Agent skill

Finman Topic Selection

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

A skill your agent uses when deciding whether a topic fits Financial Management (FM) and is worth aiming there — testing the question for general-interest finance relevance, topicality, and…

MITAuto-check passed

Install Finman Topic Selection

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill finman-topic-selection -a claude-code

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills finman-topic-selection --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/Financial-Management-Skills/skills/finman-topic-selection .claude/skills/finman-topic-selection && 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
finman-topic-selection
GitHub stars
1.2k
Token cost
~2.1k tokens
SKILL.md length
1,105 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when deciding whether a topic fits Financial Management (FM) and is worth aiming there — testing the question for general-interest finance relevance, topicality, and…

  • Works in 4 steps: General-interest gate. Could you state… → Decision-relevance gate. Name the agent… → Topicality gate. Tie the question to a… → …
  • Managerial/market payoff before the literature and design work begins
  • SKILL.md covers When to trigger, The FM topic bar, Deciding whether the topic is… and Topic signals by FM subfield, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Finman Topic Selection is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when deciding whether a topic fits Financial Management (FM) and is worth aiming there — testing the question for general-interest finance relevance, topicality, and managerial/market payoff before the literature and design work begins. Sets the target; it does not run analysis or write the paper.

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.

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

  • Managerial/market payoff before the literature and design work begins

Example prompts

  • “/finman-topic-selection”

Workflow steps

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

  1. General-interest gate. Could you state the finding in one sentence to a finance seminar with no field specialists and have them care? If…
  2. Decision-relevance gate. Name the agent whose decision changes if the result is true — a CFO setting payout, an investor pricing a factor…
  3. Topicality gate. Tie the question to a live or emerging issue (a recent regulation, a new instrument, a market structure shift, a…
  4. Originality gate. State the new thing — a new fact, a new mechanism, a new identification of an old mechanism, or a clean answer to a…

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

Finman Topic Selection loads about 2.1k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 1,105 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
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). 1,105 words, ~2,059 tokens.

Download SKILL.mdSave it as .claude/skills/finman-topic-selection/SKILL.md (or your agent's skills folder).
name
finman-topic-selection
description
Use when deciding whether a topic fits Financial Management (FM) and is worth aiming there — testing the question for general-interest finance relevance, topicality, and managerial/market payoff before the literature and design work begins. Sets the target; it does not run analysis or write the paper.

Topic Selection (finman-topic-selection)

When to trigger

  • You have a finance result or idea and are unsure FM is the right home (vs. a specialist or a top-3 outlet)
  • A coauthor asks "is this general-interest enough, or too niche, for FM?"
  • The question feels technically sound but you cannot yet say why a practitioner or a non-specialist finance academic would care
  • The topic feels dated — re-treading a settled debate rather than a live one

The FM topic bar

FM is the FMA's general-interest finance journal, and its editors are unusually explicit about taste: they want "academic articles that people actually read," judged on originality, rigor, timeliness, practical relevance, and quality, with less weight on trivial robustness and real weight on whether the paper "provokes and furthers debate." Translated into a topic filter, an FM-worthy question is one a corporate-finance, asset-pricing, banking, or markets reader would all find interesting, that speaks to a decision a manager, investor, regulator, or trader actually faces, and that is topical — anchored to a current or emerging financial issue rather than a marginal extension of a 2008 debate. The journal also actively solicits work "from anywhere around the globe," so a clean non-US setting is an asset, not a liability, when the financial mechanism is general.

Deciding whether the topic is FM-shaped

Run the question through four gates, in order. If it fails the first two, FM is probably the wrong target; if it fails the last two, the topic needs reframing before you proceed.

  1. General-interest gate. Could you state the finding in one sentence to a finance seminar with no field specialists and have them care? If it only lands with, say, microstructure insiders, consider a specialist outlet — or recast the takeaway around the broader implication.
  2. Decision-relevance gate. Name the agent whose decision changes if the result is true — a CFO setting payout, an investor pricing a factor, a regulator weighing a rule, a board designing pay. If no such agent exists, the "practical relevance" criterion is unmet.
  3. Topicality gate. Tie the question to a live or emerging issue (a recent regulation, a new instrument, a market structure shift, a data-newly-available phenomenon). A timely hook is one of FM's five stated criteria.
  4. Originality gate. State the new thing — a new fact, a new mechanism, a new identification of an old mechanism, or a clean answer to a genuinely open question. "We add controls to a known result" fails this gate at FM.

Topic signals by FM subfield

FM is general-interest, so the same four gates apply across very different subfields — but the shape of an FM-worthy question differs by area. Use this to pressure-test the topic against its home subfield's FM bar.

SubfieldAn FM-shaped question looks likeA too-narrow / mis-targeted version
Corporate financea financing/investment/M&A decision affected by a live shock, with a managerial takeawaya marginal re-test of pecking order on a new sample
Payout & capital structurehow a policy choice responds to a tax/regulatory change that separates competing theoriesanother determinants-of-leverage regression
Governancea board/ownership mechanism with a credible source of variation and a board-relevant implicationa governance-index correlation with performance
Investments / asset pricinga return pattern that speaks to a general debate (risk vs. mispricing) and survives costsa factor zoo addition with no economic story
Banking / intermediationan information/frictions mechanism that generalizes beyond banksa bank-specific regulatory note
Markets / microstructurea market-design or liquidity finding with implications a trader/regulator acts ona venue-specific tick-size technicality

Checklist

  • One-sentence claim is legible to a general finance audience, not only a subfield
  • The decision-maker who would act on the result is named (manager / investor / regulator / board)
  • The question is tied to a current or emerging financial issue (timeliness)
  • The originality is stated as a specific new fact/mechanism/answer, not an incremental extension
  • The setting (US or non-US) is justified by the generality of the mechanism, not convenience
  • The topic fits the FM-shaped column for its subfield, not the too-narrow column
  • You can articulate why this is FM and not a specialist sibling or a top-3 desk
Show full SKILL.md (430 more words)Show less

Anti-patterns

  • A technically clean paper with no audience beyond one subfield — "rigorous but no one reads it"
  • Pitching a marginal extension of a long-settled debate as if novelty came from the new sample
  • Leading with method ("we apply estimator X") instead of the financial question and its stakes
  • Treating a non-US setting as a defect to apologize for, rather than evidence of generality
  • Assuming exotic data alone makes a topic FM-worthy without a decision-relevant payoff

Worked vignette (illustrative)

A draft documents that firms in one country smooth dividends more after a 2023 tax change. As framed it reads like a country-specific note. The FM reframe: ask the general-interest question — do payout commitments respond to tax-induced changes in the marginal investor's clientele, and what should a CFO infer about signaling vs. catering? Now the decision-maker (the CFO setting payout policy), the topicality (a 2023 reform), and the originality (clean tax variation that separates two payout theories) are all explicit, and a non-US setting becomes the source of identification rather than a parochial limitation.

Early routing decisions this stage settles

Topic selection is also where you decide, provisionally, two things that shape the whole pipeline:

  • Whether FM is the right target at all. If the question fails the general-interest and decision-relevance gates, route the user honestly to a specialist sibling rather than forcing an FM pitch the editors will see through. Naming the correct home early saves a desk-reject and a fee.
  • Where the binding constraint will be. A topic whose novelty is a new fact will live or die on measurement and framing; one whose novelty is a causal claim about an old mechanism will live or die on identification. Flag this so finman-workflow can route to the right next link instead of marching through every stage.

Reframes that rescue a borderline topic

When a topic fails a gate, it is often salvageable by changing the question, not the data:

  • Fails general-interest → lift the takeaway one level: from "X happens in industry Y" to the mechanism (information, frictions, incentives) that travels across industries.
  • Fails decision-relevance → name the agent and the decision explicitly; if you cannot, the finding may be a measurement curiosity better suited elsewhere.
  • Fails timeliness → re-anchor to a current shock, instrument, or newly available dataset that makes the old question live again.
  • Fails originality → find the disagreement your result settles, or the fact no one has cleanly documented, rather than the marginal coefficient you add. A topic that survives all four after reframing is genuinely FM-shaped; one that needs the data to do the persuading is not.

Output format

【Journal】Financial Management
【Topic in one sentence】<general-interest finance claim>
【Decision-maker】<manager / investor / regulator / board who acts on it>
【Timeliness hook】<current or emerging issue it speaks to>
【Originality】<new fact / mechanism / identification / answer>
【FM vs. siblings】why FM and not JCF / JFQA / a top-3 desk
【Source status】verified / 待核实 / not asserted
【Next skill】finman-literature-positioning

© 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 Financial-Management-Skills/skills/finman-topic-selection of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Finman Topic Selection 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.

Finman Topic Selection compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Finman Topic Selection this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~2.1kAutomated safety check: PassMIT
Financial Analystalirezarezvani/claude-skills28k1 repos~1.8kAutomated safety check: PassMIT
Startup Financial Modelingwshobson/agents40k—~1.9kAutomated safety check: PassMIT
Financial Data Cross-Validationxbtlin/ai-berkshire17k—~1.4kAutomated safety check: PassMIT
Three-Statement Financial AnalysisHKUDS/Vibe-Trading35k—~1.2kAutomated safety check: PassMIT
Financial Report Analysisdigoal/blog8.6k—~1.2kAutomated safety check: PassGPL-2.0

Similar skills

  • Financial Analyst

    alirezarezvani/claude-skills

    Runs financial ratio analysis, DCF valuation, budget variance reports and rolling forecasts from statement data using four bundled Python scripts.

    28k GitHub starsUsed in 1 repo~1.8k tokens
    Business, Finance & HRAuto-check passed
  • Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow analysis, and scenario planning for early-stage startups.

    40k GitHub stars~1.9k tokensUpdated 4 days ago
    Business, Finance & HRAuto-check passed
  • A research rule set for pulling company financials from prioritized sources by market and cross-checking every key figure against two independent sources.

    17k GitHub stars~1.4k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Reads the income statement, balance sheet and cash flow statement together to judge earnings quality, apply DuPont analysis and check 12 red-flag indicators for manipulation; Chinese text.

    35k GitHub stars~1.2k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Analyze company annual reports, quarterly reports, 10-K/10-Q filings, earnings releases, shareholder letters, or financial-report PDFs/URLs/files and produce a professional Chinese Markdown report…

    8.6k GitHub stars~1.2k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Financial Model

    davepoon/buildwithclaude

    Run deterministic financial models for startup valuation and SaaS health analysis.

    3.6k GitHub stars~1.1k tokensUpdated today
    Business, Finance & HRAuto-check passed

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

Questions about Finman Topic Selection

What does Finman Topic Selection do?

A skill your agent uses when deciding whether a topic fits Financial Management (FM) and is worth aiming there — testing the question for general-interest finance relevance, topicality, and…. Finman Topic Selection is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when deciding whether a topic fits Financial Management (FM) and is worth aiming there — testing the question for general-interest finance relevance, topicality, and managerial/market payoff before the literature and design work begins.

When should I use Finman Topic Selection?

Finman Topic Selection fits situations like: managerial/market payoff before the literature and design work begins.

How do I install Finman Topic Selection in Claude Code?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill finman-topic-selection -a claude-code`. Or copy the skill folder (Financial-Management-Skills/skills/finman-topic-selection in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/finman-topic-selection in your project. Claude Code loads it when a task matches its description.

How do I install Finman Topic Selection in Codex?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill finman-topic-selection -a codex`. Or copy the skill folder (Financial-Management-Skills/skills/finman-topic-selection in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/finman-topic-selection in your project. Codex loads it when a task matches its description.

Can I use Finman Topic Selection 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 finman-topic-selection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/finman-topic-selection, .gemini/skills/finman-topic-selection, .github/skills/finman-topic-selection and .opencode/skills/finman-topic-selection in your project.

What does Finman Topic Selection need to run?

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

Does Finman Topic Selection 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 Finman Topic Selection 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 Finman Topic Selection use?

Finman Topic Selection 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 Finman Topic Selection use?

About 2.1k tokens (SKILL.md is roughly 8.2k 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 Finman Topic Selection?

Skills that share tags, products or a category with Finman Topic Selection: Financial Analyst (alirezarezvani/claude-skills, 28k stars), Startup Financial Modeling (wshobson/agents, 40k stars), Financial Data Cross-Validation (xbtlin/ai-berkshire, 17k stars) and Three-Statement Financial Analysis (HKUDS/Vibe-Trading, 35k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Finman Topic Selection?

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.