What does this skill do, and when should you use it?
This skill enables the AI agent to draw technical annotations directly on stock price charts, such as support/resistance levels, trendlines, Fibonacci retracements, event markers, and text labels. It provides two tools: draw_chart_annotation (add a single annotation) and manage_chart_annotations (list, remove, or clear annotations). Annotations are organized by symbol:timeframe (e.g. NVDA:1day) and render live on the interactive MarketView chart, or as a clickable preview card in any other chat. The skill is designed to replace prose descriptions of price levels or patterns, making analysis clearer and more visual.
The skill provides two core tools: draw_chart_annotation adds a single annotation to a chart, supporting types like price_line, trendline, marker, vertical_line, rectangle, text, event, and fib_retracement. manage_chart_annotations manages existing annotations with list, remove, and clear_all actions. Annotations are scoped to a symbol:timeframe pair (e.g. NVDA:1day) and accumulate on the same chart when re-called. It reads user chart selections (region or price_level blocks) and can draw matching shapes on the same chart based on analysis. Annotations render live on MarketView (an interactive chart page) or as clickable preview cards in other chats.
- A technical analyst discussing a support level in chat draws a price_line annotation instead of typing the price in words.
- An investor viewing a chart selects a region via the chart-selection feature; the agent analyzes it and draws a rectangle or price_line on the same chart.
- Marking an earnings date, analyst upgrade, or product launch with an event or marker annotation at the corresponding time.
- When analyzing a trend, using the trendline tool to connect two high or low points to show a channel or direction.
How do you install this skill?
- The skill depends on market data sources (ginlix-data, FMP, Yahoo) that may be inaccessible in mainland China; be aware of network restrictions.
- Publisher is unverified; evaluate risks before use.
- Network access
This skill is part of the LangAlpha repository (ginlix-ai/LangAlpha). Clone the repo and follow the README to set up the LangAlpha system (requires Docker and your own LLM subscription). The skill lives at skills/chart-annotation/SKILL.md and is loaded automatically by the agent when needed.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/ginlix-ai/LangAlpha.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/chart-annotation" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Draw a support line at 205.
In LangAlpha chat, simply describe the level or pattern you want annotated, e.g. 'Draw a support line at 205.' The skill triggers automatically. If you are on MarketView, the annotation appears live; otherwise a clickable preview card is shown. You can also send a chart-selection block (region or price level) to the agent, which analyzes it and draws the corresponding annotation. Inside the tool call, specify the annotation type and its parameters (price, time, label, etc.) via JSON.
What are this skill's strengths and limitations?
- Visualize levels and patterns directly on an interactive chart, clearer than prose.
- Supports a rich set of annotation types: price lines, trendlines, rectangles, events, Fibonacci retracements, and more.
- Annotations are scoped per symbol:timeframe, so multiple charts can be managed independently.
- Renders live and provides a preview card for out-of-chart contexts.
- Enables interactive analysis via chart selections from the user.
- Requires the LangAlpha system; cannot be used standalone.
- No dedicated test suite or documentation; integration depends on the whole repo.
- Supports only specific timeframes (1min to 1day); no intraday sub-minute intervals.
- Needs network access for market data and is tied to LangAlpha's data providers.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Chart Annotation this page | 52 · Use with care | ★ 1.8k | 3d ago | Apache-2.0 |
| TradingView MCP AI Trading Intelligence | 50 · Use with care | ★ 5k | 4d ago | MIT |
| Taiwan Stock One-Click Financial Model & Investment Deck Generator | 45 · Not recommended | ★ 40 | 3mo ago | — |
| Financial Analyst Skill | 52 · Use with care | ★ 62 | 7mo ago | MIT |
| Deep Stock Analysis Workflow (UZI-Skill deep-analysis) | 50 · Use with care | ★ 7.1k | 1mo ago | MIT |
How did FollowSkills review this skill?
The evidence shows the skill only exposes tool interfaces without explicit least-privilege or user-confirmation requirements; however, the documentation clearly states operational scope (e.g., clear_all does not delete user's original annotations) and no malicious behavior or excessive permissions were found. Deductions: lack of explicit permission requirements, user-confirmation mechanism, data-flow disclosure, and rollback plans. Unverified publisher noted but not deducted.
The skill documentation provides detailed parameter descriptions and examples, but lacks complete error-handling and edge-case coverage; no tests or execution evidence, reliability capped at 10, give 8 here. Deduction: no failure-feedback mechanism described.
Scenarios and trigger conditions are clearly described, accurately indicating when to use the skill; however, capability boundaries and non-fit scenarios are not specified, and no reachability documentation for mainland-China networks. Deduction: boundaries and trigger precision incomplete.
Information architecture is clear with layered documentation; but lacks install/dependency notes, versioning, and update path. Deduction: governance and maintenance responsibility unclear.
Core task is clear and output format is well-defined, but lacks actual execution verification and comparative benefit evidence, so marginal value is unconfirmed. Deduction: no execution or benefit evidence.
No tests, CI, or independently reproducible evidence present; documentation claims cannot be independently verified. Deduction: lack of evidence sources.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →