Agent skill

Morning Note

by ginlix-ai in ginlix-ai/LangAlpha

Daily research briefing on overnight news, pre-market movers, earnings and macro events.

Apache-2.0Auto-check passedSales & Support

Install Morning Note

skills CLI
$ npx skills add ginlix-ai/LangAlpha --skill morning-note -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ginlix-ai/LangAlpha morning-note --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ginlix-ai/LangAlpha.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/langalpha_research/skills/morning-note .claude/skills/morning-note && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
morning-note
GitHub stars
1.8k
Token cost
~1.7k tokens
SKILL.md length
1,006 words
Files
1
Skills in repo
37
Repo updated
First seen
Licence
Apache-2.0

At a glance

Daily research briefing on overnight news, pre-market movers, earnings and macro events.

  • Works in 5 steps: Gather overnight developments, labelled… → Decide what is already priced → Write the note → …
  • Morning meeting
  • SKILL.md covers Workflow and Important notes
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Morning Note is an agent skill from ginlix-ai/LangAlpha. Daily research briefing on overnight news, pre-market movers, earnings and macro events. Triggers on morning note, morning meeting, what happened overnight, morning call prep, daily note, trade idea for the open.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Sales & Support, covering Sales call preparation and Note-taking. The repository describes itself as: Claude Code for Financial Market. The licence is Apache-2.0.

When your agent uses it

  • Morning meeting
  • What happened overnight
  • Morning call prep
  • Trade idea for the open

Example prompts

  • “/morning-note”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Gather overnight developments, labelled as they land
  2. Decide what is already priced
  3. Write the note
  4. Quick take on a coverage print
  5. Deliver

What it can do on your machine

Read from SKILL.md and the folder at commit 2855e43. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Morning Note loads about 1.7k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 1,006 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ginlix-ai/LangAlpha at commit 2855e43, republished under its Apache-2.0 licence (© ginlix-ai). 1,006 words, ~1,717 tokens.

Download SKILL.mdSave it as .claude/skills/morning-note/SKILL.md (or your agent's skills folder).
name
morning-note
description
Daily research briefing on overnight news, pre-market movers, earnings and macro events. Triggers on morning note, morning meeting, what happened overnight, morning call prep, daily note, trade idea for the open.

Morning Note

One page, read in two minutes, with a view in it. A note that summarises the tape without saying what to think about it wastes the only two minutes the desk will give it.

Evidence labels, source tiers, staleness, the readiness posture and the intake limits: .agents/skills/research-conventions/SKILL.md, read before the first deliverable.

Workflow

1. Gather overnight developments, labelled as they land

Earnings and guidance

  • get_earnings_calendar(from_date, to_date) on the macro MCP server for who reported and who reports next.
  • get_company_overview for consensus and the rating distribution; yf_analysis MCP get_upgrades_downgrades for dated rating changes and get_earnings_estimates for the current consensus, which together are the revision reading, since no tool carries a consensus time series and the pre-event estimate level is an evidence gap when a call needs it.
  • Surprises against consensus on revenue, EPS and the metric the name actually trades on.
  • Guidance raised, lowered or maintained, and against what the buy side was carrying.

News and events

  • WebSearch and WebFetch for overnight headlines, deals, management changes, product and regulatory decisions, and rating changes.

Market context

  • get_market_overview for index and sector performance, get_daily_prices for the overnight and pre-market moves, get_economic_calendar for what is still ahead, plus the commodity or currency move that matters to the coverage.

Label each item as it is collected rather than at write-up. A filing and a closed-period data print are fact. A company statement about itself is company claim, with the venue. A consensus figure is a street estimate, with its vintage. A report with no primary document behind it carries the outlet, the time, and whether the date is confirmed, scheduled, estimated or reported. A rumour reaches the note as a rumour, naming who reported it and what would confirm it, or it does not reach the note. The closed label set: .agents/skills/research-conventions/references/evidence.md.

2. Decide what is already priced

Every item that moved something splits one of two ways, and the split is the value the note adds over a headline feed. Apply the test in .agents/skills/research-conventions/references/judgment.md under "Priced in", which needs both the move and the revisions to carry the effect:

  • Priced in: both halves hold; the note says which move and which revisions carry it.
  • Needs proof: anything short of both, and the note names the print or the date that would put the claim in the numbers.

Name the channel or hold the claim. An impact claim runs from the event, through a named transmission channel, to a specific line item. "Tariffs are a headwind for the group" names no channel and does not ship. "A tariff on imported cells lands in module cost of goods sold, and the two names importing most of their supply carry it in gross margin from the September quarter" does. When the channel cannot be named, the item goes in as an observation without an implication, and the next step is source work.

Show full SKILL.md (528 more words)Show less
3. Write the note

Two stamps at the top, because they are different facts: the note carries the time it was written, and every figure carries the as-of of the data itself. A note written pre-market is a pre-market note all day; a quote inside it is stale by the open unless it says what it is as of. The always-timestamped list is in evidence.md.


[Date] Morning Note, [Analyst] [Sector coverage] | Written [time]. Prices as of [time], [session].

Top Call: [the one thing the desk needs to hear]

  • Two or three sentences on the development and why it matters.
  • Stock impact: rating and target reiterated or changed.

Overnight and Pre-Market

  • [Company A]: what happened, with its source. Our take: the view.
  • [Company B]: what happened, with its source. Our take: the view.
  • [Sector or macro]: the development, and which names it reaches.

Priced In / Needs Proof

  • Priced in: [name], [what the move and the revisions already reflect].
  • Needs proof: [name], [the claim], [the print or date that would confirm it].

Today

  • [Time]: [Company] earnings call, [what to listen for].
  • [Time]: [data release], consensus against our read.
  • [Time]: conference or investor day.

Trade Ideas (when there is one)

  • [Long/Short] [Company]: thesis in two sentences, plus the catalyst and its date.
  • Risk: the observation that would make this wrong.

Fact and view stay in separate sentences. What happened carries its source; the take carries the view and is marked as one. This is the deliverable most likely to be forwarded, and the sentence quoted back has to be one that can be defended. A view welded into the same sentence as a fact reads as a fact to everyone downstream.

4. Quick take on a coverage print
MetricConsensusActualBeat/Miss
Revenue
EPS
[The metric the name trades on]
Guidance

Our take: two or three sentences on whether this is good or bad for the stock, and whether it changes the thesis rather than the quarter.

Action: the verb from the gated vocabulary in .agents/skills/research-conventions/references/judgment.md, with a rating word (maintain, upgrade, downgrade) beside it where a published rating exists, and what would change it.

5. Deliver

Save to {task}/morning_note_YYYY-MM-DD.md, as markdown for email or chat distribution. The note carries one posture from the ladder in .agents/skills/research-conventions/SKILL.md, stated once beside the stamps at the top.

One page is the bar. Over it, cut in this order: the market recap the reader already saw on a screen, the second and third bullets on one name, the calendar entries with no view attached, and any trade idea with no dated catalyst. Depth bands and the general cut order: .agents/skills/research-conventions/references/depth.md.

Important notes

  • Be opinionated. A note that summarises without a view is a worse version of a headline feed.
  • Lead with the most important thing. The headline goes first, not third.
  • "Nothing material overnight, maintaining positioning" is a complete morning note, and a better one than three paragraphs of filler.
  • Separate the actionable (a print, a deal, a guidance change) from the noise (a small rating change, a non-event), and say which is which.
  • When yesterday's call was wrong, say so in today's note and say what you missed. Credibility outlasts any single call.

© ginlix-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/langalpha_research/skills/morning-note of ginlix-ai/LangAlpha.

Open the folder on GitHubat commit 2855e43

Compare with similar skills

Morning Note next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Morning Note compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Morning Note this skillginlix-ai/LangAlpha1.8k—~1.7kAutomated safety check: PassApache-2.0
Morning Noterongxinzy/RongxinAI1541 repos~754Automated safety check: PassAGPL-3.0
Luopan Company Researchzhangxiaoqiang1991/luopan389—~998Automated safety check: PassMIT
Company Researchstophobia/deerflow2.0-enhanced822—~845Automated safety check: PassMIT
Meeting Prep BriefBrianRWagner/ai-marketing-claude-code-skills441—~922Automated safety check: PassNone
SdtStopDisTrain/sdt-skills309—~535Automated safety check: PassMIT

Similar skills

  • Morning Note

    rongxinzy/RongxinAI

    Draft concise morning meeting notes summarizing overnight developments, trade ideas, and key events for coverage stocks.

    154 GitHub starsUsed in 1 repo~754 tokens
    Sales & SupportAuto-check passed
  • Luopan Company Research

    zhangxiaoqiang1991/luopan

    罗盘的公司研究子模式。研究具体上市或非上市公司的财务增长、商业模式、 竞争生态位、治理与组织信号,并分别生成投资初筛和求职初筛。

    389 GitHub stars~998 tokensUpdated 2 mo ago
    Sales & SupportAuto-check passed
  • Company Research

    stophobia/deerflow2.0-enhanced

    综合企业背景调研技能,用于尽职调查、合作伙伴评估、投资分析、市场研究等场景。支持公司工商信息、财务数据、法律风险、舆情分析、竞品对比等多维度调研,自动生成Markdown和HTML格式的专业调研报告。触发条件:用户提及"企业调研"、"公司背景"、"尽职调查"、"合作伙伴评估"、"投资分析"、"市场研究"等关键词。

    822 GitHub stars~845 tokensUpdated 6 mo ago
    Sales & SupportAuto-check passed
  • Meeting Prep Brief

    BrianRWagner/ai-marketing-claude-code-skills

    Builds a pre-meeting brief from your Obsidian vault: participant research, past notes, open commitments, a prioritized agenda and sharp questions.

    441 GitHub stars~922 tokensUpdated 6 mo ago
    Sales & SupportAuto-check passed
  • Sdt

    StopDisTrain/sdt-skills

    SDT 内容生产工具箱的总入口:根据当前任务选择最合适的 sdt- 模块,既能完成标题、开头等单一步骤,也能组织从账号研究到发布的完整流程。用户不知道该用哪个 SDT Skill,或希望一站式完成内容生产时使用。

    309 GitHub stars~535 tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed
  • Account Research

    extruct-ai/gtm-skills

    Deep-research a single target account into a decision-ready dossier: the entity tree, the buying units and decision-makers, live signals (open/closed roles, leadership moves, news, tech stack), and…

    109 GitHub stars~1.6k tokensUpdated 12 days ago
    Sales & SupportAuto-check passed

More from ginlix-ai/LangAlpha

All 37 skills in this repo
  • Investment Deck Check

    ginlix-ai/LangAlpha

    Quality-checks an investment deck in .pptx form before it goes out: number consistency, chart and narrative alignment, source coverage, language and a circulation verdict.

    1.8k GitHub stars~3.7k tokensUpdated today
    Auto-check passed
  • Equity Initiation Report

    ginlix-ai/LangAlpha

    Produces a first-time equity research initiation report in five tasks: company research, financial model, valuation, charts and a DOCX report.

    1.8k GitHub stars~3.8k tokensUpdated today
    Auto-check passed
  • Builds or repairs an integrated income statement, balance sheet and cash flow model in Excel with live formulas, supporting schedules, scenarios and a Checks sheet.

    1.8k GitHub stars~5.4k tokensUpdated today
    Auto-check passed
  • Financial Model Checker

    ginlix-ai/LangAlpha

    Audits an existing Excel financial model without editing it, checking structure, formulas, integrity identities and source tie-out, and ends in a prioritized issue log.

    1.8k GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • DCF Model Builder

    ginlix-ai/LangAlpha

    Builds a live Excel DCF valuation workbook with free cash flow projections, WACC, terminal value, three scenarios, sensitivity grids and a reverse DCF.

    1.8k GitHub stars~7.7k tokensUpdated today
    Auto-check passed
  • Builds Word files with python-docx, edits existing ones in place with tracked changes and comments, then renders and validates the result.

    1.8k GitHub stars~4.8k tokensUpdated today
    Auto-check passed

Questions about Morning Note

What does Morning Note do?

Daily research briefing on overnight news, pre-market movers, earnings and macro events. Morning Note is an agent skill from ginlix-ai/LangAlpha. Daily research briefing on overnight news, pre-market movers, earnings and macro events.

When should I use Morning Note?

Morning Note fits situations like: morning meeting; what happened overnight; morning call prep; trade idea for the open.

How do I install Morning Note in Claude Code?

Run `npx skills add ginlix-ai/LangAlpha --skill morning-note -a claude-code`. Or copy the skill folder (plugins/langalpha_research/skills/morning-note in ginlix-ai/LangAlpha) into .claude/skills/morning-note in your project. Claude Code loads it when a task matches its description.

How do I install Morning Note in Codex?

Run `npx skills add ginlix-ai/LangAlpha --skill morning-note -a codex`. Or copy the skill folder (plugins/langalpha_research/skills/morning-note in ginlix-ai/LangAlpha) into .agents/skills/morning-note in your project. Codex loads it when a task matches its description.

Can I use Morning Note in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ginlix-ai/LangAlpha --skill morning-note -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/morning-note, .gemini/skills/morning-note, .github/skills/morning-note and .opencode/skills/morning-note in your project.

What does Morning Note need to run?

SKILL.md names no scripts, command-line tools or credentials: Morning Note is instructions for the agent only.

Does Morning Note access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Morning Note safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Morning Note use?

Morning Note is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Morning Note use?

About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Morning Note?

Skills that share tags, products or a category with Morning Note: Morning Note (rongxinzy/RongxinAI, 154 stars), Luopan Company Research (zhangxiaoqiang1991/luopan, 389 stars), Company Research (stophobia/deerflow2.0-enhanced, 822 stars) and Meeting Prep Brief (BrianRWagner/ai-marketing-claude-code-skills, 441 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Morning Note?

ginlix-ai (a GitHub organization) maintains it in ginlix-ai/LangAlpha, which has 1,811 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 10, 2026.

Source: ginlix-ai/LangAlpha on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.