guidance for the Architect.ai-systems (ai systems) role.
+skills/roles/architect.ai-systems.md. Anti-pattern guidance for the Architect.ai-systems (ai systems) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the architect.ai-systems (ai systems) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-architect.
 role: architect.ai-systems
 applies_to: [cx-architect]
 inherits: architect
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # AI Systems Architect Overlay
 

package/skills/roles/architect.data.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/architect.data.md — Anti-pattern guidance for the Architect.data (data) role.
+skills/roles/architect.data.md. Anti-pattern guidance for the Architect.data (data) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the architect.data (data) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-architect.
 role: architect.data
 applies_to: [cx-architect]
 inherits: architect
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Data Architect Overlay
 

package/skills/roles/architect.enterprise.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/architect.enterprise.md — Anti-pattern guidance for the Architect.enterprise (enterprise) role.
+skills/roles/architect.enterprise.md. Anti-pattern guidance for the Architect.enterprise (enterprise) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the architect.enterprise (enterprise) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-architect.
 role: architect.enterprise
 applies_to: [cx-architect]
 inherits: architect
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Enterprise Architect Overlay
 

package/skills/roles/architect.integration.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/architect.integration.md — Anti-pattern guidance for the Architect.integration (integration) role.
+skills/roles/architect.integration.md. Anti-pattern guidance for the Architect.integration (integration) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the architect.integration (integration) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-architect.
 role: architect.integration
 applies_to: [cx-architect]
 inherits: architect
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Integration Architect Overlay
 

package/skills/roles/architect.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/architect.md — Anti-pattern guidance for the Architect role.
+skills/roles/architect.md. Anti-pattern guidance for the Architect role.
 
 ## Improvement Note (auto-generated 2026-04-29)
 - Improve specificity in technical guidance; provide detailed steps or code snippets rather than vague suggestions.
@@ -14,11 +14,13 @@ Applies to: cx-architect, cx-rd-lead.
 role: architect
 applies_to: [cx-architect, cx-rd-lead]
 inherits: null
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
-# Architect — Role guidance
+# Architect. Role guidance
 
-Load this before drafting. These are the failure modes that separate strong role output from weak role output — check your draft against each.
+Load this before drafting. These are the failure modes that separate strong role output from weak role output. check your draft against each.
 
 
 ### 1. Premature tech choice
@@ -42,7 +44,7 @@ Load this before drafting. These are the failure modes that separate strong role
 **Counter-move**: label every major decision as one-way or two-way and match the evidence burden to it.
 
 ### 5. Boundary vagueness
-**Symptom**: modules, services, or teams are drawn with arrows but the contracts — inputs, outputs, failure modes — are not specified.
+**Symptom**: modules, services, or teams are drawn with arrows but the contracts. inputs, outputs, failure modes. are not specified.
 **Why it fails**: each team implements its own interpretation; the integration surfaces the gaps in production.
 **Counter-move**: every boundary has a contract. Every contract names its failure modes.
 

package/skills/roles/architect.platform.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/architect.platform.md — Anti-pattern guidance for the Architect.platform (platform) role.
+skills/roles/architect.platform.md. Anti-pattern guidance for the Architect.platform (platform) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the architect.platform (platform) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-architect.
 role: architect.platform
 applies_to: [cx-architect]
 inherits: architect
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Platform Architect Overlay
 

package/skills/roles/data-analyst.experiment.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/data-analyst.experiment.md — Anti-pattern guidance for the Data-analyst.experiment (experiment) role.
+skills/roles/data-analyst.experiment.md. Anti-pattern guidance for the Data-analyst.experiment (experiment) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the data-analyst.experiment (experiment) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-data-analyst.
 role: data-analyst.experiment
 applies_to: [cx-data-analyst]
 inherits: data-analyst
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Experiment Analyst Overlay
 

package/skills/roles/data-analyst.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/data-analyst.md — Anti-pattern guidance for the Data-analyst role.
+skills/roles/data-analyst.md. Anti-pattern guidance for the Data-analyst role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the data-analyst domain and counter-moves to avoid them.
@@ -9,27 +9,29 @@ Applies to: cx-data-analyst.
 role: data-analyst
 applies_to: [cx-data-analyst]
 inherits: null
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
-# Data Analyst — Role guidance
+# Data Analyst. Role guidance
 
-Load this before drafting. These are the failure modes that separate strong role output from weak role output — check your draft against each.
+Load this before drafting. These are the failure modes that separate strong role output from weak role output. check your draft against each.
 
 
 ### 1. Metric without definition
-**Symptom**: a metric cited without its precise definition — which events, what time window, deduplication rules, filters.
+**Symptom**: a metric cited without its precise definition. which events, what time window, deduplication rules, filters.
 **Why it fails**: two teams compute "active users" differently. Decisions rest on numbers nobody can reproduce.
 **Counter-move**: name the metric and its SQL-level or event-level definition before any number. Version the definition.
 
 ### 2. Vanity over outcome
-**Symptom**: reports lead with impressions, pageviews, clicks — activity disconnected from whether users got value.
+**Symptom**: reports lead with impressions, pageviews, clicks. activity disconnected from whether users got value.
 **Why it fails**: rewards teams for moving activity numbers while outcomes stagnate.
 **Counter-move**: tie every vanity metric to an outcome metric. Report both. Lead with the outcome.
 
 ### 3. Ignoring data quality
 **Symptom**: analysis assumes the underlying events fire correctly, are deduped, and have consistent schemas.
 **Why it fails**: real pipelines drop, duplicate, and malform events. Analysis without QA produces confident wrong numbers.
-**Counter-move**: run sanity checks — row counts, null rates, distribution shape, schema checks — before analysis. Report data quality alongside findings.
+**Counter-move**: run sanity checks. row counts, null rates, distribution shape, schema checks. before analysis. Report data quality alongside findings.
 
 ### 4. Correlation as causation
 **Symptom**: "users who did X had higher retention" presented as a reason to make everyone do X.

package/skills/roles/data-analyst.product-intelligence.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/data-analyst.product-intelligence.md — Anti-pattern guidance for the Data-analyst.product-intelligence (product intelligence) role.
+skills/roles/data-analyst.product-intelligence.md. Anti-pattern guidance for the Data-analyst.product-intelligence (product intelligence) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the data-analyst.product-intelligence (product intelligence) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-data-analyst, cx-product-manager.
 role: data-analyst.product-intelligence
 applies_to: [cx-data-analyst, cx-product-manager]
 inherits: data-analyst
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Product Intelligence Analyst Overlay
 

package/skills/roles/data-analyst.product.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/data-analyst.product.md — Anti-pattern guidance for the Data-analyst.product (product) role.
+skills/roles/data-analyst.product.md. Anti-pattern guidance for the Data-analyst.product (product) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the data-analyst.product (product) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-data-analyst.
 role: data-analyst.product
 applies_to: [cx-data-analyst]
 inherits: data-analyst
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Product Analytics Overlay
 

package/skills/roles/data-analyst.telemetry.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/data-analyst.telemetry.md — Anti-pattern guidance for the Data-analyst.telemetry (telemetry) role.
+skills/roles/data-analyst.telemetry.md. Anti-pattern guidance for the Data-analyst.telemetry (telemetry) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the data-analyst.telemetry (telemetry) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-data-analyst, cx-sre.
 role: data-analyst.telemetry
 applies_to: [cx-data-analyst, cx-sre]
 inherits: data-analyst
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Telemetry Analyst Overlay
 

package/skills/roles/data-engineer.pipeline.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/data-engineer.pipeline.md — Anti-pattern guidance for the Data-engineer.pipeline (pipeline) role.
+skills/roles/data-engineer.pipeline.md. Anti-pattern guidance for the Data-engineer.pipeline (pipeline) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the data-engineer.pipeline (pipeline) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-data-engineer.
 role: data-engineer.pipeline
 applies_to: [cx-data-engineer]
 inherits: engineer.data
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Data Pipeline Engineer Overlay
 

package/skills/roles/data-engineer.vector-retrieval.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/data-engineer.vector-retrieval.md — Anti-pattern guidance for the Data-engineer.vector-retrieval (vector retrieval) role.
+skills/roles/data-engineer.vector-retrieval.md. Anti-pattern guidance for the Data-engineer.vector-retrieval (vector retrieval) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the data-engineer.vector-retrieval (vector retrieval) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-data-engineer, cx-ai-engineer.
 role: data-engineer.vector-retrieval
 applies_to: [cx-data-engineer, cx-ai-engineer]
 inherits: engineer.data
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Vector Retrieval Engineer Overlay
 

package/skills/roles/data-engineer.warehouse.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/data-engineer.warehouse.md — Anti-pattern guidance for the Data-engineer.warehouse (warehouse) role.
+skills/roles/data-engineer.warehouse.md. Anti-pattern guidance for the Data-engineer.warehouse (warehouse) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the data-engineer.warehouse (warehouse) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-data-engineer.
 role: data-engineer.warehouse
 applies_to: [cx-data-engineer]
 inherits: engineer.data
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Warehouse Engineer Overlay
 

package/skills/roles/debugger.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/debugger.md — Anti-pattern guidance for the Debugger role.
+skills/roles/debugger.md. Anti-pattern guidance for the Debugger role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the debugger domain and counter-moves to avoid them.
@@ -9,11 +9,13 @@ Applies to: cx-debugger.
 role: debugger
 applies_to: [cx-debugger]
 inherits: null
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
-# Debugger — Role guidance
+# Debugger. Role guidance
 
-Load this before drafting. These are the failure modes that separate strong role output from weak role output — check your draft against each.
+Load this before drafting. These are the failure modes that separate strong role output from weak role output. check your draft against each.
 
 
 ### 1. Fixing the symptom
@@ -63,6 +65,6 @@ Load this before drafting. These are the failure modes that separate strong role
 - [ ] Failure reproduced locally and reproduction preserved as a test
 - [ ] No speculative logs, retries, or sleeps in the fix
 - [ ] Earliest anomaly in the log is the starting point
-- [ ] Diff is narrow — fix only, no drive-bys
+- [ ] Diff is narrow. fix only, no drive-bys
 - [ ] Intermittent failures investigated, not shelved
 - [ ] Regression test added alongside the fix

package/skills/roles/designer.accessibility.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/designer.accessibility.md — Anti-pattern guidance for the Designer.accessibility (accessibility) role.
+skills/roles/designer.accessibility.md. Anti-pattern guidance for the Designer.accessibility (accessibility) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the designer.accessibility (accessibility) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-accessibility.
 role: designer.accessibility
 applies_to: [cx-accessibility]
 inherits: designer
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Accessibility Overlay
 

package/skills/roles/designer.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/designer.md — Anti-pattern guidance for the Designer role.
+skills/roles/designer.md. Anti-pattern guidance for the Designer role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the designer domain and counter-moves to avoid them.
@@ -9,15 +9,17 @@ Applies to: cx-designer, cx-accessibility.
 role: designer
 applies_to: [cx-designer, cx-accessibility]
 inherits: null
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
-# Designer — Role guidance
+# Designer. Role guidance
 
-Load this before drafting. These are the failure modes that separate strong role output from weak role output — check your draft against each.
+Load this before drafting. These are the failure modes that separate strong role output from weak role output. check your draft against each.
 
 
 ### 1. Template defaults
-**Symptom**: the design looks like an unmodified Tailwind, shadcn, or Material page — centered hero, gradient blob, uniform card grid, one accent color.
+**Symptom**: the design looks like an unmodified Tailwind, shadcn, or Material page. centered hero, gradient blob, uniform card grid, one accent color.
 **Why it fails**: nothing about the output communicates product intent. It could be any app.
 **Counter-move**: pick an explicit visual direction before designing. Commit to typography, color, and layout choices specific to the product.
 
@@ -39,12 +41,12 @@ Load this before drafting. These are the failure modes that separate strong role
 ### 5. Uniform emphasis
 **Symptom**: every card, section, and action is rendered at the same visual weight.
 **Why it fails**: the user cannot tell what matters. Attention fails; scanning fails.
-**Counter-move**: use hierarchy — scale, weight, color, spacing — to express importance. One primary action per view.
+**Counter-move**: use hierarchy. scale, weight, color, spacing. to express importance. One primary action per view.
 
 ### 6. Motion for motion's sake
 **Symptom**: decorative transitions, parallax, and animated backgrounds that do not clarify flow or state.
 **Why it fails**: slows the interaction, distracts from content, fails reduced-motion preferences.
-**Counter-move**: motion should clarify — state change, origin-destination, or loading progress. Respect `prefers-reduced-motion`.
+**Counter-move**: motion should clarify. state change, origin-destination, or loading progress. Respect `prefers-reduced-motion`.
 
 ### 7. Desktop-first, responsive later
 **Symptom**: the design is mocked at 1440, then "responsive breakpoints" are annotated as an afterthought.
@@ -54,7 +56,7 @@ Load this before drafting. These are the failure modes that separate strong role
 ### 8. Invisible system
 **Symptom**: every screen reinvents spacing, radius, shadow, and color values.
 **Why it fails**: the product feels inconsistent even when individual screens are fine. Engineering cannot implement cleanly.
-**Counter-move**: name the tokens — space, color, type, radius, motion — before designing. Use them.
+**Counter-move**: name the tokens. space, color, type, radius, motion. before designing. Use them.
 
 ## Self-check before shipping
 

package/skills/roles/engineer.ai.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/engineer.ai.md — Anti-pattern guidance for the Engineer.ai (ai) role.
+skills/roles/engineer.ai.md. Anti-pattern guidance for the Engineer.ai (ai) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the engineer.ai (ai) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-ai-engineer.
 role: engineer.ai
 applies_to: [cx-ai-engineer]
 inherits: engineer
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # AI Engineer Overlay
 

package/skills/roles/engineer.data.md

@@ -1,5 +1,5 @@
 <!--
-skills/roles/engineer.data.md — Anti-pattern guidance for the Engineer.data (data) role.
+skills/roles/engineer.data.md. Anti-pattern guidance for the Engineer.data (data) role.
 
 Loaded at sync time to inline role-specific failure modes into specialist agent prompts.
 Covers common failure modes for the engineer.data (data) domain and counter-moves to avoid them.
@@ -9,7 +9,9 @@ Applies to: cx-data-engineer.
 role: engineer.data
 applies_to: [cx-data-engineer]
 inherits: engineer
-version: 1
+version: 2
+profiles: [rnd]
+cap: 1
 ---
 # Data Engineer Overlay
 
@@ -24,7 +26,7 @@ Additional failure modes on top of the engineer core.
 ### 2. No idempotency
 **Symptom**: re-running a job produces duplicates, double-counts, or partial-write corruption.
 **Why it fails**: every retry or backfill becomes a data cleanup event. Oncall pages multiply.
-**Counter-move**: design writes to be idempotent — upsert on natural key, or tag by run-id and replace.
+**Counter-move**: design writes to be idempotent. upsert on natural key, or tag by run-id and replace.
 
 ### 3. Silent data loss
 **Symptom**: ETL rows that fail validation get logged and dropped.