New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Equity Research Core

by byteseek in byteseek/Mira

Run Mira's core single-equity research workflow across fundamentals, financial quality, macro context, technical pricing, events, and thesis framing.

Apache-2.0Auto-check passedBusiness, Finance & HR

Install Equity Research Core

skills CLI
$ npx skills add byteseek/Mira --skill equity-research-core -a claude-code

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

GitHub CLI
$ gh skill install byteseek/Mira equity-research-core --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/byteseek/Mira.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/equity-research-core .claude/skills/equity-research-core && 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
equity-research-core
GitHub stars
275
Token cost
~1.9k tokens
SKILL.md length
495 words
Files
12 (incl. references)
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Run Mira's core single-equity research workflow across fundamentals, financial quality, macro context, technical pricing, events, and thesis framing.

  • Tasks that involve Stock and market analysis
  • SKILL.md covers Upstream Analysis Routing, Use When, Required Inputs and Thesis Horizon Routing, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Essays and academic help

What it does

Equity Research Core is an agent skill from byteseek/Mira. Run Mira's core single-equity research workflow across fundamentals, financial quality, macro context, technical pricing, events, and thesis framing.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `references/commodity-overlay.md`, `references/framework-routing.md` and `references/large-mega.md`).

It sits in Business, Finance & HR, covering Stock and market analysis and Essays and academic help. The repository describes itself as: Agent-native investment research workspace for evidence-tracked, refreshable investment theses across equities, earnings, macro, and portfolio review. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Stock and market analysis
  • Tasks that involve Essays and academic help

Example prompts

  • “/equity-research-core”

What it can do on your machine

Read from SKILL.md and the folder at commit adddce7. 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

Equity Research Core loads about 1.9k tokens when it runs, and up to ~19k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 495 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~19k

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 byteseek/Mira at commit adddce7, republished under its Apache-2.0 licence (© byteseek). 495 words, ~1,853 tokens.

Download SKILL.mdSave it as .claude/skills/equity-research-core/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
equity-research-core
description
Run Mira's core single-equity research workflow across fundamentals, financial quality, macro context, technical pricing, events, and thesis framing.

Equity Research Core Skill

这是当前主 research skill，用于在单次研究中统一处理：

  • 基本面
  • 财务质量
  • 宏观经济与金融条件
  • 技术面节奏
  • 事件与舆情

它不是多个独立 skill 的简单拼接，而是一个面向 research package 的主 skill。

这个 skill 现在采用：

  • 一个统一输出骨架
  • 一个 upstream analysis router
  • 一个 thesis horizon router
  • 一个 framework router
  • 一个 overlay selector
  • 多个可切换研究框架

也就是说，输出仍然统一，但研究顺序、证据权重和结论重心会随时间跨度和标的的定价主导变量变化。

在主框架之外，还允许叠加专题 overlay，用于补充特定研究路径。

Upstream Analysis Routing

进入本 skill 前，应先通过总路由确认任务确实是 single_equity。

总路由见：

如果任务本质是财报事件、产业概念、宏观 regime、ETF 产品或方法论研究，应优先进入对应 loop / skill，再决定是否 handoff 到单票研究。

Use When

  • 需要对单一股票做首次覆盖或阶段性复核
  • 需要把多源数据整理成一个可追溯的研究包
  • 需要在同一份输出里同时包含公司、财务、宏观、价格、事件等视角
  • 需要根据标的特征切换研究框架，而不是默认用同一套分析权重
  • 需要区分财报/短中期执行判断和一年以上的长期公司或产业 thesis
  • 已通过 industry-concept-analysis 识别出某个产业概念中的候选标的，需要进入单票研究

Required Inputs

  • company_name
  • ticker
  • market
  • research_question
  • research_cutoff_date
  • thesis_horizon
  • depth_mode 可选；默认由 analysis-routing 推断
  • framework_hint 可选，用户已有明确框架偏好时使用
  • overlay_hint 可选，用户已有明确研究视角时使用

Thesis Horizon Routing

在正式分析前，必须先完成 thesis horizon selection。

默认不要把最新财报、未来几个季度盈利修正和长期产业趋势写成同一种结论。先判断：

  • thesis_horizon
  • horizon_bucket
  • horizon_basis
  • horizon_mismatch_risk

时间跨度选择规则见：

当前默认支持四种 horizon bucket：

  • near_term_execution
  • medium_term_revision
  • long_term_thesis
  • regime_transition

Framework Routing

完成 thesis horizon selection 后，必须继续完成 framework selection。

默认不要只按市值机械分类，而要优先判断：

  • market_cap_bucket
  • liquidity_and_float
  • ownership_structure
  • business_maturity
  • catalyst_type
  • valuation_anchor_usefulness

框架选择规则见：

当前默认支持三个主框架：

如果标的存在明显混合特征，允许声明：

  • 主框架
  • 次要干扰变量
  • 为什么不采用另一个看起来相近的框架

Overlay Selection

完成主框架选择后，可以继续判断是否需要专题 overlay。

overlay 不改变主框架，只补充一条高价值研究路径。

当前可用 overlay 以 references/overlay-routing.md 为单一来源，常用包括：

overlay 选择规则见：

supply-chain overlay 适用于以下问题：

  • 上下游传导是否决定盈利弹性
  • 客户集中度是否决定收入确定性
  • 哪一层供应链更受益或更受损
  • 同层级可比公司对照能否帮助验证叙事

macro overlay 适用于以下问题：

  • 增长、通胀、政策、利率、美元、信用、流动性或风险偏好是否主导当前定价
  • 市场已经 price in 的宏观路径是什么
  • 宏观变量通过哪条链影响收入、利润率、估值、融资、仓位或催化剂
  • 新数据或政策口径是否会改变 thesis

strategic-catalyst overlay 适用于以下问题：

  • 巨头合作、投资、并购、客户认证、独家授权、平台接入或供应链导入是否会重写小盘股预期
  • 社交传闻、行业聊天、异常量价或非正式线索是否值得纳入 alpha signal 监控
  • 线索应如何区分为 confirmed、reported、social_signal 或 unverified_rumor
  • 下一步确认或证伪路径是什么

Required Source Types

  • L1 公司披露或官方材料
  • L5 市场数据
  • L4 事件/新闻材料可选但建议使用
  • 如果启用 macro overlay，至少补充官方宏观数据、政策材料或市场定价数据中的两类
  • 如果启用 strategic-catalyst overlay，允许使用 social_and_community 作为 alpha signal，但必须降级标记并写入验证路径

SEC Filing Boundary

单票研究默认把 SEC 作为事实底座和冲突校验，走 sec_supplement：

  • 查 CIK、最新 filing timeline、10-K/10-Q/8-K/proxy 是否覆盖研究 cutoff。
  • 抽取 thesis-critical 指标，例如 cash flow、debt、share count、SBC、inventory、RPO/backlog、segment、customer concentration 或 risk-factor facts。
  • 在 evidence-log.csv、financial snapshot 或 case notes 中记录 SEC provenance。

只有在以下情况升级为 sec_filing_deep_dive：

  • 用户明确要求拆 SEC 文件。
  • 核心 thesis 依赖 accounting quality、risk factor delta、debt/liquidity、related-party、ownership/control、dilution 或 segment 细节。
  • filing 与 release、management commentary、market-data page 或 prior Mira case 冲突。
  • 缺失 filing 阻断 actionability，需要 source-gap refresh 后再复核。
Show full SKILL.md (225 more words)Show less

Output Package

这个 skill 默认输出统一的 research package，但受 depth_mode 约束：

  • quick_map: 可以只输出 routing card、core judgment、source notes、source gaps、refresh triggers 和升级条件；不默认写完整 case artifacts。
  • standard: 输出完整 research package。
  • deep_dive: 在完整 package 外，按 gate 触发 expectation map、calculation artifacts、workflow scorecard 或专题 overlay 文件。

标准 research package 包括：

  • investment-memo.md
  • evidence-log.csv
  • case-notes.md

研究包里必须显式写明：

  • task_mode
  • research_object
  • routing_basis
  • routing_mismatch_risk
  • horizon_bucket
  • horizon_basis
  • horizon_mismatch_risk
  • selected_framework
  • framework_basis
  • framework_mismatch_risk
  • selected_overlays
  • overlay_basis
  • selected_lenses
  • lens_basis
  • readiness_level
  • readiness_basis
  • blocking_gaps
  • evidence_log_status
  • quant_gate_status

新的 evidence-log.csv 应使用 ../../data/evidence-posture-taxonomy.md 中的 evidence posture 字段。不要因为来源层级高就自动把 claim 升级成 verified_fact；必须匹配 claim、期间、口径、单位和当前研究用途。

研究包还应包含或更新 research-package-manifest.json，用于记录 hero artifacts、 support artifacts、readiness、handoffs、source scope、quant gate 和 refresh 条件。

如果研究问题明显属于“预期差判断”，建议额外使用：

这个 checklist 不替代 memo，只用于把 thesis 压缩成：

  • consensus proxy
  • what is mispriced
  • why market may be wrong
  • what changes the price
  • what falsifies the view

如果研究问题明显属于“长期 10x / 100x / multibagger 候选”，建议额外使用：

这个 checklist 不替代 memo，只用于把长期 thesis 压缩成：

  • target_return_path
  • return_path_math
  • market_expansion
  • right_to_win
  • reinvestment_runway
  • dilution_risk
  • evidence_ladder
  • kill_criteria

Required Sections In Case Notes

  • business and industry
  • financial quality
  • macro and financial conditions
  • technical context
  • events and sentiment
  • overlays
  • fact vs inference
  • claim classification notes

Boundaries

  • 它只定义研究组织方式，不承诺自动抓取。
  • 它不把每个框架拆成完全独立的报告系统。
  • 它不是 Mira 的总入口路由；总入口由 loops/analysis-routing.md 处理。
  • 它不负责从零解释产业概念；如果输入是 GPU、ABF、HBM、存储 这类概念，先使用 industry-concept-analysis。
  • 它允许写技术面和事件面，但它们服务于 thesis，不单独形成交易系统。
  • 它不允许跳过 framework selection 直接套模板。
  • 它不允许用 overlay 替代主框架。

Quality Bar

  • 核心结论必须可回溯到来源
  • 事实、公司口径、承诺、指引、目标、预测、假设、观点和市场定价必须显式区分
  • evidence log 必须记录 claim_type、claim_text、source_speaker 和 verification_status
  • 每份 memo 必须有时效边界
  • 必须说明结论对应的时间跨度，且不能把短期财报信号自动外推成长期 thesis
  • 至少覆盖公司、财务、宏观、价格、事件五类视角中的三个
  • 必须解释为什么当前框架适配这只票
  • 必须指出如果框架错配，最可能错在哪里
  • 如果启用 overlay，必须解释它补充验证了什么
  • 如果使用 variant perception，必须给出可观察的 consensus proxy 和 falsification condition
  • 如果使用 long-term-multibagger，必须给出 target_return_path、implied_cagr、evidence_ladder、dilution_risk 和 kill_criteria
  • 如果启用 macro overlay，必须写明 macro_weight、dominant_macro_chain、market_pricing 和 macro_refresh_triggers
  • 如果启用 strategic-catalyst overlay，必须写明 catalyst_status、verification_path、what_would_confirm 和 what_would_disconfirm

© byteseek, 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

SKILL.md and 11 other files (references) in skills/equity-research-core of byteseek/Mira.

  • SKILL.md
  • references/commodity-overlay.md
  • references/framework-routing.md
  • references/large-mega.md
  • references/macro-overlay.md
  • references/micro-small.md
  • references/mid-cap.md
  • references/overlay-routing.md
  • references/strategic-catalyst-overlay.md
  • references/supply-chain-overlay.md
  • references/thesis-horizon-routing.md
  • references/valuation-expectation-overlay.md

Open the folder on GitHubat commit adddce7

Compare with similar skills

Equity Research Core 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.

Equity Research Core compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Equity Research Core this skillbyteseek/Mira275—~1.9kAutomated safety check: PassApache-2.0
Xvary Stock Researchsickn33/agentic-awesome-skills47k2 repos~952Automated safety check: PassMIT
Earnings AnalysisWind-Alice/AliceMarket1343 repos~2.2kAutomated safety check: PassNone
Catalyst ConfirmationSuperior-Trade/superior-skills215—~667Automated safety check: PassMIT
Research Conventionsginlix-ai/LangAlpha1.8k—~881Automated safety check: PassApache-2.0
Stock AnalysisPatrickSUDO/fadacai-portfolio142—~5.5kAutomated safety check: PassMIT

Similar skills

  • Xvary Stock Research

    sickn33/agentic-awesome-skills

    Thesis-driven equity analysis from public SEC EDGAR and market data; /analyze, /score, /compare workflows with bundled Python tools (Claude Code, Cursor, Codex).

    47k GitHub starsUsed in 2 repos~952 tokens
    Business, Finance & HRAuto-check passed

  • Earnings Analysis

    Wind-Alice/AliceMarket

    Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage.

    134 GitHub starsUsed in 3 repos~2.2k tokens
    Business, Finance & HRAuto-check passed

  • Catalyst Confirmation

    Superior-Trade/superior-skills

    A skill your agent uses when a Polymarket prediction-market thesis rests on an external event — CPI, Fed, elections, court rulings, ETF decisions — and needs market confirmation before committing.

    215 GitHub stars~667 tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed

  • Research Conventions

    ginlix-ai/LangAlpha

    The evidence, judgement, intake and market-data rules every research deliverable follows.

    1.8k GitHub stars~881 tokensUpdated yesterday
    Business, Finance & HRAuto-check passed

  • Stock Analysis

    PatrickSUDO/fadacai-portfolio

    Analyze a stock ticker with fundamentals, technicals, analyst ratings, and investment thesis.

    142 GitHub stars~5.5k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check passed

  • Investor Call Prep

    gooseworks-ai/goose-skills

    Prepare for investor calls by pulling upcoming meetings from Google Calendar, deeply researching each investor and their firm (website scraping, portfolio analysis, thesis extraction), checking for…

    1.2k GitHub starsUsed in 1 repo~3.8k tokens
    Business, Finance & HRAuto-check passed

More from byteseek/Mira

All 10 skills in this repo

  • Etf Listing Discovery

    byteseek/Mira

    Discover listed, pending, filed, or newly announced ETFs and create a structured candidate watchlist for ETF listing analysis.

    275 GitHub stars~887 tokensUpdated 1 mo ago
    Auto-check passed

  • Etf Listing Analysis

    byteseek/Mira

    Analyze new, pending, or expanding ETF products as product signals, exposure maps, demand indicators, and potential asset-pricing read-throughs.

    275 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Commodity Cycle Analysis

    byteseek/Mira

    Analyze commodity cycles, futures curves, inventories, cost curves, policy/geopolitics, positioning, and transmission into related assets.

    275 GitHub stars~3k tokensUpdated 1 mo ago
    Auto-check passed

  • Data Analysis Quality Gate

    byteseek/Mira

    Gate quantitative Mira conclusions by requiring reproducible data, formulas, calculation ledgers, or explicit downgrades when numbers drive judgment.

    275 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Earnings Report Analysis

    byteseek/Mira

    Analyze earnings releases, filings, transcripts, guidance, peer comparisons, market reaction, and thesis impact for a company reporting event.

    275 GitHub stars~2.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Industry Concept Analysis

    byteseek/Mira

    Map an unclear industry concept into boundaries, value chain, supply-demand mechanics, profit pools, evidence gaps, and investable candidates.

    275 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Equity Research Core

What does Equity Research Core do?

Run Mira's core single-equity research workflow across fundamentals, financial quality, macro context, technical pricing, events, and thesis framing. Equity Research Core is an agent skill from byteseek/Mira. Run Mira's core single-equity research workflow across fundamentals, financial quality, macro context, technical pricing, events, and thesis framing.

When should I use Equity Research Core?

Equity Research Core fits situations like: tasks that involve Stock and market analysis; tasks that involve Essays and academic help.

How do I install Equity Research Core in Claude Code?

Run `npx skills add byteseek/Mira --skill equity-research-core -a claude-code`. Or copy the skill folder (skills/equity-research-core in byteseek/Mira) into .claude/skills/equity-research-core in your project. Claude Code loads it when a task matches its description.

How do I install Equity Research Core in Codex?

Run `npx skills add byteseek/Mira --skill equity-research-core -a codex`. Or copy the skill folder (skills/equity-research-core in byteseek/Mira) into .agents/skills/equity-research-core in your project. Codex loads it when a task matches its description.

Can I use Equity Research Core 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 byteseek/Mira --skill equity-research-core -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/equity-research-core, .gemini/skills/equity-research-core, .github/skills/equity-research-core and .opencode/skills/equity-research-core in your project.

What does Equity Research Core need to run?

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

Does Equity Research Core 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 Equity Research Core 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 Equity Research Core use?

Equity Research Core 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 Equity Research Core use?

About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 17k tokens, read only when the agent opens those files.

What are the alternatives to Equity Research Core?

Skills that share tags, products or a category with Equity Research Core: Xvary Stock Research (sickn33/agentic-awesome-skills, 47k stars), Earnings Analysis (Wind-Alice/AliceMarket, 134 stars), Catalyst Confirmation (Superior-Trade/superior-skills, 215 stars) and Research Conventions (ginlix-ai/LangAlpha, 1.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Equity Research Core?

byteseek (a GitHub organization) maintains it in byteseek/Mira, which has 275 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 8, 2026.

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