Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

hmg-health

Sterne7

Forks3

Aktualisiert16. Juli 2026 um 13:46

Produce an HMG health scorecard from doctor JSON, disposable memory smoke, agent-event explain, and daemon latency sampling.

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

In Manus ausführen

Quelle

HMG-AI

HMG-AI/HMG-public

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

SoftwareentwicklerInformatik- und Mathematikberufe·SOC 15-1252

SKILL.md

readonly

name	hmg-health
description	Produce an HMG health scorecard from doctor JSON, disposable memory smoke, agent-event explain, and daemon latency sampling.

HMG Health

Use this workflow when HMG readiness is unclear or a benchmark/integration needs an independent health scorecard.

Workflow

Run hmg doctor --format json.
Use a disposable scope for a memorize/recall/handoff smoke.
Run hmg agent-event explain --file event.json --format json.
Run hmg integrations explain --format json and distinguish verified, advisory, and planned integration evidence.
Sample daemon latency with hmg daemon status --format json and a small scoped recall.
Report core memory, scope, hooks, daemon, scheduler, embedding, and optional integration status separately.

Output

Return pass/warn/fail, evidence, blocker status, and the shortest repair command. Do not treat warnings as blockers, and do not downgrade blockers to warnings.

Mehr aus diesem Repository

gleiches Repository

hmg-integrate

HMG-AI/HMG-public

Create a non-invasive HMG integration plan for a target repository using MCP, hooks, runtime, and smoke tests behind a feature flag.

2026-07-167

hmg

HMG-AI/HMG-public

Use HMG durable coding-agent memory when a task benefits from branch-aware recall, prior decisions, correction history, governance, or an end-of-task handoff.

2026-07-167

hmg-test-integration

HMG-AI/HMG-public

Independently verify that an HMG integration can write, recall, handoff, preserve scope isolation, and emit lifecycle events.

2026-07-167

hmg-context-loader

HMG-AI/HMG-public

Manually load scoped HMG context when SessionStart or prompt-time hooks are unavailable.

2026-07-137

hmg-eval-baseline

HMG-AI/HMG-public

Run the local mem0 OSS vs HMG branch-isolation scorecard and interpret latency, hit rate, scope leakage, and agent brief usefulness.

2026-07-137

hmg-import

HMG-AI/HMG-public

Plan safe dry-run imports from mem0, MEMORY.md, Claude memory banks, or project documents into HMG.

2026-07-137

name	hmg-health
description	Produce an HMG health scorecard from doctor JSON, disposable memory smoke, agent-event explain, and daemon latency sampling.

HMG Health

Use this workflow when HMG readiness is unclear or a benchmark/integration needs an independent health scorecard.

Workflow

Run hmg doctor --format json.
Use a disposable scope for a memorize/recall/handoff smoke.
Run hmg agent-event explain --file event.json --format json.
Run hmg integrations explain --format json and distinguish verified, advisory, and planned integration evidence.
Sample daemon latency with hmg daemon status --format json and a small scoped recall.
Report core memory, scope, hooks, daemon, scheduler, embedding, and optional integration status separately.

Output

Return pass/warn/fail, evidence, blocker status, and the shortest repair command. Do not treat warnings as blockers, and do not downgrade blockers to warnings.