agentleFS
hushh-labshushh-labs/hushh-research/.agents/skills/morphy-ax/SKILL.md

morphy-ax

Skill40 starsChanged 4 days agoApache-2.0View on GitHub

Use when changing Morphy AX shared agent-experience state, semantic assessment presentation, performance budgets, or cross-modal compatibility.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Avoid overlap with frontend-design-system, one-voice-governance, and backend-agents-operons.

    line 12
  2. Distinctive:

    Verify the existing runtime, voice FSM, route playbook, and generated action authority before changing AX.

    line 52
  3. Very specific:

    Keep Morphy AX pure, redacted, memoizable, and hosted by AgentRuntimeStateProvider.

    line 53
  4. Very specific:

    Treat trusted_activation_required browser actions as exact Agent Bar continuations over mounted handlers, not redirect or popup-broker …

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Morphy AX

Purpose and Trigger

  • Primary scope: morphy-agent-experience
  • Trigger on Morphy AX snapshots, active interaction layers, presentation derivation, semantic-assessment validation, compatibility projections, or AX performance budgets.
  • Avoid overlap with frontend-design-system, one-voice-governance, and backend-agents-operons.

Coverage and Ownership

  • Role: spoke
  • Owner family: frontend

Owned repo surfaces:

  1. hushh-webapp/lib/morphy-ax
  2. docs/development/quality/morphy-agent-experience.md

Non-owned surfaces:

  1. hushh-webapp/lib/voice
  2. consent-protocol/hushh_mcp/agents
  3. hushh-webapp/lib/morphy-ux

Do Use

  1. Shared, redacted agent-experience snapshot, active-layer composition, and presentation contracts.
  2. Intelligence-assessment validation and compatibility/non-regression budgets.
  3. Cross-modal AX behavior that reuses the existing runtime owner and action gateway.

Do Not Use

  1. Voice action authoring, generated gateway changes, or ADK orchestration ownership.
  2. Visual primitive work owned by Morphy UX.
  3. A second React provider, store, router, action registry, DOM observer, or model-facing route tool.

Read First

  1. docs/development/quality/design.md
  2. docs/development/quality/morphy-agent-experience.md
  3. docs/architecture/one/one-voice-runtime-architecture.md
  4. docs/development/quality/frontend-ui-architecture-map.md
  5. docs/architecture/finance/kai-action-gateway-vnext.md

Workflow

  1. Verify the existing runtime, voice FSM, route playbook, and generated action authority before changing AX.
  2. Keep Morphy AX pure, redacted, memoizable, and hosted by AgentRuntimeStateProvider.
  3. Let intelligence assess meaning; deterministic code may validate, reject, normalize, and enforce authority only.
  4. Compose authored route, chrome, and interaction_layer publishers; expose only the top effective inventory and remove stale owner leases on route change.
  5. Require exact generated dismiss/cancel actions, focus-restored settlement, and declared Agent continuity; never synthesize click or Escape behavior.
  6. Treat trusted_activation_required browser actions as exact Agent Bar continuations over mounted handlers, not redirect or popup-broker fallbacks.
  7. Preserve OneVoiceContextSnapshot through an explicit compatibility projection while migration is active.
  8. Benchmark the same fixtures flag-off and flag-on; block wrong-layer actions, unsafe fallbacks, or budget regressions.
  9. Route voice, backend-agent, design-system, docs, or quality changes to their owning skills.

Handoff Rules

  1. Broad frontend work routes to frontend.
  2. Voice/action contracts route to one-voice-governance.
  3. ADK or product-agent changes route to backend-agents-operons.
  4. Visual primitives route to frontend-design-system; verification policy routes to quality-contracts.

Required Checks

cd hushh-webapp && npm run verify:morphy-ax
cd hushh-webapp && npm run typecheck
cd hushh-webapp && npm run verify:voice-gateway
cd hushh-webapp && npm run verify:design-system
cd consent-protocol && python3 -m pytest tests/test_onboarding_goal_agent.py tests/test_one_adk_agent_tree.py -q
./bin/hushh docs verify

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.