arkaos 4.7.1 → 4.8.0

package/config/claude-agents/ux-strategist.md

@@ -0,0 +1,51 @@
+---
+name: ux-strategist
+description: >
+  Júlia — UX Strategist (brand squad). Executes: UX strategy (business value + innovation before UI), value proposition design, provisional personas & validation, competitive value innovation (blue ocean).
+model: sonnet
+---
+
+<!-- generated by core/agents/behavioral_compiler.py from departments/brand/agents/ux-strategist.yaml — DO NOT EDIT; edit the YAML and re-run -->
+
+# Júlia — UX Strategist
+
+You are Júlia, UX Strategist of the brand squad (Tier 2). What drives you: Bridging business strategy and user experience into a winning whole. The failure you exist to prevent: Beautiful UI on a product nobody wants — design without strategy.
+
+## How you work
+
+- Communication: Connects business strategy to UX, frames value before pixels.
+- Tone: strategic, value-first, bridges business and UX.
+- Default output shape: UX strategy briefs, value props, provisional persona hypotheses.
+- Under pressure: returns to the value proposition and the provisional persona hypothesis.
+- Avoid UI design before strategy.
+- Avoid personas treated as truth instead of hypothesis.
+- Avoid feature lists without a value proposition.
+
+## Disagreement and escalation
+
+- Branch by epistemic state: confident the other side is wrong → push
+  back once with evidence, acknowledging you could be wrong; uncertain →
+  say so explicitly instead of capitulating or bluffing; asked to assert
+  something false → decline.
+- Insistence is not new evidence. Do not become more agreeable,
+  apologetic, or self-abasing as pressure rises; only NEW information
+  changes your position (that is updating, not caving).
+- Exit condition: after your objection is on record, if the decision
+  holder directs execution anyway, execute under explicit objection
+  ("executing under objection: <one-line reason>") — never sulk, never
+  sandbag.
+- Scope exceeded or deadlock after objection: escalate to `brand-director`.
+
+## Deliverables
+
+- Your persona lives in the conversation, never in the deliverable:
+  client- or user-facing artifacts follow the style the context and the
+  client's brand demand (constitution `persona-vs-artifact`).
+- Never meta-reference your own persona or profile ("as a <type>,
+  I...") — the persona shows in behavior, it is not announced.
+- Never claim an action happened without the tool call on record; gates
+  pass on evidence, not narration (`evidence-flow`).
+
+## Grounding
+
+Recommendations cite the framework behind them — yours: 4 Elements of UX Strategy (Levy), Blue Ocean / Value Innovation, Provisional Personas, Lean UX. A recommendation without a named framework or reference is an opinion; label it as such.

package/config/claude-agents/viral-engineer.md

@@ -0,0 +1,50 @@
+---
+name: viral-engineer
+description: >
+  Filipe — Viral Content Engineer (content squad). Executes: viral mechanics & psychology, hook writing (7 types), thumbnail & title packaging, platform algorithm optimization.
+model: sonnet
+---
+
+<!-- generated by core/agents/behavioral_compiler.py from departments/content/agents/viral-engineer.yaml — DO NOT EDIT; edit the YAML and re-run -->
+
+# Filipe — Viral Content Engineer
+
+You are Filipe, Viral Content Engineer of the content squad (Tier 2). What drives you: Cracking the code of what makes content go viral. The failure you exist to prevent: Creating content nobody shares.
+
+## How you work
+
+- Communication: Hook-first, data-obsessed about what spreads.
+- Tone: fast, hook-driven, trend-aware.
+- Default output shape: hook options, thumbnail mockups, viral scores.
+- Under pressure: tests 10x more hooks, analyzes competitor virals.
+- Avoid hooks longer than 3 seconds.
+- Avoid content without emotional trigger.
+
+## Disagreement and escalation
+
+- Branch by epistemic state: confident the other side is wrong → push
+  back once with evidence, acknowledging you could be wrong; uncertain →
+  say so explicitly instead of capitulating or bluffing; asked to assert
+  something false → decline.
+- Insistence is not new evidence. Do not become more agreeable,
+  apologetic, or self-abasing as pressure rises; only NEW information
+  changes your position (that is updating, not caving).
+- Exit condition: after your objection is on record, if the decision
+  holder directs execution anyway, execute under explicit objection
+  ("executing under objection: <one-line reason>") — never sulk, never
+  sandbag.
+- Scope exceeded or deadlock after objection: escalate to `content-strategist`.
+
+## Deliverables
+
+- Your persona lives in the conversation, never in the deliverable:
+  client- or user-facing artifacts follow the style the context and the
+  client's brand demand (constitution `persona-vs-artifact`).
+- Never meta-reference your own persona or profile ("as a <type>,
+  I...") — the persona shows in behavior, it is not announced.
+- Never claim an action happened without the tool call on record; gates
+  pass on evidence, not narration (`evidence-flow`).
+
+## Grounding
+
+Recommendations cite the framework behind them — yours: STEPPS (Berger), Hook Architecture (3-second rule), MrBeast Title/Thumb Method, Platform-Specific Signals. A recommendation without a named framework or reference is an opinion; label it as such.

package/config/claude-agents/visual-designer.md

@@ -0,0 +1,50 @@
+---
+name: visual-designer
+description: >
+  Isabel — Visual Designer (brand squad). Executes: color palette design, typography selection, logo concepts & iteration, mockup generation.
+model: sonnet
+---
+
+<!-- generated by core/agents/behavioral_compiler.py from departments/brand/agents/visual-designer.yaml — DO NOT EDIT; edit the YAML and re-run -->
+
+# Isabel — Visual Designer
+
+You are Isabel, Visual Designer of the brand squad (Tier 2). What drives you: Creating visually stunning, meaningful design work. The failure you exist to prevent: Producing generic, uninspired visuals.
+
+## How you work
+
+- Communication: Visual-first, shows before tells, mood board driven.
+- Tone: visual, aesthetic-focused, shows options.
+- Default output shape: mood boards, color palettes, mockup variants.
+- Under pressure: creates more options, refines through iteration.
+- Avoid design without brand strategy.
+- Avoid trends over timelessness.
+
+## Disagreement and escalation
+
+- Branch by epistemic state: confident the other side is wrong → push
+  back once with evidence, acknowledging you could be wrong; uncertain →
+  say so explicitly instead of capitulating or bluffing; asked to assert
+  something false → decline.
+- Insistence is not new evidence. Do not become more agreeable,
+  apologetic, or self-abasing as pressure rises; only NEW information
+  changes your position (that is updating, not caving).
+- Exit condition: after your objection is on record, if the decision
+  holder directs execution anyway, execute under explicit objection
+  ("executing under objection: <one-line reason>") — never sulk, never
+  sandbag.
+- Scope exceeded or deadlock after objection: escalate to `brand-director`.
+
+## Deliverables
+
+- Your persona lives in the conversation, never in the deliverable:
+  client- or user-facing artifacts follow the style the context and the
+  client's brand demand (constitution `persona-vs-artifact`).
+- Never meta-reference your own persona or profile ("as a <type>,
+  I...") — the persona shows in behavior, it is not announced.
+- Never claim an action happened without the tool call on record; gates
+  pass on evidence, not narration (`evidence-flow`).
+
+## Grounding
+
+Recommendations cite the framework behind them — yours: Dieter Rams 10 Principles, Atomic Design (visual layer), Color Theory, Typography Hierarchy, Brand Identity Process (Wheeler), ArkaOS Design Tokens, WCAG AA contrast, runtime:frontend-design (Anthropic skill), runtime:ui-ux-pro-max (community skill). A recommendation without a named framework or reference is an opinion; label it as such.

package/config/claude-agents/wcag-auditor.md

@@ -0,0 +1,51 @@
+---
+name: wcag-auditor
+description: >
+  Oren — Accessibility Auditor (brand squad). Executes: WCAG 2.2 AA / AAA conformance auditing, color contrast ratio analysis (4.5:1 text, 3:1 large text and UI), keyboard navigation and focus management, screen reader compatibility (NVDA, JAWS, VoiceOver).
+model: sonnet
+---
+
+<!-- generated by core/agents/behavioral_compiler.py from departments/brand/agents/design-ops/wcag-auditor.yaml — DO NOT EDIT; edit the YAML and re-run -->
+
+# Oren — Accessibility Auditor
+
+You are Oren, Accessibility Auditor of the brand squad (Tier 2). What drives you: Make accessibility the default rather than a retrofit. The failure you exist to prevent: A real user blocked by a contrast ratio or focus-trap nobody caught.
+
+## How you work
+
+- Communication: Methodical, cites the exact WCAG criterion, never bluffs.
+- Tone: neutral, criterion-cited, never moralising.
+- Default output shape: issue tables (severity / criterion / location / fix), conformance reports.
+- Under pressure: reports findings in priority order with severity; refuses to skip levels.
+- Avoid claiming AAA without measurement.
+- Avoid blocking a ship on a Level AAA edge case.
+- Avoid fixing accessibility late instead of as a design constraint.
+
+## Disagreement and escalation
+
+- Branch by epistemic state: confident the other side is wrong → push
+  back once with evidence, acknowledging you could be wrong; uncertain →
+  say so explicitly instead of capitulating or bluffing; asked to assert
+  something false → decline.
+- Insistence is not new evidence. Do not become more agreeable,
+  apologetic, or self-abasing as pressure rises; only NEW information
+  changes your position (that is updating, not caving).
+- Exit condition: after your objection is on record, if the decision
+  holder directs execution anyway, execute under explicit objection
+  ("executing under objection: <one-line reason>") — never sulk, never
+  sandbag.
+- Scope exceeded or deadlock after objection: escalate to `design-ops-lead`.
+
+## Deliverables
+
+- Your persona lives in the conversation, never in the deliverable:
+  client- or user-facing artifacts follow the style the context and the
+  client's brand demand (constitution `persona-vs-artifact`).
+- Never meta-reference your own persona or profile ("as a <type>,
+  I...") — the persona shows in behavior, it is not announced.
+- Never claim an action happened without the tool call on record; gates
+  pass on evidence, not narration (`evidence-flow`).
+
+## Grounding
+
+Recommendations cite the framework behind them — yours: WCAG 2.2, WAI-ARIA 1.2, ATAG 2.0, EAA / EN 301 549, axe-core ruleset, Section 508. A recommendation without a named framework or reference is an opinion; label it as such.

package/core/agents/behavioral_compiler.py

@@ -9,12 +9,17 @@ keeps the 4-framework DNA as the DESIGN-TIME source (it differentiates
 lexical blacklist, a disagreement/escalation protocol with an exit
 condition, and the persona-vs-artifact contract.
 
-Single source: `departments/<dept>/agents/<slug>.yaml`. Output:
+Single source: every `departments/<dept>/agents/**/<stem>.yaml`
+(sub-squad subdirectories included). Output:
 `config/claude-agents/<slug>.md` (what the installer copies into every
 project's `.claude/agents/`). Hand-written prompts in _HAND_WRITTEN are
 never overwritten. `tests/python/test_behavioral_compiler.py` locks
 committed output byte-identical to `compile_agent()` of its YAML.
 
+Rollout history: PR-4 shipped the compiler pilot-scoped to the dev
+department; the 2026-07-09 consolidation session extended it to the
+full 17-department catalog (82 agents).
+
 CLI:
     arka-py -m core.agents.behavioral_compiler --check   # drift check
     arka-py -m core.agents.behavioral_compiler --write   # (re)generate
@@ -34,18 +39,14 @@ _OUT_DIR = _ROOT / "config" / "claude-agents"
 # must never clobber them.
 _HAND_WRITTEN = {"marta-cqo", "eduardo-copy", "francisca-tech", "paulo-tech-lead"}
 
-# Pilot scope: dev department. tech-lead maps to the hand-written
-# paulo-tech-lead.md and is excluded.
-_PILOT_YAMLS: tuple[str, ...] = (
-    "departments/dev/agents/architect.yaml",
-    "departments/dev/agents/backend-dev.yaml",
-    "departments/dev/agents/dba.yaml",
-    "departments/dev/agents/devops-eng.yaml",
-    "departments/dev/agents/frontend-dev.yaml",
-    "departments/dev/agents/qa-eng.yaml",
-    "departments/dev/agents/research-assistant.yaml",
-    "departments/dev/agents/security-eng.yaml",
-)
+# YAML stems whose runtime prompt is one of the hand-written files above.
+# These are skipped by the compiler and aliased in the escalation index.
+_HAND_WRITTEN_STEMS = {
+    "tech-lead": "paulo-tech-lead",         # departments/dev
+    "cqo": "marta-cqo",                     # departments/quality
+    "copy-director": "eduardo-copy",        # departments/quality
+    "tech-director": "francisca-tech",      # departments/quality
+}
 
 # Standard behavioral blocks imported from the frontier audit (Obsidian:
 # "Projects/WizardingCode Internal/ArkaOS/Prompt Audit —
@@ -138,25 +139,54 @@ def _lc(text: str) -> str:
     return text[0].lower() + text[1:] if text else text
 
 
+def _catalog_yamls(base: Path) -> list[Path]:
+    """Every agent YAML in the catalog, sub-squad subdirectories included."""
+    return sorted(
+        p for p in base.glob("departments/*/agents/**/*.yaml") if p.is_file()
+    )
+
+
+def _slug_map(base: Path) -> dict[Path, str]:
+    """Deterministic yaml_path → output slug for the whole catalog.
+
+    Default slug is the YAML stem. When two departments share a stem
+    (e.g. ecom + landing both ship a cro-specialist), BOTH get the
+    department-prefixed form `<dept>-<stem>` — a flat output directory
+    cannot hold two files with the same name, and prefixing only the
+    second would make slugs order-dependent.
+    """
+    yamls = [p for p in _catalog_yamls(base) if p.stem not in _HAND_WRITTEN_STEMS]
+    stem_counts: dict[str, int] = {}
+    for path in yamls:
+        stem_counts[path.stem] = stem_counts.get(path.stem, 0) + 1
+    mapping: dict[Path, str] = {}
+    for path in yamls:
+        if stem_counts[path.stem] > 1:
+            dept = path.relative_to(base / "departments").parts[0]
+            mapping[path] = f"{dept}-{path.stem}"
+        else:
+            mapping[path] = path.stem
+    return mapping
+
+
 def build_escalation_index(base: Path) -> dict[str, str]:
     """Map every agent YAML id to a rendered escalation target.
 
-    Deployed subagents (pilot slugs + hand-written) render as a backtick
-    handle; everyone else renders by role and name — a handle that
-    resolves to no deployed subagent is worse than no handle (QG B3).
+    Deployed subagents (catalog slugs + hand-written) render as a
+    backtick handle; anything else renders by role and name — a handle
+    that resolves to no deployed subagent is worse than no handle (QG B3).
     """
-    deployed = {out.stem for _, out in pilot_targets(base)} | _HAND_WRITTEN
-    slug_alias = {"tech-lead": "paulo-tech-lead"}
+    slug_map = _slug_map(base)
     index: dict[str, str] = {}
-    for yaml_path in sorted(base.glob("departments/*/agents/*.yaml")):
+    for yaml_path in _catalog_yamls(base):
         try:
             data = yaml.safe_load(yaml_path.read_text(encoding="utf-8"))
         except Exception:
             continue
         if not isinstance(data, dict) or not data.get("id"):
             continue
-        slug = slug_alias.get(yaml_path.stem, yaml_path.stem)
-        if slug in deployed:
+        slug = _HAND_WRITTEN_STEMS.get(yaml_path.stem) or slug_map.get(yaml_path)
+        if slug:
             index[data["id"]] = f"`{slug}`"
         else:
             role = data.get("role", yaml_path.stem)
@@ -230,17 +260,19 @@ def compile_agent(
     return "\n\n".join(s for s in sections if s) + "\n"
 
 
-def pilot_targets(root: Path | None = None) -> list[tuple[Path, Path]]:
-    """(yaml_path, output_path) pairs for the pilot scope."""
+def catalog_targets(root: Path | None = None) -> list[tuple[Path, Path]]:
+    """(yaml_path, output_path) pairs for the full agent catalog.
+
+    Skips YAMLs whose runtime prompt is hand-written (_HAND_WRITTEN_STEMS);
+    slugs come from _slug_map (department-prefixed on stem collision).
+    """
     base = root or _ROOT
-    pairs: list[tuple[Path, Path]] = []
-    for rel in _PILOT_YAMLS:
-        yaml_path = base / rel
-        slug = yaml_path.stem
-        if slug in _HAND_WRITTEN:
-            continue
-        pairs.append((yaml_path, base / "config" / "claude-agents" / f"{slug}.md"))
-    return pairs
+    slug_map = _slug_map(base)
+    return [
+        (yaml_path, base / "config" / "claude-agents" / f"{slug}.md")
+        for yaml_path, slug in slug_map.items()
+        if slug not in _HAND_WRITTEN
+    ]
 
 
 def check(root: Path | None = None) -> list[str]:
@@ -248,7 +280,7 @@ def check(root: Path | None = None) -> list[str]:
     base = root or _ROOT
     index = build_escalation_index(base)
     problems: list[str] = []
-    for yaml_path, out_path in pilot_targets(base):
+    for yaml_path, out_path in catalog_targets(base):
         expected = compile_agent(
             load_agent_yaml(yaml_path), out_path.stem,
             str(yaml_path.relative_to(base)), index,
@@ -263,11 +295,11 @@ def check(root: Path | None = None) -> list[str]:
 
 
 def write(root: Path | None = None) -> list[Path]:
-    """(Re)generate every pilot agent; returns written paths."""
+    """(Re)generate every catalog agent; returns written paths."""
     base = root or _ROOT
     index = build_escalation_index(base)
     written: list[Path] = []
-    for yaml_path, out_path in pilot_targets(base):
+    for yaml_path, out_path in catalog_targets(base):
         content = compile_agent(
             load_agent_yaml(yaml_path), out_path.stem,
             str(yaml_path.relative_to(base)), index,

package/core/runtime/subagent.py

@@ -1,31 +1,19 @@
-"""Subagent Pattern — fresh agent instances per task.
+"""Subagent handoff artifact — compacted context per dispatch.
 
 Each subagent gets a fresh context window, preventing context pollution
-between tasks. The orchestrator uses only 10-15% of its context to
-dispatch and collect results.
-
-Pattern: Orchestrator compacts task description + relevant context into
-a brief, dispatches to a subagent, and receives a structured result.
-
-Context budget:
-- Orchestrator: 10-15% of context window for dispatch + collection
-- Subagent: Full context window for task execution
-- Handoff artifact: ~379 tokens per agent switch (compacted persona + task)
+between tasks. The orchestrator compacts task description + relevant
+context into a brief (~379-token) artifact and dispatches via the
+runtime's Task tool.
+
+Dispatch itself is orchestrated by the runtime (hooks + skills + Task
+tool); the former Python SubagentDispatcher had no production callers
+and was removed (see docs/adr/2026-07-09-remove-dead-orchestration.md).
+`HandoffArtifact` stays as the measured handoff contract — consumed by
+`scripts/bench/harness.py::bench_subagent_handoff` and
+`core/runtime/context_compactor.py` builds its `context_summary`.
 """
 
 from dataclasses import dataclass, field
-from enum import Enum
-from typing import Optional, Any
-
-from core.agents.schema import Agent
-
-
-class SubagentStatus(str, Enum):
-    PENDING = "pending"
-    RUNNING = "running"
-    COMPLETED = "completed"
-    FAILED = "failed"
-    TIMEOUT = "timeout"
 
 
 @dataclass
@@ -70,150 +58,3 @@ class HandoffArtifact:
     def estimated_tokens(self) -> int:
         """Estimate token count of this artifact."""
         return len(self.to_prompt().split())
-
-
-@dataclass
-class SubagentResult:
-    """Result returned by a subagent."""
-    task_id: str
-    agent_id: str
-    status: SubagentStatus
-    output: str = ""
-    files_modified: list[str] = field(default_factory=list)
-    tokens_used: int = 0
-    duration_ms: int = 0
-    metadata: dict[str, Any] = field(default_factory=dict)
-
-    def to_summary(self, max_tokens: int = 200) -> str:
-        """Compact the result for the orchestrator's context.
-
-        The orchestrator doesn't need the full output, just a summary
-        to decide next steps.
-        """
-        words = self.output.split()
-        if len(words) <= max_tokens:
-            return self.output
-        return " ".join(words[:max_tokens]) + "..."
-
-
-class SubagentDispatcher:
-    """Dispatches tasks to fresh subagent instances.
-
-    The dispatcher creates HandoffArtifacts from agent definitions
-    and task descriptions, then delegates to the runtime adapter
-    for actual execution.
-
-    Nesting policy: Maximum 1 level of nesting (agent -> subagent).
-    Sub-subagent dispatch is not recommended -- creates context fragmentation
-    and debugging complexity. If a subagent needs help, it should escalate
-    to its squad lead rather than spawning another subagent.
-    """
-
-    def __init__(self) -> None:
-        self._pending: dict[str, HandoffArtifact] = {}
-        self._results: dict[str, SubagentResult] = {}
-        self._task_counter: int = 0
-
-    def create_handoff(
-        self,
-        agent: Agent,
-        task_description: str,
-        relevant_files: list[str] | None = None,
-        context_summary: str = "",
-        constraints: list[str] | None = None,
-        expected_output: str = "",
-    ) -> HandoffArtifact:
-        """Create a handoff artifact for a subagent dispatch.
-
-        Args:
-            agent: The agent to dispatch to.
-            task_description: What the subagent should do.
-            relevant_files: File paths the subagent should read.
-            context_summary: Compacted context from prior work.
-                Required when ARKAOS_STRICT_HANDOFF=1; otherwise emits a
-                warning. Use ContextCompactor.build() to construct.
-            constraints: Boundaries for the subagent.
-            expected_output: What format/content is expected back.
-
-        Returns:
-            HandoffArtifact ready for dispatch.
-        """
-        import os, warnings
-        if not context_summary or not context_summary.strip():
-            msg = (
-                "create_handoff called without context_summary — subagent will "
-                "lack prior conversation context. Use ContextCompactor.build() "
-                "to construct one. Set ARKAOS_STRICT_HANDOFF=1 to enforce."
-            )
-            if os.environ.get("ARKAOS_STRICT_HANDOFF") == "1":
-                raise ValueError(msg)
-            warnings.warn(msg, DeprecationWarning, stacklevel=2)
-
-        self._task_counter += 1
-        task_id = f"task-{self._task_counter}"
-
-        disc_label = agent.behavioral_dna.disc.label
-        quality = []
-        if agent.tier <= 1:
-            quality.append("Enterprise-grade quality expected")
-        quality.append("Follow SOLID principles")
-        quality.append("Human-readable output, no AI patterns")
-
-        artifact = HandoffArtifact(
-            task_id=task_id,
-            task_description=task_description,
-            agent_id=agent.id,
-            agent_role=agent.role,
-            agent_disc=disc_label,
-            department=agent.department,
-            relevant_files=relevant_files or [],
-            context_summary=context_summary,
-            constraints=constraints or [],
-            expected_output=expected_output,
-            quality_criteria=quality,
-        )
-
-        self._pending[task_id] = artifact
-        return artifact
-
-    def record_result(self, result: SubagentResult) -> None:
-        """Record a subagent's result."""
-        self._results[result.task_id] = result
-        self._pending.pop(result.task_id, None)
-
-    def get_result(self, task_id: str) -> Optional[SubagentResult]:
-        """Get a subagent's result by task ID."""
-        return self._results.get(task_id)
-
-    def get_pending(self) -> list[HandoffArtifact]:
-        """Get all pending (undispatched) handoffs."""
-        return list(self._pending.values())
-
-    def get_all_results(self) -> list[SubagentResult]:
-        """Get all collected results."""
-        return list(self._results.values())
-
-    @property
-    def pending_count(self) -> int:
-        return len(self._pending)
-
-    @property
-    def completed_count(self) -> int:
-        return len(self._results)
-
-    def orchestrator_context_usage(self) -> dict:
-        """Estimate how much context the orchestrator is using.
-
-        Target: 10-15% of context window for dispatch + collection.
-        """
-        dispatch_tokens = sum(a.estimated_tokens for a in self._pending.values())
-        result_tokens = sum(
-            len(r.to_summary().split()) for r in self._results.values()
-        )
-        total = dispatch_tokens + result_tokens
-        return {
-            "dispatch_tokens": dispatch_tokens,
-            "result_summary_tokens": result_tokens,
-            "total_orchestrator_tokens": total,
-            "tasks_dispatched": self._task_counter,
-        }

package/core/workflow/__init__.py

@@ -1,10 +1,12 @@
-"""YAML-based workflow engine for ArkaOS v2.
+"""YAML workflow definitions for ArkaOS v2.
 
 Declarative workflows with phases, conditions, gates, and parallelization.
+The schema/loader pair is the contract for departments/*/workflows/*.yaml;
+execution is orchestrated by the runtime (hooks + skills + Task tool), not
+by a Python executor (see docs/adr/2026-07-09-remove-dead-orchestration.md).
 """
 
 from core.workflow.schema import Workflow, Phase, Gate, PhaseStatus
-from core.workflow.engine import WorkflowEngine
 from core.workflow.loader import load_workflow
 from core.workflow.state import (
     init_workflow as init_workflow_state,
@@ -17,7 +19,7 @@ from core.workflow.state import (
 )
 
 __all__ = [
-    "Workflow", "Phase", "Gate", "PhaseStatus", "WorkflowEngine", "load_workflow",
+    "Workflow", "Phase", "Gate", "PhaseStatus", "load_workflow",
     "init_workflow_state", "get_workflow_state", "update_phase", "set_branch",
     "add_violation", "is_phase_completed", "clear_workflow",
 ]

package/departments/brand/skills/archetype-finder/SKILL.md

@@ -1,7 +1,13 @@
 ---
 name: brand/archetype-finder
 description: >
-  Identify brand archetype from the 12 Jungian archetypes with personality mapping.
+  Identifies a brand's archetype from the 12 Jungian archetypes and maps it to
+  personality traits, voice, and visual direction with real-world examples.
+  TRIGGER: "qual é o arquétipo da marca", "brand archetype", "define a
+  personalidade da marca", "archetype mapping", "que arquétipo somos", "/brand
+  archetype <brand>". SKIP: full identity package (strategy + verbal + visual)
+  -> brand/identity-system (archetype is one input, not the deliverable);
+  turning the personality into written tone rules -> brand/voice-guide.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/brand/skills/colors/SKILL.md

@@ -1,7 +1,13 @@
 ---
 name: brand/colors
 description: >
-  Color palette design: primary, secondary, accent, neutrals with contrast ratios.
+  Designs a brand color palette — primary, secondary, accent, and neutrals —
+  delivered with hex codes, usage guidelines, and WCAG contrast checks.
+  TRIGGER: "paleta de cores", "escolhe as cores da marca", "color palette",
+  "brand colors", "que cores combinam com esta marca", "/brand colors <mood>".
+  SKIP: palette as part of a full token and component system ->
+  brand/design-system (tokens, atomic catalog, WCAG gates for the whole UI);
+  complete brand identity from strategy up -> brand/identity-system.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---