local-analysis-offload

Sterne1

Forks0

Aktualisiert25. Juli 2026 um 18:19

Plan privacy-first local AI/model offload for expensive elder-care casework analysis. Use for Qwen/GLM/Gemma-class local models, LM Studio/lms, LM Studio OpenAI-compatible API, Goose CLI, Ollama, llama.cpp, vLLM, local VLM/image analysis, OCR, ffmpeg, Whisper, Parakeet, diarization, transcript enrichment, and batch prompt planning. Defaults to plan-only until the user approves running jobs.

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.

Quelle

mbeacom

mbeacom/elder-care-casework

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

SoftwareentwicklerInformatik- und Mathematikberufe·SOC 15-1252

SKILL.md

readonly

name	local-analysis-offload
description	Plan privacy-first local AI/model offload for expensive elder-care casework analysis. Use for Qwen/GLM/Gemma-class local models, LM Studio/lms, LM Studio OpenAI-compatible API, Goose CLI, Ollama, llama.cpp, vLLM, local VLM/image analysis, OCR, ffmpeg, Whisper, Parakeet, diarization, transcript enrichment, and batch prompt planning. Defaults to plan-only until the user approves running jobs.
argument-hint	Workload, input paths, output root, candidate tools/models, plan-only or run, validation standard

Local Analysis Offload

This VS Code / Copilot skill wrapper points to the canonical Cowork / Claude Desktop plugin workflow.

Load these files

../../../elder-care-casework/skills/local-analysis-offload/SKILL.md
../../../elder-care-casework/skills/audio-transcript-review/LOCAL_AUDIO_OFFLOAD.md for audio/transcript work.
Any workload-specific canonical skill, such as ../../../elder-care-casework/skills/snf-records-review/SKILL.md or ../../../elder-care-casework/skills/audio-transcript-review/SKILL.md.

Use this wrapper when

The user wants to use local models or deterministic local tools before consuming main-agent context.
The task is expensive, repetitive, or privacy-sensitive: OCR/image labeling, transcript cleanup, speaker attribution, table extraction, first-pass tagging, or packet review triage.
The user mentions Qwen, GLM, Gemma, LM Studio, lms, LM Studio OpenAI-compatible API, Goose, Ollama, llama.cpp, vLLM, ffmpeg, Whisper, Parakeet, diarization, VLM, local image analysis, or GPU offload.

Default to plan-only. Do not run local tools or models until the user explicitly approves the run.

Mehr aus diesem Repository

gleiches Repository

admin-interaction-log

mbeacom/elder-care-casework

Append a dated, factual entry to an ongoing SNF/facility Admin Interaction Log in terse, cited, third-person prose that states facts without characterizing anyone's motive and without emotional language, so the log can later be attached to a complaint, appeal, or ombudsman filing. Creates the log file if one does not exist yet. Use when the user says "log an interaction", "add an entry to the admin log", "document this call with the facility", "note this for the log", or mentions a phone call / voicemail / visit / email exchange with facility staff that needs to be preserved for the case record.

2026-07-251

audio-transcript-review

mbeacom/elder-care-casework

Review and enrich elder-care audio transcripts from plan-of-care meetings, IDT calls, facility phone calls, voicemail, payer calls, JFS/ODM calls, or staff conversations. Supports local Whisper/Parakeet transcription outputs, speaker labeling/diarization reconciliation, timestamped statement attribution, casework evidence tagging, transcript-quality triage, and routing into admin logs, appeals, complaints, Medicaid disputes, legal-referral packets, and case-context ledgers.

2026-07-251

case-context-ledger

mbeacom/elder-care-casework

Create or update a durable elder-care case context ledger for long-running Medicare, Medicaid, SNF, facility, payer, and regulatory matters. Use when the user says "case memory", "case context", "update the case file", "track deadlines", "remember this for the appeal", "build a case ledger", or needs canonical facts, contacts, deadlines, document inventory, evidence register, open questions, and decision log across multiple skills and large record productions.

2026-07-251

case-project-upgrade

mbeacom/elder-care-casework

Safely upgrade or migrate an existing elder-care case workspace created with an older plugin layout into the current privacy-first structure without losing source material. Use when the user says "upgrade my case project", "migrate old case folder", "move this case to the new layout", "prepare my existing case folder for this plugin", "don't lose existing findings", or needs a dry-run migration plan, checksums, backup manifest, case-context creation, and no-delete/no-overwrite transfer workflow before publishing or updating the plugin.

2026-07-251

hipaa-records-request

mbeacom/elder-care-casework

Draft a HIPAA records request, itemized billing request, or follow-up / second-request email to a Skilled Nursing Facility or its corporate entity. Style is direct, specific, and deadline-driven rather than hostile — it confirms the requester's legal authority, enumerates exactly what is requested, cites the HIPAA 30-day access right (45 CFR 164.524) and 42 CFR 483.21(c) where discharge planning is at issue, sets a firm response date, and names the regulatory escalation path without threatening litigation. The escalation agencies it names are Ohio's; users in other states must substitute their own state survey agency, insurance regulator, and attorney general before sending. Use when the user says "draft a records request", "follow up on the records request", "second-request email to [facility]", "send a HIPAA letter", needs to escalate unanswered records requests, or wants a narrow supplement based on snf-document-map / snf-review missing-document findings.

2026-07-251

legal-referral-intake-packet

mbeacom/elder-care-casework

Assemble a ready-to-send intake packet for an elder-law attorney, a legal-plan referral (MetLife Legal Plan, LegalShield), or the Area Agency on Aging's legal-services line. Reuses `*_Timeline.md`, `*_HotItems.md`, and `*_Findings.md` from the `/snf-review` pipeline. Tone is cooperative and attorney-facing — the audience is on the user's side. Produces a markdown packet (optionally .docx) whose first page is always a case-in-a-page summary, because attorneys triage on page one. Use when the user says "/legal-referral-intake-packet", "draft MetLife legal plan intake", "elder-law attorney intake", "AAA legal services referral", "assemble legal referral packet", or otherwise signals that it's time to hand the case over (or up) to a lawyer.

2026-07-251

name	local-analysis-offload
description	Plan privacy-first local AI/model offload for expensive elder-care casework analysis. Use for Qwen/GLM/Gemma-class local models, LM Studio/lms, LM Studio OpenAI-compatible API, Goose CLI, Ollama, llama.cpp, vLLM, local VLM/image analysis, OCR, ffmpeg, Whisper, Parakeet, diarization, transcript enrichment, and batch prompt planning. Defaults to plan-only until the user approves running jobs.
argument-hint	Workload, input paths, output root, candidate tools/models, plan-only or run, validation standard

Local Analysis Offload

This VS Code / Copilot skill wrapper points to the canonical Cowork / Claude Desktop plugin workflow.

Load these files

../../../elder-care-casework/skills/local-analysis-offload/SKILL.md
../../../elder-care-casework/skills/audio-transcript-review/LOCAL_AUDIO_OFFLOAD.md for audio/transcript work.
Any workload-specific canonical skill, such as ../../../elder-care-casework/skills/snf-records-review/SKILL.md or ../../../elder-care-casework/skills/audio-transcript-review/SKILL.md.

Use this wrapper when

The user wants to use local models or deterministic local tools before consuming main-agent context.
The task is expensive, repetitive, or privacy-sensitive: OCR/image labeling, transcript cleanup, speaker attribution, table extraction, first-pass tagging, or packet review triage.
The user mentions Qwen, GLM, Gemma, LM Studio, lms, LM Studio OpenAI-compatible API, Goose, Ollama, llama.cpp, vLLM, ffmpeg, Whisper, Parakeet, diarization, VLM, local image analysis, or GPU offload.

Default to plan-only. Do not run local tools or models until the user explicitly approves the run.