← 返回 Skills 市场
j3m2b

Catalyst Edge

作者 j3m2b · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
108
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install jb-catalyst-edge
功能描述
Identifies high-conviction stock opportunities and tracks JB's retirement portfolio with weekly scans, quarterly reviews, and FIRE signal analysis.
使用说明 (SKILL.md)

Skill: Catalyst Edge

Purpose: High-conviction stock opportunities + JB's retirement portfolio tracker.

Trigger: Weekly (Sunday 10 AM CDT via cron) or on demand.

Part 1 — Stock Scanning

What It Looks For

Pattern Description Conviction
Earnings Surprise Beat estimates, raised guidance 🟡-🟢
Catalyst Event FDA approval, contract win, merger 🟡-🟠
Technical Breakout Volume surge, breakout above resistance 🟡
Insider Buying Executives buying heavily 🟡
Sector Rotation Money flowing into our themes 🟢

Target Themes

  • Healthcare/RCM tech
  • AI/automation
  • Dividend payers
  • Growth with value

Quality Criteria

  • Score ≥75 = alert JB immediately (Discord DM)
  • Score 60-75 = include in weekly summary
  • Score \x3C60 = skip
  • Always include source + date

Output Format

🎯 CATALYST EDGE — [Date]

[Stock] — [Ticker]
Catalyst: [What it is]
Conviction: [🔵🟡🟢🟠]
Score: [0-100]
Thesis: [1-sentence why]

Watch List:
1. [Stock] - [reason]
2. [Stock] - [reason]

Part 2 — Quarterly Financial Review (Every 3 Months)

Trigger: January, April, July, October — first Sunday of the month at 10 AM CDT.

Steps

  1. Read the current state:

    • /workspace/skills/catalyst-edge/FIRE_MODEL.md — current numbers
    • /workspace/skills/catalyst-edge/PORTFOLIO_ANALYSIS.md — portfolio
    • /workspace/memory/life-archive.md — personal context

  2. Post to Discord #retirement-edge:

    📊 QUARTERLY FINANCIAL REVIEW — [Month Year]

Net Worth: $XX,XXX (vs $XX,XXX last quarter — +/- $X,XXX)
This Quarter: [what changed — new savings, paid down debt, market movement]

FIRE Progress: [X years to FI / age XX target]
Next Quarter Goals:
• [Action 1]
• [Action 2]

Action Items Due:
• [Stale items from FIRE_MODEL.md priority list]

  3. Update the files:

    • Note any account changes in PORTFOLIO_ANALYSIS.md
    • Flag any action items that are overdue
    • Log the quarter's net worth in a table at the bottom of FIRE_MODEL.md

  4. Alert JB if:

    • A major milestone was hit (e.g., hit $100K, mortgage paid off early)
    • An action item is 60+ days overdue
    • Net worth dropped >15% (market downturn check)

Quality Standards

  • Keep it to 10 lines or less in Discord
  • Full details go in the .md files
  • Numbers over opinions always

Part 3 — FIRE Pipeline (Weekly)

Trigger: Runs alongside the weekly stock scan (Sunday 10 AM CDT).

What It Does

  1. Reads RSI results from /workspace/skills/catalyst-edge/stock_scanner/last_scan.json
  2. Applies FIRE model thresholds from /workspace/skills/catalyst-edge/fire_config.json
  3. Calculates signals: STRONG BUY / BUY / HOLD / WEAK / AVOID / TAKE PROFIT
  4. Posts a formatted signal report to Discord #retirement-edge

FIRE Signal Logic

RSI Range Signal Action
≤ 30 (core) / ≤ 35 (income) 🟢 STRONG BUY FI deployment window
30-40 🟢 BUY Accumulation candidate
40-60 🟡 HOLD No action
60-70 🟠 WEAK Partial profit taking
≥ 70 (core) / ≥ 75 (income) 🔴 TAKE PROFIT / AVOID Book gains; not an entry

Core Principle

VT/VTI/QYLD at RSI ~29-30 simultaneously = historically rare cluster bottom. When 2+ core holdings hit RSI \x3C 30 → FI deployment signal. This has happened \x3C5 times in the past 5 years.

Run the Pipeline

cd /workspace/skills/catalyst-edge/stock_scanner
python3 scan_once.py  # runs fresh scan
python3 ../fire_pipeline.py  # applies FIRE logic + posts to Discord

Files

  • /workspace/skills/catalyst-edge/SKILL.md (this)
  • /workspace/skills/catalyst-edge/FIRE_MODEL.md — current numbers
  • /workspace/skills/catalyst-edge/PORTFOLIO_ANALYSIS.md — portfolio details
  • /workspace/skills/catalyst-edge/HISTORICAL_PICKS.md — past picks + performance
  • /workspace/skills/catalyst-edge/fire_config.json — FIRE threshold config
  • /workspace/skills/catalyst-edge/fire_pipeline.py — signal engine
  • /workspace/skills/catalyst-edge/stock_scanner/last_scan.json — latest scan results
安全使用建议
This skill mostly does what it says (scans tickers, computes FIRE signals, writes .md reports), but I recommend you do not install or enable it until you address these issues: - Remove or redact personal financial documents included in the skill (CASH_FLOW_ANALYSIS.md, FIRE_MODEL.md, PORTFOLIO_ANALYSIS.md) or keep them outside the skill bundle. Those files contain PII and account details that the skill will read and could post to Discord. - Confirm and control how Discord posting is authorized. The code has a channel/server ID but no declared token or webhook; ask the author how credentials are supplied. Prefer storing any Discord bot token or webhook URL in a secure environment variable (not in repo) and require explicit admin consent before the skill can post. - Rotate or remove the hard-coded Alpha Vantage API key. If Alpha Vantage is not needed (scan_once.py uses Yahoo), remove scanner.py or disable its embedded key. Never leave secrets in code. - If you plan to run this skill, run it in a sandboxed environment first (no access to your full workspace/memory). Limit the skill's read access to only the specific portfolio files you approve. Consider disabling autonomous invocation until you trust the deployment. If the author can justify the included personal files, move any tokens/keys to secure env vars, and remove hard-coded secrets, the skill would move closer to coherent. As-is, there is a real privacy and credential-handling mismatch — proceed with caution.
功能分析
Type: OpenClaw Skill Name: jb-catalyst-edge Version: 1.0.1 The skill bundle is classified as suspicious due to high-risk data handling and hardcoded credentials. Specifically, SKILL.md instructs the agent to read /workspace/memory/life-archive.md (a sensitive personal data store) and fire_pipeline.py exfiltrates financial summaries to a hardcoded Discord channel (ID: 1484979090892259449). Additionally, stock_scanner/scanner.py contains a hardcoded Alpha Vantage API key (AYP4CXXCHLRXNH8L). While these behaviors align with the stated purpose of a personalized retirement tracker, the hardcoding of external exfiltration targets and the broad access to personal memory files represent significant security risks.
能力评估
ℹ Purpose & Capability
The code (scan scripts, FIRE pipeline) implements stock scanning, weekly/quarterly reviews, and Discord notifications as described — that matches the skill's stated purpose. Minor redundancy: two scanner implementations exist (scan_once.py uses Yahoo Finance; scanner.py uses Alpha Vantage and includes a hardcoded API key), which is explainable but unnecessary.
⚠ Instruction Scope
SKILL.md instructs the agent to read multiple local files including personal documents and '/workspace/memory/life-archive.md' (agent memory). The repo in fact contains highly sensitive personal financial files (bank account numbers, credit card suffixes, spouse & dependent info). The instructions also require posting summaries to a Discord channel but do not declare how credentials/webhook or posting authorization are obtained. Reading and broadcasting that level of personal data is scope-expansive and risky.
✓ Install Mechanism
No install spec; this is effectively an instruction+code skill that runs existing Python scripts. That is low-install risk (nothing downloaded from arbitrary URLs).
⚠ Credentials
Registry metadata claims no required env vars or credentials, yet the code performs network calls and expects to post to Discord. scanner.py contains a hard-coded Alpha Vantage API key (embedded secret) while SKILL.md claims the primary scanner uses Yahoo (no key). Discord channel and server IDs are hard-coded, but there's no declared mechanism for the Discord bot token or webhook — a missing credential declaration is an incoherence. Also the skill expects access to agent memory and local files containing PII, which is far-reaching relative to a simple stock scanner.
ℹ Persistence & Privilege
always:false (normal). The skill can be invoked autonomously (platform default). Autonomous invocation combined with the ability to read personal files and post to an external chat channel increases the blast radius; this is a contextual operational risk rather than a direct misconfiguration in the manifest.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install jb-catalyst-edge
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /jb-catalyst-edge 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.1
Sanitized: excluded private scan logs and config
v1.0.0
Catalyst Edge 1.0.0 introduces a streamlined workflow for high-conviction stock opportunities and FIRE tracking: - Weekly scans for actionable stock catalysts, with conviction scores and theme focus. - Automated notifications for high-scoring opportunities via Discord. - Quarterly financial review workflow, including portfolio progress and overdue action alerts. - FIRE pipeline analyzes RSI and model thresholds to generate clear buy/hold/sell signals. - All updates and signals posted to dedicated Discord channels for easy tracking.
元数据
Slug jb-catalyst-edge
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Catalyst Edge 是什么？

Identifies high-conviction stock opportunities and tracks JB's retirement portfolio with weekly scans, quarterly reviews, and FIRE signal analysis. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 108 次。

如何安装 Catalyst Edge？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install jb-catalyst-edge」即可一键安装，无需额外配置。

Catalyst Edge 是免费的吗？

是的，Catalyst Edge 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Catalyst Edge 支持哪些平台？

Catalyst Edge 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Catalyst Edge？

由 j3m2b（@j3m2b）开发并维护，当前版本 v1.0.1。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论