← Back to list
alphaear-deepear-lite Checked
Fetch the latest financial signals and transmission-chain analyses from DeepEar Lite. Use when th…
7.8Overall rating
2Views
6Downloads
3.0kStars
Installation
🤖 Install via AI
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "alphaear-deepear-lite" skill by following the instructions at https://skill123.me/install/alphaear-deepear-lite.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/alphaear-deepear-lite.sh | bash
📦 Download ZIP
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v1.0.0 · 2 KB🛡 Dynamic test
—
Not live-tested yet — this skill is rated on static analysis only.
About this skill
Fetch the latest financial signals and transmission-chain analyses from DeepEar Lite. Use when the user needs immediate insights into financial market trends, stock performance factors, and reasoning from the DeepEar Lite dashboard.
DeepEar Lite Skill
Documentation
Fetch the latest financial signals and transmission-chain analyses from DeepEar Lite. Use when the user needs immediate insights into financial market trends, stock performance factors, and reasoning from the DeepEar Lite dashboard.
DeepEar Lite Skill
Overview
Fetch high-frequency financial signals, including titles, summaries, confidence scores, and reasoning directly from the DeepEar Lite platform's real-time data source.
Capabilities
### 1. Fetch Latest Financial Signals
Use scripts/deepear_lite.py via DeepEarLiteTools.
- **Fetch Signals**:
fetch_latest_signals() - Retrieves all latest signals from
https://deepear.vercel.app/latest.json. - Returns a formatted report of signal titles, sentiment/confidence metrics, summaries, and source links.
Dependencies
-
requests,loguru - No local database required for this skill.
Testing
Run the test script to verify the connection and data fetching:
python scripts/deepear_lite.py
Score breakdown
Trigger
5.0
Trigger Quality 10/20: What (fetch financial signals/transmission-chain analyses) and When (immediate insights into market trends, stock performance factors) are covered, but there is no When Not clause and no exclusion boundary (1.4 = 0). Trigger coverage is narrow — a single English phrasing family with no indirect-expression or variant triggers (1.2 = 3/7). Keyword richness is moderate: financial signals, transmission-chain, market trends, stock performance, DeepEar Lite dashboard (1.3 = 3/4). Description completeness 4/6 (When Not missing).
Structure
8.7
Structure Design 13/15: SKILL.md is 32 lines, well within limits (2.1 = 4/4). Resource classification is correct — executable code in scripts/, no mixing (2.2 = 5/5). Progressive disclosure is only implicit; there is no explicit when/why-to-load annotation, though with a single script there is little to disclose (2.3 = 2/4). No README/CHANGELOG or other redundant files (2.4 = 2/2).
Workflow
6.8
Workflow Design 17/25: A reasonable Tool Wrapper pattern choice for a data-fetch skill (3.2 = 5/6), and the risky/deterministic part (HTTP fetch, parsing, formatting) is fully scripted while nothing else needs freedom (3.3 = 4/6). Error handling exists at the script level: try/except, raise_for_status, timeout=10, empty-signal guard (3.4 = 3/4). A verification step is present (run python scripts/deepear_lite.py to verify connection) (3.5 = 2/3). But the SKILL.md is more capability description than task instruction — it says to use DeepEarLiteTools.fetch_latest_signals() without showing how the agent should instantiate or invoke it, and gives no guidance on interpreting or presenting results (3.1 = 3/6).
Content
9.0
Content Quality 9/10: Writing is concise and imperative, every sentence is actionable, no filler (4.1 = 4/4). Formatting is uniform with proper code blocks and headers (4.3 = 3/3). Command executability is slightly weak: the test command works, but there is no copy-pasteable invocation example for fetch_latest_signals() itself (no python -c or import snippet), leaving the agent to infer usage from the script source (4.2 = 2/3).
Engineering
9.0
Engineering Robustness 9/10: Frontmatter has valid name and description in correct YAML (5.1 = 3/3). The single referenced path scripts/deepear_lite.py exists (5.3 = 3/3). Script has no shebang but does have a run instruction (python scripts/...) and its dependencies (requests, loguru) are declared in SKILL.md (5.2 = 3/4; shebang missing and loguru is an unnecessary heavyweight dependency for this use case).
Security
10.0
Security & Compliance 20/20: Capability manifest — (1) data source reads: none, only a remote JSON endpoint; (2) side effects: none, no file writes or deletions; (3) network destinations: single GET to https://deepear.vercel.app/latest.json, fully declared in both description and SKILL.md; (4) credential access: none; (5) persistence: none (no cron, launch agents, rc files, or git hooks). Promise-capability gap analysis: capabilities match declared scope — no undeclared network egress, no undeclared data access. No eval/base64 dynamic execution, no destructive commands, no prompt injection text, no hardcoded secrets, and the external URL is the platform's own vercel.app subdomain. No veto conditions met.
Small, clean tool-wrapper skill that fetches financial signals from the DeepEar Lite dashboard. Strengths: excellent security posture (single declared GET to https://deepear.vercel.app/latest.json, try/except with raise_for_status, no local file/credential access, no side effects, no persistence); concise 32-line SKILL.md; correct frontmatter and file layout; dependencies declared. Weaknesses: thin trigger design (no When Not boundary, limited trigger-phrase variants), workflow is more descriptive than instructional (no usage code example showing how the agent should call DeepEarLiteTools, only a bare test command), script lacks shebang, and the skill is entirely dependent on a third-party vercel.app endpoint with no offline or error-recovery guidance beyond the script-level try/except. Dimension 6 pre-check: capability manifest matches declared scope — the only network egress (deepear.vercel.app) is explicitly documented; capabilities match declared scope, no undeclared gaps.
Assessment methodology
AI-assessed
Evaluated by automated analysis across quality, usability, and security dimensions. This is not a substitute for your own review — always inspect a skill before installing it.
Version history
v1.0.0
2026-09-20
Imported from RKiding/Awesome-finance-skills@main