Presentations
asgeirtj/system_prompts_leaks
Help choose a presentation's audience, story, outline, or use of evidence and visuals.
Agent skill
Jep Evidence Without Equations
by brycewang-stanford in brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when presenting empirical or theoretical evidence credibly in a Journal of Economic Perspectives (JEP) article with minimal math — intuition, examples, well-chosen numbers…
MITAuto-check passed
Install Jep Evidence Without Equations
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill jep-evidence-without-equations -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills jep-evidence-without-equations --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/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations .claude/skills/jep-evidence-without-equations && 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 "jep-evidence-without-equations" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations into .claude/skills/jep-evidence-without-equations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jep-evidence-without-equations", 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/brycewang-stanford/Awesome-Journal-Skills/tree/main/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equationsType 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 brycewang-stanford/Awesome-Journal-Skills --skill jep-evidence-without-equations -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills jep-evidence-without-equations --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations .agents/skills/jep-evidence-without-equations && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "jep-evidence-without-equations" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations into .agents/skills/jep-evidence-without-equations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jep-evidence-without-equations", 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 brycewang-stanford/Awesome-Journal-Skills --skill jep-evidence-without-equations -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills jep-evidence-without-equations --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations .cursor/skills/jep-evidence-without-equations && 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 "jep-evidence-without-equations" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations into .cursor/skills/jep-evidence-without-equations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jep-evidence-without-equations", 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/brycewang-stanford/Awesome-Journal-Skills.git --path Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations--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 brycewang-stanford/Awesome-Journal-Skills --skill jep-evidence-without-equations -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills jep-evidence-without-equations --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations .gemini/skills/jep-evidence-without-equations && 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 "jep-evidence-without-equations" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations into .gemini/skills/jep-evidence-without-equations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jep-evidence-without-equations", 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 brycewang-stanford/Awesome-Journal-Skills jep-evidence-without-equationsInstalls 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 brycewang-stanford/Awesome-Journal-Skills --skill jep-evidence-without-equations -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations .github/skills/jep-evidence-without-equations && 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 "jep-evidence-without-equations" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations into .github/skills/jep-evidence-without-equations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jep-evidence-without-equations", 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 brycewang-stanford/Awesome-Journal-Skills --skill jep-evidence-without-equations -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills jep-evidence-without-equations --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations .opencode/skills/jep-evidence-without-equations && 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 "jep-evidence-without-equations" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations into .opencode/skills/jep-evidence-without-equations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jep-evidence-without-equations", 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
jep-evidence-without-equations- GitHub stars
- 1.2k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 688 words
- Files
- 1
- Skills in repo
- 2,387
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when presenting empirical or theoretical evidence credibly in a Journal of Economic Perspectives (JEP) article with minimal math — intuition, examples, well-chosen numbers…
- Presenting empirical
- SKILL.md covers When to trigger, The JEP evidence bar, How to present evidence… and Honesty devices (build…, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Theoretical evidence credibly in a Journal of Economic Perspectives (JEP) article with minimal math — intuition
What it does
Jep Evidence Without Equations is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when presenting empirical or theoretical evidence credibly in a Journal of Economic Perspectives (JEP) article with minimal math — intuition, examples, well-chosen numbers, and honest caveats. Handles how evidence is conveyed in prose; defer figures/tables to jep-exhibits-for-general-readers and fairness across studies to jep-balance-and-objectivity.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的… The licence is MIT.
When your agent uses it
- Presenting empirical
- Theoretical evidence credibly in a Journal of Economic Perspectives (JEP) article with minimal math — intuition
- Well-chosen numbers
Example prompts
- “/jep-evidence-without-equations”
What it can do on your machine
Read from SKILL.md and the folder at commit 932eb23. 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
Jep Evidence Without Equations loads about 1.3k tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 688 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 brycewang-stanford/Awesome-Journal-Skills at commit 932eb23, republished under its MIT licence (© brycewang-stanford). 688 words, ~1,339 tokens.
Download SKILL.mdSave it as
.claude/skills/jep-evidence-without-equations/SKILL.md (or your agent's skills folder).- name
- jep-evidence-without-equations
- description
- Use when presenting empirical or theoretical evidence credibly in a Journal of Economic Perspectives (JEP) article with minimal math — intuition, examples, well-chosen numbers, and honest caveats. Handles how evidence is conveyed in prose; defer figures/tables to jep-exhibits-for-general-readers and fairness across studies to jep-balance-and-objectivity.
Evidence Without Equations (jep-evidence-without-equations)
When to trigger
- You need to convince a reader of a finding without a regression table in the body
- The draft leans on "significant at the 1% level" or coefficient dumps to make its case
- You have many numbers and aren't sure which few to feature
- You worry that going light on math will make the evidence look soft
The JEP evidence bar
JEP communicates evidence through intuition, well-chosen numbers, and honest caveats, not through equations and estimation tables in the body. The credibility comes from which evidence you feature, how clearly you convey magnitude, and how honestly you state limits — not from displaying machinery. A JEP reader should finish a paragraph knowing the size of an effect, how sure the field is, and what could be wrong.
How to present evidence credibly with little math
- Lead with magnitude in plain units. "Roughly a third of the cost is passed through to prices" beats a coefficient. Translate elasticities/log points into amounts a reader feels (dollars, percentage points, days).
- Pick a few load-bearing numbers. Two or three vivid, well-sourced figures land; a wall of estimates does not. Each featured number should earn its place in the argument.
- Convey precision plainly. Instead of asterisks, say how settled it is: "estimates cluster between 5% and 8%," or "studies disagree, ranging from near zero to large." Give the reader a sense of the range, not a star.
- Use examples and analogies. A concrete case or a familiar analogy makes a mechanism stick where a model would not.
- Characterize the body of evidence, not one study. "A dozen studies across countries find…" is more JEP than "Smith (2019) estimates…". Synthesis means describing the weight and consistency of evidence.
- State caveats in the same breath. "This holds for short horizons; over decades the evidence thins" builds trust and is the JEP norm.
Honesty devices (build credibility without machinery)
- Name the identification in words, once. A reader should know why a number is believable (a natural experiment, a long literature, a clean comparison) without seeing the design.
- Distinguish settled from contested. Tell the reader what is consensus, what is debated, and what is unknown — this is also the bridge to
jep-balance-and-objectivity. - Flag external validity. Say where a result travels and where it likely doesn't.
- Avoid false precision. "About 6%" is more honest than "6.23%" when the range is wide.
- Anchor with a benchmark. A number means more next to a familiar reference point: "about the size of a typical recession's effect on employment," or "roughly a month's rent." Benchmarks let a non-specialist judge whether an effect is big or small.
Show full SKILL.md (251 more words)Show less
Checklist
- Effect sizes given in plain, feelable units (not raw coefficients)
- Only a few load-bearing numbers featured, each well-sourced
- Precision conveyed as ranges / degree of agreement, never asterisks
- Evidence characterized as a body (weight, consistency), not one study
- Identification/credibility explained in words, once, not displayed
- Caveats and external-validity limits stated alongside the claims
- Key magnitudes anchored against a familiar benchmark
- No false precision; magnitudes rounded to what the evidence supports
Worked vignette (illustrative)
A draft says: "The treatment effect is 0.184 log points (s.e. 0.061), significant at the 1% level (***)." A JEP rewrite drops the asterisks and the raw coefficient: "Workers in the program earned about 20% more a year later — an effect large enough to matter for a household budget, and one that a dozen studies in different settings find consistently, though the gains fade after a few years." The reader now has magnitude in feelable units, a sense of how settled it is (many consistent studies), and the key caveat (fading) — all without an equation or a star.
Anti-patterns
- A regression table or estimating equation in the body to "prove" a point
- "Significant at the 1% level" (and asterisks) standing in for magnitude and precision
- A blizzard of numbers with no hierarchy — the reader can't tell which matter
- Citing a single study as if it settled a question (synthesis means weighing many)
- Hiding caveats to make the evidence look stronger (a balance and an honesty failure)
- False precision ("6.23%") that overstates how much the field actually knows
Output format
【Headline magnitude (plain units)】[...]
【Load-bearing numbers (≤3)】1) … 2) … 3) … (sources)
【Precision conveyed as】[range / degree of agreement]
【Why believable (in words)】[natural experiment / long literature / clean comparison]
【Caveats + external validity】[...]
【Body of evidence framed?】many studies vs. one: [Y/N]
【Next step】jep-exhibits-for-general-readers© brycewang-stanford, MIT. 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 Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Jep Evidence Without Equations 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 |
|---|---|---|---|---|---|---|
| Jep Evidence Without Equations this skillbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Presentationsasgeirtj/system_prompts_leaks | 69k | — | ~858 | Automated safety check: Pass | CC0-1.0 | |
| PresentationRightNow-AI/openfang | 18k | — | ~829 | Automated safety check: Pass | Apache-2.0 | |
| AI Presenter VideoNousResearch/hermes-agent | 253k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Kortix Presentationkortix-ai/suna | 20k | — | ~3k | Automated safety check: Pass | Custom licence | |
| Presentation Styling Referenceshanraisshan/claude-code-best-practice | 67k | — | ~780 | Automated safety check: Pass | MIT |
Similar skills
Presentation
RightNow-AI/openfang
Presentation expert for slide structure, storytelling, visual design, and audience engagement
AI Presenter Video
NousResearch/hermes-agent
Produces a presenter-led video from a topic or script plus one authorized presenter image, with captions, lip-sync checks and acceptance reports.
Kortix Presentation
kortix-ai/suna
Recipe: build, edit, present or record a Kortix deck or film (a Next.js route under /presentations in apps/web, never a file).
Presentation Styling Reference
shanraisshan/claude-code-best-practice
Reference for the CSS classes, HTML slide patterns and code-block highlighting spans used in a project's presentation/index.html slide deck.
Twenty Record Presentation
twentyhq/twenty
Retrieves Twenty CRM records through the connected MCP server and presents them as readable summaries or tables with working record links instead of raw API output.
More from brycewang-stanford/Awesome-Journal-Skills
All 2,387 skills in this repoAaag Data Analysis
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when running and reporting the analysis for an Annals of the American Association of Geographers manuscript — spatial statistics and modeling, remote-sensing accuracy, or…
Aaag Literature Positioning
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when positioning an Annals of the American Association of Geographers manuscript in the literature — engaging geographic scholarship across the relevant area and the…
Aaag Rebuttal
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when responding to an Annals of the American Association of Geographers decision letter (major/minor revision) — building a point-by-point response to the subject editor and…
Aaag Research Design
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when defending the research design of an Annals of the American Association of Geographers manuscript — spatial/quantitative analysis and GIScience, remote-sensing and…
Aaag Review Process
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript — double-anonymous review routed through a subject editor by…
Aaag Submission
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when running the final pre-submission preflight for the Annals of the American Association of Geographers via ScholarOne Manuscripts — area/article-type selection…
Questions about Jep Evidence Without Equations
What does Jep Evidence Without Equations do?
A skill your agent uses when presenting empirical or theoretical evidence credibly in a Journal of Economic Perspectives (JEP) article with minimal math — intuition, examples, well-chosen numbers…. Jep Evidence Without Equations is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when presenting empirical or theoretical evidence credibly in a Journal of Economic Perspectives (JEP) article with minimal math — intuition, examples, well-chosen numbers, and honest caveats.
When should I use Jep Evidence Without Equations?
Jep Evidence Without Equations fits situations like: presenting empirical; theoretical evidence credibly in a Journal of Economic Perspectives (JEP) article with minimal math — intuition; well-chosen numbers.
How do I install Jep Evidence Without Equations in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill jep-evidence-without-equations -a claude-code`. Or copy the skill folder (Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/jep-evidence-without-equations in your project. Claude Code loads it when a task matches its description.
How do I install Jep Evidence Without Equations in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill jep-evidence-without-equations -a codex`. Or copy the skill folder (Journal-of-Economic-Perspectives-Skills/skills/jep-evidence-without-equations in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/jep-evidence-without-equations in your project. Codex loads it when a task matches its description.
Can I use Jep Evidence Without Equations 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 brycewang-stanford/Awesome-Journal-Skills --skill jep-evidence-without-equations -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jep-evidence-without-equations, .gemini/skills/jep-evidence-without-equations, .github/skills/jep-evidence-without-equations and .opencode/skills/jep-evidence-without-equations in your project.
What does Jep Evidence Without Equations need to run?
SKILL.md names no scripts, command-line tools or credentials: Jep Evidence Without Equations is instructions for the agent only.
Does Jep Evidence Without Equations 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 Jep Evidence Without Equations 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 Jep Evidence Without Equations use?
Jep Evidence Without Equations 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 Jep Evidence Without Equations use?
About 1.3k tokens (SKILL.md is roughly 5.4k 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 Jep Evidence Without Equations?
Skills that share tags, products or a category with Jep Evidence Without Equations: Presentations (asgeirtj/system_prompts_leaks, 69k stars), Presentation (RightNow-AI/openfang, 18k stars), AI Presenter Video (NousResearch/hermes-agent, 253k stars) and Kortix Presentation (kortix-ai/suna, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Jep Evidence Without Equations?
brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,231 GitHub stars. The repository holds 2,387 skills in this directory. The repository was last updated on September 27, 2026.
Source: brycewang-stanford/Awesome-Journal-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.