Stock Analysis
24mlight/StockClaw
Analyze stocks and cryptocurrencies using Yahoo Finance data.
Analyze sell-side analyst estimates and how they are changing, using Yahoo Finance data (yfinance): EPS and revenue consensus by period, estimate ranges and dispersion, revision trends over…
Install Estimate Analysis
$ npx skills add himself65/finance-skills --skill estimate-analysis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install himself65/finance-skills estimate-analysis --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/himself65/finance-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/market-analysis/skills/estimate-analysis .claude/skills/estimate-analysis && rm -rf skills-srcUse ~/.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/
Install the "estimate-analysis" agent skill from https://github.com/himself65/finance-skills/tree/main/plugins/market-analysis/skills/estimate-analysis into .claude/skills/estimate-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "estimate-analysis", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/himself65/finance-skills/tree/main/plugins/market-analysis/skills/estimate-analysisType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add himself65/finance-skills --skill estimate-analysis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install himself65/finance-skills estimate-analysis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/himself65/finance-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/market-analysis/skills/estimate-analysis .agents/skills/estimate-analysis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "estimate-analysis" agent skill from https://github.com/himself65/finance-skills/tree/main/plugins/market-analysis/skills/estimate-analysis into .agents/skills/estimate-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "estimate-analysis", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add himself65/finance-skills --skill estimate-analysis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install himself65/finance-skills estimate-analysis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/himself65/finance-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/market-analysis/skills/estimate-analysis .cursor/skills/estimate-analysis && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "estimate-analysis" agent skill from https://github.com/himself65/finance-skills/tree/main/plugins/market-analysis/skills/estimate-analysis into .cursor/skills/estimate-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "estimate-analysis", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/himself65/finance-skills.git --path plugins/market-analysis/skills/estimate-analysis--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add himself65/finance-skills --skill estimate-analysis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install himself65/finance-skills estimate-analysis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/himself65/finance-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/market-analysis/skills/estimate-analysis .gemini/skills/estimate-analysis && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "estimate-analysis" agent skill from https://github.com/himself65/finance-skills/tree/main/plugins/market-analysis/skills/estimate-analysis into .gemini/skills/estimate-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "estimate-analysis", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install himself65/finance-skills estimate-analysisInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add himself65/finance-skills --skill estimate-analysis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/himself65/finance-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/market-analysis/skills/estimate-analysis .github/skills/estimate-analysis && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "estimate-analysis" agent skill from https://github.com/himself65/finance-skills/tree/main/plugins/market-analysis/skills/estimate-analysis into .github/skills/estimate-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "estimate-analysis", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add himself65/finance-skills --skill estimate-analysis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install himself65/finance-skills estimate-analysis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/himself65/finance-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/market-analysis/skills/estimate-analysis .opencode/skills/estimate-analysis && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "estimate-analysis" agent skill from https://github.com/himself65/finance-skills/tree/main/plugins/market-analysis/skills/estimate-analysis into .opencode/skills/estimate-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "estimate-analysis", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
estimate-analysis- GitHub stars
- 3.4k
- Token cost
- ~1.8k tokens
- SKILL.md length
- 748 words
- Files
- 3 (incl. references)
- Skills in repo
- 22
- Repo updated
- First seen
- Licence
- MIT
At a glance
Analyze sell-side analyst estimates and how they are changing, using Yahoo Finance data (yfinance): EPS and revenue consensus by period, estimate ranges and dispersion, revision trends over…
- Works in 5 steps: Ensure yfinance Is Available → Identify the Ticker and Gather Estimate… → Route Based on User Intent → …
- The user wants more than a single estimate lookup: estimate revisions
- SKILL.md covers Step 1: Ensure yfinance Is…, Step 2: Identify the Ticker…, Step 3: Route Based on User… and Step 4: Build the Estimate…, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Estimate Analysis is an agent skill from himself65/finance-skills. Analyze sell-side analyst estimates and how they are changing, using Yahoo Finance data (yfinance): EPS and revenue consensus by period, estimate ranges and dispersion, revision trends over 7/30/60/90 days and up/down revision breadth, growth estimates vs industry, sector, and the S&P 500, and historical estimate accuracy. Use this skill when the user wants more than a single estimate lookup: estimate revisions or momentum, EPS trend, consensus changes, forward or next-quarter and annual estimates, the bull vs…
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `README.md` and `references/api_reference.md`).
It sits in Business, Finance & HR, covering Stock and market analysis. It works with yfinance. The repository describes itself as: A collection of skills for AI financial analysis. The licence is MIT.
When your agent uses it
- The user wants more than a single estimate lookup: estimate revisions
- Consensus changes
- Next-quarter and annual estimates
- The bull vs bear estimate spread
Example prompts
- “/estimate-analysis”
Requirements
- Python 3
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 01fc7b4. 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 (its code samples are python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
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
Estimate Analysis loads about 1.8k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 148 tokens; SKILL.md has 748 words of instructions outside code blocks.
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 himself65/finance-skills at commit 01fc7b4, republished under its MIT licence (© himself65). 748 words, ~1,765 tokens.
Download SKILL.mdSave it as
.claude/skills/estimate-analysis/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- estimate-analysis
- description
- Analyze sell-side analyst estimates and how they are changing, using Yahoo Finance data (yfinance): EPS and revenue consensus by period, estimate ranges and dispersion, revision trends over 7/30/60/90 days and up/down revision breadth, growth estimates vs industry, sector, and the S&P 500, and historical estimate accuracy. Use this skill when the user wants more than a single estimate lookup: estimate revisions or momentum, EPS trend, consensus changes, forward or next-quarter and annual estimates, the bull vs bear estimate spread, or growth projections across periods.
Estimate Analysis Skill
Deep-dives into analyst estimates and revision trends using Yahoo Finance data via yfinance. Covers EPS and revenue estimate distributions, revision momentum, growth projections, and multi-period comparisons — the full picture of where the street thinks a company is heading.
Important: Data is for research and educational purposes only. Not financial advice. yfinance is not affiliated with Yahoo, Inc.
Step 1: Ensure yfinance Is Available
Current environment status:
!`python3 -c "exec('try:\n import yfinance\n print(\'yfinance \' + yfinance.__version__ + \' installed\')\nexcept Exception:\n print(\'YFINANCE_NOT_INSTALLED\')')"`If YFINANCE_NOT_INSTALLED, install it:
import subprocess, sys
subprocess.check_call([sys.executable, "-m", "pip", "install", "-q", "yfinance"])If already installed, skip to the next step.
Step 2: Identify the Ticker and Gather Estimate Data
Extract the ticker from the user's request. Fetch all estimate-related data in one script.
import yfinance as yf
import pandas as pd
ticker = yf.Ticker("AAPL") # replace with actual ticker
# --- Estimate data ---
earnings_est = ticker.earnings_estimate # EPS estimates by period
revenue_est = ticker.revenue_estimate # Revenue estimates by period
eps_trend = ticker.eps_trend # EPS estimate changes over time
eps_revisions = ticker.eps_revisions # Up/down revision counts
growth_est = ticker.growth_estimates # Growth rate estimates
# --- Historical context ---
earnings_hist = ticker.earnings_history # Track record
info = ticker.info # Company basics
quarterly_income = ticker.quarterly_income_stmt # Recent actualsWhat each data source provides
| Data Source | What It Shows | Why It Matters |
|---|---|---|
earnings_estimate | Current EPS consensus by period (0q, +1q, 0y, +1y) | The estimate levels — what analysts expect |
revenue_estimate | Current revenue consensus by period | Top-line expectations |
eps_trend | How the EPS estimate has changed (7d, 30d, 60d, 90d ago) | Revision direction — rising or falling expectations |
eps_revisions | Count of upward vs downward revisions (7d, 30d) | Revision breadth — are most analysts raising or cutting? |
growth_estimates | Growth rate estimates vs peers and sector | Relative positioning |
earnings_history | Actual vs estimated for last 4 quarters | Calibration — how good are these estimates historically? |
Step 3: Route Based on User Intent
Match the depth of the analysis to the question:
| User Request | Focus Area | Key Sections |
|---|---|---|
| General estimate analysis | Full analysis | All sections |
| "How have estimates changed" | Revision trends | EPS Trend + Revisions |
| "What are analysts expecting" | Current consensus | Estimate overview |
| "Growth estimates" | Growth projections | Growth Estimates |
| "Bull vs bear case" | Estimate range | High/low spread analysis |
| Compare estimates across periods | Multi-period | Period comparison table |
A general request gets the full analysis; a narrow question gets the matching sections.
Step 4: Build the Estimate Analysis
Section 1: Estimate Overview
Present the current consensus for every available period (0q, +1q, 0y, +1y) from earnings_estimate and revenue_estimate: consensus, low, high, range width (as a % of consensus), analyst count, and YoY growth. Flag:
- Range width — ranges wider than 15% of consensus signal high uncertainty
- Analyst coverage — fewer than 5 analysts means thin coverage
- Growth trajectory — whether growth accelerates or decelerates across periods
Section 2: Revision Trends (EPS Trend)
Often the most actionable section. From eps_trend, show each period's current estimate against its value 7, 30, 60, and 90 days ago, and summarize the direction and whether the recent moves are accelerating.
How to read it:
- Rising estimates ahead of earnings = positive setup (the bar is rising)
- Falling estimates = analysts cutting numbers, often a negative signal
- Flat estimates = no new information being priced in
- Recent acceleration or deceleration matters more than the total move
Show full SKILL.md (313 more words)Show less
Section 3: Revision Breadth (EPS Revisions)
From eps_revisions, show up vs down revision counts over the last 7 and 30 days for each period, and the revision ratio Up / (Up + Down). Ratios above 0.7 are strongly bullish; below 0.3 are bearish.
Section 4: Growth Estimates
From growth_estimates, compare the company's expected growth for each period (and its past 5-year annual growth) with its industry, sector, and the S&P 500, and say whether it is expected to grow faster or slower than its peers.
Section 5: Historical Estimate Accuracy
From earnings_history, show estimate vs actual EPS and the surprise % for the last four quarters, then assess:
- Beat rate — how many of the four quarters beat
- Average surprise — magnitude and direction
- Trend in surprise — are beats getting bigger or smaller? A shrinking surprise with rising estimates can mean the bar is catching up to reality.
Step 5: Synthesize and Respond
Lead with the key insight — the direction and breadth of revisions across periods — then show the tables for the sections the user cares about. Interpret rather than just tabulate: does the revision trend confirm or contradict the stock's recent price action, how does the growth outlook compare with what the current P/E prices in, and what does the estimate-accuracy history say about today's consensus?
Flag the nuances that apply: estimates cluster around consensus, so the real distribution of outcomes is wider than low/high suggests; revision momentum can reverse on a single guidance change or macro event; Yahoo Finance estimates can lag real-time consensus providers by hours or days; out-year (+1y) estimates are inherently less reliable. Close with the standing caveats: analyst estimates reflect a consensus view, not certainty; revisions are a signal, not a guarantee; this is not financial advice.
Reference Files
references/api_reference.md— Detailed yfinance API reference for all estimate-related methods
Read the reference file when you need exact return formats or edge case handling.
© himself65, MIT. 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 2 other files (references) in plugins/market-analysis/skills/estimate-analysis of himself65/finance-skills.
- SKILL.md
- README.md
- references/api_reference.md
Open the folder on GitHubat commit 01fc7b4
Compare with similar skills
Estimate Analysis 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Estimate Analysis this skillhimself65/finance-skills | 3.4k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Stock Analysis24mlight/StockClaw | 101 | 2 repos | ~2k | Automated safety check: Notes | MIT | |
| Regimejackson-video-resources/markov-hedge-fund-method | 483 | — | ~1.6k | Automated safety check: Pass | Custom licence | |
| Stock Value AnalyzerFunnyKun/stock-value-analyzer | 139 | — | ~3.3k | Automated safety check: Pass | None | |
| Yahoo Finance24mlight/StockClaw | 101 | 2 repos | ~1.1k | Automated safety check: Notes | MIT | |
| Stock Analysisliusai0820/Stock-Analysis-Skill | 142 | — | ~904 | Automated safety check: Notes | None |
Similar skills
Regime
jackson-video-resources/markov-hedge-fund-method
Detect the market regime (Bull / Bear / Sideways) for ANY asset and turn it into a tradeable signal or a risk filter.
Stock Value Analyzer
FunnyKun/stock-value-analyzer
基于邱国鹭《投资中最简单的事》方法论的股票价值分析器（v2.0 双层架构）。通过"三好原则"（好行业、好公司、好价格）系统评估一只股票是否值得投资。v2.0 在原定性框架之上注入一套可量化、可复现的硬模型层——反向 DCF 反解市场隐含增速、情景概率加权估值、EPV 盈利能力价值、分行业估值路由、杜邦三/五因子分解、ROIC vs WACC、Piotroski F-Score、Beneish…
Yahoo Finance
24mlight/StockClaw
Get stock prices, quotes, fundamentals, earnings, options, dividends, and analyst ratings using Yahoo Finance.
Stock Analysis
liusai0820/Stock-Analysis-Skill
股票智能分析技能。输入股票代码（A股/港股/美股），自动完成： 1. An agent skill from liusai0820/Stock-Analysis-Skill.
B3 Analysis
guhcostan/b3analysis
Load this skill when analyzing Brazilian stocks listed on B3, building investment portfolios with Brazilian equities, or interpreting data from yfinance, BCB API, and Google News PT-BR.
More from himself65/finance-skills
All 22 skills in this repoCompany Valuation
himself65/finance-skills
Estimate a public company's intrinsic value with DCF, relative (peer multiple), and sum-of-the-parts (SOTP) methods, then blend them into an implied share price with upside/downside vs the market…
Discord Reader
himself65/finance-skills
Read Discord for financial research through opencli connected to the Discord desktop app: servers, channels, members, recent messages in the active channel, and message search.
Earnings Preview
himself65/finance-skills
Build a pre-earnings briefing for a stock from Yahoo Finance data (yfinance): the upcoming report date and timing, consensus EPS and revenue estimates with their range, the beat/miss track record…
Earnings Recap
himself65/finance-skills
Analyze a company's most recent (or a specified past) earnings report from Yahoo Finance data (yfinance): actual vs estimated EPS, surprise size, revenue and margin trends, and the stock's price…
Fintel Data
himself65/finance-skills
Query Fintel (fintel.io) institutional market data through its REST API or official MCP server.
Generative UI
himself65/finance-skills
Design system and templates for Claude's built-in generative UI — the showwidget tool that renders interactive HTML/SVG widgets inline in claude.ai conversations.
Related
Works with
Categories
Questions about Estimate Analysis
What does Estimate Analysis do?
Analyze sell-side analyst estimates and how they are changing, using Yahoo Finance data (yfinance): EPS and revenue consensus by period, estimate ranges and dispersion, revision trends over…. Estimate Analysis is an agent skill from himself65/finance-skills. Analyze sell-side analyst estimates and how they are changing, using Yahoo Finance data (yfinance): EPS and revenue consensus by period, estimate ranges and dispersion, revision trends over 7/30/60/90 days and up/down revision breadth, growth estimates vs industry, sector, and the S&P 500, and historical estimate accuracy.
When should I use Estimate Analysis?
Estimate Analysis fits situations like: the user wants more than a single estimate lookup: estimate revisions; consensus changes; Next-quarter and annual estimates; the bull vs bear estimate spread.
How do I install Estimate Analysis in Claude Code?
Run `npx skills add himself65/finance-skills --skill estimate-analysis -a claude-code`. Or copy the skill folder (plugins/market-analysis/skills/estimate-analysis in himself65/finance-skills) into .claude/skills/estimate-analysis in your project. Claude Code loads it when a task matches its description.
How do I install Estimate Analysis in Codex?
Run `npx skills add himself65/finance-skills --skill estimate-analysis -a codex`. Or copy the skill folder (plugins/market-analysis/skills/estimate-analysis in himself65/finance-skills) into .agents/skills/estimate-analysis in your project. Codex loads it when a task matches its description.
Can I use Estimate Analysis 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 himself65/finance-skills --skill estimate-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/estimate-analysis, .gemini/skills/estimate-analysis, .github/skills/estimate-analysis and .opencode/skills/estimate-analysis in your project.
What does Estimate Analysis need to run?
SKILL.md names no scripts, command-line tools or credentials: Estimate Analysis is instructions for the agent only. Our summary lists: Python 3.
Does Estimate Analysis access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Estimate Analysis 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 Estimate Analysis use?
Estimate Analysis is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Estimate Analysis use?
About 1.8k tokens (SKILL.md is roughly 7.1k 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 1.3k tokens, read only when the agent opens those files.
What are the alternatives to Estimate Analysis?
Skills that share tags, products or a category with Estimate Analysis: Stock Analysis (24mlight/StockClaw, 101 stars), Regime (jackson-video-resources/markov-hedge-fund-method, 483 stars), Stock Value Analyzer (FunnyKun/stock-value-analyzer, 139 stars) and Yahoo Finance (24mlight/StockClaw, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Estimate Analysis?
himself65 (a GitHub user) maintains it in himself65/finance-skills, which has 3,382 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 5, 2026.
Source: himself65/finance-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.