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

Jmcb Robustness

by brycewang-stanford in brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when a Journal of Money, Credit and Banking (JMCB) result may be specification-, sample-, or inference-sensitive and you need to plan checks that each kill a specific threat.

MITAuto-check passedResearch & Science

Install Jmcb Robustness

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill jmcb-robustness -a claude-code

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills jmcb-robustness --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/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Journal-of-Money-Credit-and-Banking-Skills/skills/jmcb-robustness .claude/skills/jmcb-robustness && 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
jmcb-robustness
GitHub stars
1.2k
Token cost
~2.1k tokens
SKILL.md length
1,014 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a Journal of Money, Credit and Banking (JMCB) result may be specification-, sample-, or inference-sensitive and you need to plan checks that each kill a specific threat.

  • Works in 4 steps: Lead with the threats a JMCB referee… → For each, show the headline magnitude… → Put the 3–4 load-bearing checks in the… → …
  • A Journal of Money
  • SKILL.md covers When to trigger, The JMCB robustness logic, Threat → check map (build… and How to present it, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Jmcb Robustness is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when a Journal of Money, Credit and Banking (JMCB) result may be specification-, sample-, or inference-sensitive and you need to plan checks that each kill a specific threat. Builds a threat-mapped robustness suite; it does not re-run the core identification or write the prose.

Its SKILL.md is about 2.1k 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 Research & Science. 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

  • A Journal of Money
  • Credit and Banking (JMCB) result may be specification-
  • Inference-sensitive and you need to plan checks that each kill a specific threat

Example prompts

  • “/jmcb-robustness”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Lead with the threats a JMCB referee will actually raise, ordered by how damaging they would be if true.
  2. For each, show the headline magnitude next to the baseline so the reader sees stability (or honest movement), not just significance…
  3. Put the 3–4 load-bearing checks in the main text; relegate the long tail to the online appendix with a pointer (see jmcb-internet-appendix).
  4. Where a check does move the result, say so and interpret it — a transparent boundary is more credible than a uniform table of survivors.

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

Jmcb Robustness loads about 2.1k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 1,014 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

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). 1,014 words, ~2,140 tokens.

Download SKILL.mdSave it as .claude/skills/jmcb-robustness/SKILL.md (or your agent's skills folder).
name
jmcb-robustness
description
Use when a Journal of Money, Credit and Banking (JMCB) result may be specification-, sample-, or inference-sensitive and you need to plan checks that each kill a specific threat. Builds a threat-mapped robustness suite; it does not re-run the core identification or write the prose.

Robustness Strategy (jmcb-robustness)

When to trigger

  • The headline (an IRF, an elasticity, a counterfactual welfare number) might flip under nearby choices
  • A referee will ask "is this the recursion ordering / lag length / sample window talking?"
  • Standard errors look too tight for a bank×time panel or for serially correlated macro data
  • The result depends on one regime (a crisis, the ZLB) and you have not shown sub-sample stability
  • You have a pile of "robustness" tables but cannot say which threat each one rules out

The JMCB robustness logic

JMCB referees do not reward a wall of additional regressions; they reward checks that are mapped to a named threat to the specific identification. A robustness suite is a list of "the result could be wrong because X — here is the check that rules out X." Given the journal's monetary/banking focus, the recurring threats are: shock contamination, specification dependence (lags, ordering, controls), inference understatement on panels and serially correlated series, and regime/sample instability around crises and policy transitions.

Threat → check map (build yours from this)

Named threatDiagnostic / check
Shock is contaminated (information effect, anticipation)Re-identify with info-robust surprises; orthogonalize to forecast revisions; placebo on pre-announcement windows
SVAR result is ordering-/restriction-drivenVary recursive ordering; alternative sign-restriction sets; report the full identified set
IRF is lag-length / horizon dependentVary VAR lags; local-projection vs. VAR; alternative horizons
Panel SEs understatedTwo-way (bank and time) clustering; wild-cluster bootstrap with few clusters; Driscoll–Kraay for cross-sectional dependence
Result is one-regime (crisis/ZLB) artifactSplit pre/post-2008, exclude crisis, exclude ZLB; state-dependent specification
Demand contamination (micro-banking)Tighter fixed effects (firm×time); single-bank-firm vs. multi-bank-firm subsample
Controls are doing the workSequentially add controls (Oster-style movement check); show coefficient stability
Outliers / measurementAlternative winsorizing; drop largest institutions; alternative variable definitions

How to present it

  1. Lead with the threats a JMCB referee will actually raise, ordered by how damaging they would be if true.
  2. For each, show the headline magnitude next to the baseline so the reader sees stability (or honest movement), not just significance survival.
  3. Put the 3–4 load-bearing checks in the main text; relegate the long tail to the online appendix with a pointer (see jmcb-internet-appendix).
  4. Where a check does move the result, say so and interpret it — a transparent boundary is more credible than a uniform table of survivors.

Inference deserves its own pass

For JMCB's two dominant data shapes, the default standard errors are usually wrong in a predictable direction:

  • Bank/firm panels: a single dimension of clustering understates uncertainty when shocks are common across units within a period. Cluster on both the cross-sectional unit (bank/firm) and time; with few clusters in either dimension, use the wild-cluster bootstrap (Cameron–Gelbach–Miller). If cross-sectional dependence is plausible, report Driscoll–Kraay as a complement.
  • Macro time series / local projections: serially correlated errors require HAR/Newey–West or lag-augmentation; for VARs, report bootstrap or bias-corrected bands rather than asymptotic ones at short samples.

State the clustering/inference choice once, prominently, and show the headline survives a reasonable alternative — referees treat a casual one-way-clustered SE as a red flag.

Crisis and regime stability is not optional for long samples

Many JMCB samples straddle the 2008 crisis, the ZLB/QE era, and post-Basel-III regulation. A result that holds only because one of these episodes dominates the variation is fragile. Show the headline in pre/post sub-samples, excluding the crisis window, and — where the mechanism plausibly changes at the bound — in a state-dependent specification (e.g., interacting the shock with a ZLB or high-uncertainty indicator). If the effect genuinely is regime-specific, that is itself a finding; report it as one rather than letting it masquerade as a general result.

Show full SKILL.md (417 more words)Show less

Execution bridge (StatsPAI / Stata MCP)

Run the battery, don't just enumerate it. Full map: execution-with-mcp. JMCB is monetary/banking — macro time series + bank panels; local projections for the macro lane, DiD/IV for the bank lane.

  • Many outcomes / specifications: romano_wolf (step-down FWER) or benjamini_hochberg.
  • OVB sensitivity: oster_delta / sensemakr.
  • Inference: wild_cluster_bootstrap (few clusters), twoway_cluster / conley.
  • Re-fit off one handle: audit_result(result_id) lists missing checks + the exact suggest_function for each.
  • Exhibits: etable / did_summary_to_latex from the handle — no retyped numbers.

Decisive checks in the body, exhaustive battery in the appendix. JF execution walkthrough.

Checklist

  • Each robustness check is tied to a named threat to this identification
  • Inference re-examined: clustering dimensions correct; few-cluster and serial-correlation handled
  • Specification dependence shown (ordering/lags/horizon/controls) with magnitudes side by side
  • Sub-sample / regime stability shown (crisis, ZLB, policy transition) if the period spans one
  • Micro-banking: demand-contamination check via tighter fixed effects or single-vs-multi-bank firms
  • Load-bearing checks in main text; long tail in the online appendix with a map
  • Any check that moves the result is reported and interpreted, not hidden

Anti-patterns

  • A robustness section that adds controls and reports "still significant" without showing the magnitude
  • Twenty appendix tables with no statement of which threat each addresses
  • Reporting only the checks that survive and quietly dropping the ones that did not
  • Leaving panel SEs one-way clustered when shocks are common across banks in a period
  • Claiming generality from a single regime without a crisis/ZLB sub-sample
  • Treating statistical-significance survival as the bar when the question is magnitude stability

Don't over-test: a focused suite beats an exhaustive one

A robustness section that runs every permutation signals uncertainty, not rigor. Pick the checks that map to the objections a JMCB referee will actually raise (shock cleanliness, demand contamination, inference, regime stability) and present those in the body with magnitudes side by side. Everything else — alternative winsorization thresholds, dozens of control permutations — goes to the online appendix with a one-line summary in text. The goal is to show the headline is stable where it matters, not to bury the reader.

Worked vignette (illustrative)

An SVAR finds a contractionary monetary shock raises credit spreads. A referee suspects the recursive ordering. The threat-mapped response: re-estimate under three alternative orderings and a sign-restricted scheme, plot the IRFs together, and show the peak spread response stays in a 15–22bp band across all of them (illustrative). One check — using revised instead of real-time data — does shift the peak; the authors report it and argue the real-time version is the policy-relevant one. That honesty reads as strength at JMCB.

Output format

text
【Journal】Journal of Money, Credit and Banking
【Skill】jmcb-robustness
【Top threats】ranked list of what could make the headline wrong
【Threat → check】each check mapped to the threat it rules out
【Inference fix】clustering dims / few-cluster / serial-correlation handling
【Regime stability】crisis / ZLB / transition sub-samples
【Main vs appendix】load-bearing checks in text; tail mapped to online appendix
【Honest movement】any check that shifts the result + interpretation
【Next skill】jmcb-tables-figures

© 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-Money-Credit-and-Banking-Skills/skills/jmcb-robustness of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Jmcb Robustness 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.

Jmcb Robustness compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jmcb Robustness this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~2.1kAutomated safety check: PassMIT
Hypothesis Generationspacering-net/codeg3.9k14 repos~3.6kAutomated safety check: NotesMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Nature Paper CardYuan1z0825/nature-skills47k2 repos~2.1kAutomated safety check: PassApache-2.0
Content Research Writerweapp-tailwindcss/weapp-tailwindcss1.9k25 repos~3.5kAutomated safety check: PassMIT
Peer Reviewspacering-net/codeg3.9k17 repos~5.9kAutomated safety check: NotesMIT

Similar skills

  • Hypothesis Generation

    spacering-net/codeg

    Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.

    3.9k GitHub starsUsed in 14 repos~3.6k tokens
    Research & ScienceAuto-check: notes

  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed

  • Nature Paper Card

    Yuan1z0825/nature-skills

    Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.

    47k GitHub starsUsed in 2 repos~2.1k tokens
    Research & ScienceAuto-check passed

  • Content Research Writer

    weapp-tailwindcss/weapp-tailwindcss

    Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section.

    1.9k GitHub starsUsed in 25 repos~3.5k tokens
    Research & ScienceAuto-check passed

  • Peer Review

    spacering-net/codeg

    Structured manuscript/grant review with checklist-based evaluation.

    3.9k GitHub starsUsed in 17 repos~5.9k tokens
    Research & ScienceAuto-check: notes

  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.9k tokensUpdated yesterday
    Research & ScienceAuto-check: notes

More from brycewang-stanford/Awesome-Journal-Skills

All 2,387 skills in this repo

  • Aaag 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…

    1.2k GitHub stars~1.3k tokensUpdated 12 days ago
    Auto-check passed

  • 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…

    1.2k GitHub stars~1.3k tokensUpdated 12 days ago
    Auto-check passed

  • 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…

    1.2k GitHub stars~1.4k tokensUpdated 12 days ago
    Auto-check passed

  • 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…

    1.2k GitHub stars~1.4k tokensUpdated 12 days ago
    Auto-check passed

  • 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…

    1.2k GitHub stars~1.3k tokensUpdated 12 days ago
    Auto-check passed

  • 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…

    1.2k GitHub stars~1.6k tokensUpdated 12 days ago
    Auto-check passed

Categories

Questions about Jmcb Robustness

What does Jmcb Robustness do?

A skill your agent uses when a Journal of Money, Credit and Banking (JMCB) result may be specification-, sample-, or inference-sensitive and you need to plan checks that each kill a specific threat. Jmcb Robustness is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when a Journal of Money, Credit and Banking (JMCB) result may be specification-, sample-, or inference-sensitive and you need to plan checks that each kill a specific threat.

When should I use Jmcb Robustness?

Jmcb Robustness fits situations like: A Journal of Money; credit and Banking (JMCB) result may be specification-; inference-sensitive and you need to plan checks that each kill a specific threat.

How do I install Jmcb Robustness in Claude Code?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill jmcb-robustness -a claude-code`. Or copy the skill folder (Journal-of-Money-Credit-and-Banking-Skills/skills/jmcb-robustness in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/jmcb-robustness in your project. Claude Code loads it when a task matches its description.

How do I install Jmcb Robustness in Codex?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill jmcb-robustness -a codex`. Or copy the skill folder (Journal-of-Money-Credit-and-Banking-Skills/skills/jmcb-robustness in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/jmcb-robustness in your project. Codex loads it when a task matches its description.

Can I use Jmcb Robustness 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 jmcb-robustness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jmcb-robustness, .gemini/skills/jmcb-robustness, .github/skills/jmcb-robustness and .opencode/skills/jmcb-robustness in your project.

What does Jmcb Robustness need to run?

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

Does Jmcb Robustness 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 Jmcb Robustness 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 Jmcb Robustness use?

Jmcb Robustness 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 Jmcb Robustness use?

About 2.1k tokens (SKILL.md is roughly 8.6k 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 Jmcb Robustness?

Skills that share tags, products or a category with Jmcb Robustness: Hypothesis Generation (spacering-net/codeg, 3.9k stars), GitHub Deep Research (bytedance/deer-flow, 84k stars), Nature Paper Card (Yuan1z0825/nature-skills, 47k stars) and Content Research Writer (weapp-tailwindcss/weapp-tailwindcss, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jmcb Robustness?

brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,228 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.