← 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
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 KBAbout this skill
Overview
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.
Source
- Repo: https://github.com/RKiding/Awesome-finance-skills
- Path: skills/alphaear-deepear-lite
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.