Alphagbm Health Check logo

Alphagbm Health Check

CommunityPopular
AlphaGBM
alphagbm-health-check

Weekly diagnostic report on a user's research knowledge base — flags stale profiles (not updated in weeks), thesis drift (AI detects original premise no longer holds), and orphan pages (profiles with no thesis, themes with missing profiles). Returns an overall 0-100 health score with specific action recommendations. Use when: auditing knowledge base state, triggering a fresh report, reviewing what needs attention. Triggers on: "health check my research", "what's stale", "any drift", "generate a report", "研究库体检", "过期档案", "论据偏离", "孤立主题".

Overview

PublisherAlphaGBM
Repositoryskills
Skill namealphagbm-health-check
Stars
2.7K
Forks
290
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by AlphaGBM on GitHub. Read the source before you install it.

Installation

Install the Alphagbm Health Check AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AlphaGBM/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/alphagbm-health-check .claude/skills/alphagbm-health-check
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Alphagbm Health Check in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Alphagbm Health Check on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Alphagbm Health Check is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AlphaGBM Knowledge Base Health Check

Periodic audit of a user's research workspace — stale profiles, drifted theses, orphan pages — with an overall 0-100 score and concrete recommendations.

When to use

  • User asks for an overview of what's broken / out of date in their KB
  • User wants to manually trigger a fresh health report
  • User asks about stale profiles, thesis drift, or orphan items
  • User mentions "健康体检" / "体检" / "audit" / "health check" / "什么需要更新"

Prerequisites

  • API Key: env ALPHAGBM_API_KEY (format agbm_xxxx…).
  • Base URL: default https://alphagbm.zeabur.app. Override via ALPHAGBM_BASE_URL.
  • Tier requirement for generate: POST /health/generate is Pro-only. Free/Plus users get 403 with upgrade_required: true. Free/Plus users can still read the latest auto-generated weekly report via GET /health.

API Endpoints

All endpoints require Authorization: Bearer $ALPHAGBM_API_KEY.

1. Get latest health report

GET /api/research/health

Response when a report exists:

json
{
  "success": true,
  "has_report": true,
  "report_date": "2026-04-13",
  "overall_score": 78,
  "stale_profiles": [
    {"ticker": "AAPL", "days_since_update": 21}
  ],
  "thesis_drift": [
    {"ticker": "NVDA", "drift_reason": "Revenue growth now 12% vs 25% when thesis was written"}
  ],
  "orphan_pages": [
    {"ticker": "XYZ", "issue": "Profile has no thesis after 30 days"}
  ],
  "recommendations": [
    {"action": "refresh", "ticker": "AAPL", "reason": "21 days stale"},
    {"action": "review_thesis", "ticker": "NVDA", "reason": "growth decelerated"},
    {"action": "archive", "ticker": "XYZ", "reason": "orphan for 30+ days"}
  ],
  "created_at": "2026-04-13T02:00:00Z"
}

Response when no report yet:

json
{
  "success": true,
  "has_report": false
}

2. Generate fresh report (Pro-only)

POST /api/research/health/generate

Kicks off immediate audit across the user's profiles + theses + themes. Returns the new report in the same shape as GET.

Tier-blocked response (403):

json
{
  "success": false,
  "error": "Health check generation is a Pro feature.",
  "upgrade_required": true
}

Free/Plus users still get an auto-generated report weekly (served by GET), just can't trigger on-demand.

Response schema — report

{
  id, report_date,
  stale_profiles,          // [{ticker, days_since_update}]
  thesis_drift,            // [{ticker, drift_reason}]
  orphan_pages,            // [{ticker, issue}]
  overall_score,           // 0-100
  recommendations,         // [{action, ticker, reason}]
  created_at
}

Score band interpretation

ScoreBandMeaning
90-100ExcellentNothing urgent
75-89GoodMinor staleness
60-74FairSeveral profiles need refresh, some drift
40-59PoorSignificant drift / orphans
0-39CriticalKB is mostly out of date

Recommendation action types

  • refresh — call POST /api/research/profiles/<ticker>/refresh
  • review_thesis — surface the thesis + updated fundamentals; user decides to edit/close
  • archiveDELETE /api/research/profiles/<ticker> or delete orphan
  • create_thesis — profile exists but has no thesis; prompt user to write one

Skills that execute these actions: alphagbm-company-profile, alphagbm-investment-thesis.

Typical Workflow

1. User: "How's my research brain looking?"
   → GET /api/research/health
   → If has_report=false: "No report yet — your first auto-audit runs on <day>.
      Pro users can trigger one now."
   → If has_report=true: present score + top 3 recommendations

2. User (Pro): "Run a fresh health check now"
   → POST /api/research/health/generate
   → Present the new report

3. User (Free/Plus): "Run a health check"
   → POST /api/research/health/generate returns 403
   → Fall back: show the last weekly auto-report via GET, suggest upgrade

4. User: "Fix the stale ones"
   → For each recommendation with action=refresh:
     POST /api/research/profiles/<ticker>/refresh
   → Re-check: GET /api/research/health → show updated score

Output Formatting Tips

When presenting a health report:

  1. Lead with overall score + band (color: green ≥ 75, yellow 60-74, red < 60)
  2. Top 3 recommendations — most actionable first (refresh > review > archive)
  3. Group by category — "3 stale profiles · 1 drifted thesis · 2 orphans" as a chip row
  4. Each ticker actionable — pair the reason with a one-click (or one-prompt) action
  5. Report date prominence — "as of 2026-04-13" so user knows freshness
  6. If no report yet — explain the weekly cadence, offer Pro upgrade for on-demand

Related Skills

  • alphagbm-company-profile — Run refresh on flagged stale profiles
  • alphagbm-investment-thesis — Review / close drifted theses
  • alphagbm-theme-research — Address orphan pages inside themes

Powered by AlphaGBM — Real-data options & research intelligence for traders and AI agents. 10K+ users.

Frequently asked questions

What does the Alphagbm Health Check AI skill do?

Weekly diagnostic report on a user's research knowledge base — flags stale profiles (not updated in weeks), thesis drift (AI detects original premise no longer holds), and orphan pages (profiles with no thesis, themes with missing profiles). Returns an overall 0-100 health score with specific action recommendations. Use when: auditing knowledge base state, triggering a fresh report, reviewing what needs attention. Triggers on: "health check my research", "what's stale", "any drift", "generate a report", "研究库体检", "过期档案", "论据偏离", "孤立主题".

Why use Alphagbm Health Check on TypingMind?

Because you install it once and use it with any model. Alphagbm Health Check is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Alphagbm Health Check in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AlphaGBM/skills/tree/main/skills/alphagbm-health-check. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Alphagbm Health Check?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Alphagbm Health Check?

As many as you like. As long as a model supports skills, you can use Alphagbm Health Check with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Alphagbm Health Check AI skill free?

Yes. It is published on GitHub by AlphaGBM under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇