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

Muddy Waters Forensic

by questflowai in questflowai/investorskills

A skill your agent uses when evaluating Muddy Waters-style forensic short research: fraud, channel checks, related-party structures, cash verification, governance failure, and evidence-based short…

MITAuto-check passed

Install Muddy Waters Forensic

skills CLI
$ npx skills add questflowai/investorskills --skill muddy-waters-forensic -a claude-code

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

GitHub CLI
$ gh skill install questflowai/investorskills muddy-waters-forensic --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/questflowai/investorskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/muddy-waters-forensic .claude/skills/muddy-waters-forensic && 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
muddy-waters-forensic
GitHub stars
1.9k
Token cost
~527 tokens
SKILL.md length
211 words
Files
2
Skills in repo
63
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when evaluating Muddy Waters-style forensic short research: fraud, channel checks, related-party structures, cash verification, governance failure, and evidence-based short…

  • Works in 4 steps: Map the market's trusted management story. → Identify the specific alleged false… → Gather primary evidence: filings,… → …
  • Evaluating Muddy Waters-style forensic short research: fraud
  • SKILL.md covers When To Use, Do Not Use When, Inputs Needed and Process, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Muddy Waters Forensic is an agent skill from questflowai/investorskills. Use when evaluating Muddy Waters-style forensic short research: fraud, channel checks, related-party structures, cash verification, governance failure, and evidence-based short theses.

Its SKILL.md is about 530 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `invest.md`).

The repository describes itself as: Investor Skills is an open-source library that turns durable investing judgment into portable, structured formats. It collects how great investors think, filter opportunities… The licence is MIT.

When your agent uses it

  • Evaluating Muddy Waters-style forensic short research: fraud
  • Related-party structures
  • Cash verification
  • Governance failure

Example prompts

  • “/muddy-waters-forensic”

Workflow steps

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

  1. Map the market's trusted management story.
  2. Identify the specific alleged false mechanism.
  3. Gather primary evidence: filings, channel checks, related parties, cash trail.
  4. Define catalyst, short structure, squeeze/time risk, and invalidation.

What it can do on your machine

Read from SKILL.md and the folder at commit 2844d78. 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 markdown).

    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

Muddy Waters Forensic loads about 527 tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 211 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~527

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 questflowai/investorskills at commit 2844d78, republished under its MIT licence (© questflowai). 211 words, ~527 tokens.

Download SKILL.mdSave it as .claude/skills/muddy-waters-forensic/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
muddy-waters-forensic
description
Use when evaluating Muddy Waters-style forensic short research: fraud, channel checks, related-party structures, cash verification, governance failure, and evidence-based short theses.
invest
./invest.md

Muddy Waters Forensic Short

Use this skill to apply Muddy Waters / Carson Block-style judgment.

When To Use

Use this skill when the user asks for:

  • forensic short report
  • fraud or channel-stuffing suspicion
  • related-party complexity
  • cash/revenue verification
  • China/overseas complex structure short

Trigger phrases include Muddy Waters, Carson Block, forensic short, channel check, related party, fraud short, cash verification.

Do Not Use When

  • Another investor skill fits the setup better.
  • Critical primary evidence is unavailable.
  • The user wants guaranteed returns or unbounded risk.
  • The request is generic chatter with no decision.

Inputs Needed

  • Company, startup, token, report target, or market context
  • Primary documents, product data, user/revenue evidence, or research materials
  • Time horizon, capital structure, and risk constraints
  • Valuation or round pricing if sizing/commitment is requested

Process

  1. Map the market's trusted management story.
  2. Identify the specific alleged false mechanism.
  3. Gather primary evidence: filings, channel checks, related parties, cash trail.
  4. Define catalyst, short structure, squeeze/time risk, and invalidation.

Output Format

md
# Muddy Waters Forensic Short View: [Subject]

## Verdict
Short / Watch / Evidence Incomplete / Structure Risk Too High / Pass

## Thesis

## Evidence

## Risks

## Action Plan

## Invalidation

## Missing Data

Guardrails

  • Do not force conviction without evidence.
  • Do not ignore incentives, structure, or liquidity/risk constraints.
  • Separate facts, assumptions, and judgment.
  • Do not present this as financial advice.

Questflow Use

In Questflow, this skill is best used as a specialized judgment module for research workflows, Fund theses, diligence, monitoring, and decision support.

© questflowai, 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 1 other file in skills/muddy-waters-forensic of questflowai/investorskills.

  • SKILL.md
  • invest.md

Open the folder on GitHubat commit 2844d78

Compare with similar skills

Muddy Waters Forensic 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.

Muddy Waters Forensic compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Muddy Waters Forensic this skillquestflowai/investorskills1.9k—~527Automated safety check: PassMIT
Arize Evaluatorgithub/awesome-copilot40k1 repos~8.1kAutomated safety check: NotesMIT
Shortsickn33/agentic-awesome-skills47k1 repos~281Automated safety check: PassMIT
LLM Evaluationdavila7/claude-code-templates32k12 repos~3.5kAutomated safety check: PassMIT
Agent Evaluationsickn33/agentic-awesome-skills47k1 repos~2kAutomated safety check: PassMIT
Digital Forensicssickn33/agentic-awesome-skills47k1 repos~495Automated safety check: PassMIT

Similar skills

  • Arize Evaluator

    github/awesome-copilot

    Official

    Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and…

    40k GitHub starsUsed in 1 repo~8.1k tokens
    AI & LLM EngineeringAuto-check: notes

  • Short

    sickn33/agentic-awesome-skills

    Rewrite the previous response more briefly while preserving the substance.

    47k GitHub starsUsed in 1 repo~281 tokens
    Auto-check passed

  • LLM Evaluation

    davila7/claude-code-templates

    Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.

    32k GitHub starsUsed in 12 repos~3.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Agent Evaluation

    sickn33/agentic-awesome-skills

    Evaluate agent behavior with versioned cases and explicit verifiers.

    47k GitHub starsUsed in 1 repo~2k tokens
    Agent WorkflowsAuto-check passed

  • Digital Forensics

    sickn33/agentic-awesome-skills

    Authorized digital forensics: memory dumps, disk timelines, PCAP investigation, artifact triage, and incident-response evidence preservation.

    47k GitHub starsUsed in 1 repo~495 tokens
    SecurityAuto-check passed

  • Digital Forensics

    zhaoxuya520/reverse-skill

    A skill your agent uses for authorized digital forensics including memory dumps, disk timelines, PCAP investigation, artifact triage, and IR evidence preservation.

    40k GitHub starsUsed in 2 repos~389 tokens
    SecurityAuto-check: warnings

More from questflowai/investorskills

All 63 skills in this repo

  • A16z Techno Optimist

    questflowai/investorskills

    A skill your agent uses when evaluating startups or tech platforms through an a16z-style lens: technology adoption, market creation, platform power, AI/crypto/software narratives, and bold…

    1.9k GitHub stars~512 tokensUpdated 1 mo ago
    Auto-check passed

  • Ackman Concentrated Activism

    questflowai/investorskills

    A skill your agent uses when evaluating Bill Ackman-style concentrated long theses, activist campaigns, high-conviction multiyear bets, and public narrative plus fundamental catalysts.

    1.9k GitHub stars~491 tokensUpdated 1 mo ago
    Auto-check passed

  • Ansem Crypto

    questflowai/investorskills

    A skill your agent uses when evaluating crypto narratives, attention rotation, memecoin cycles, Solana-style ecosystem momentum, social distribution, and reflexive retail flows in an Ansem-style…

    1.9k GitHub stars~793 tokensUpdated 1 mo ago
    Auto-check passed

  • Arthur Hayes Liquidity

    questflowai/investorskills

    A skill your agent uses when evaluating crypto markets through an Arthur Hayes-style liquidity lens: dollar liquidity, funding, risk appetite, cycle psychology, and macro-driven crypto positioning.

    1.9k GitHub stars~449 tokensUpdated 1 mo ago
    Auto-check passed

  • Buffett

    questflowai/investorskills

    A skill your agent uses when evaluating a business through Buffett-style ownership, owner earnings, durable moat, management quality, capital allocation, and margin-of-safety judgment.

    1.9k GitHub stars~617 tokensUpdated 1 mo ago
    Auto-check passed

  • Burry Asymmetric Contrarian

    questflowai/investorskills

    A skill your agent uses when evaluating Michael Burry-style contrarian, asymmetric, unpopular trades: deep mispricing, short theses, complex assets, forced consensus errors, and catalyst-driven…

    1.9k GitHub stars~495 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Muddy Waters Forensic

What does Muddy Waters Forensic do?

A skill your agent uses when evaluating Muddy Waters-style forensic short research: fraud, channel checks, related-party structures, cash verification, governance failure, and evidence-based short…. Muddy Waters Forensic is an agent skill from questflowai/investorskills. Use when evaluating Muddy Waters-style forensic short research: fraud, channel checks, related-party structures, cash verification, governance failure, and evidence-based short theses.

When should I use Muddy Waters Forensic?

Muddy Waters Forensic fits situations like: evaluating Muddy Waters-style forensic short research: fraud; related-party structures; cash verification; governance failure.

How do I install Muddy Waters Forensic in Claude Code?

Run `npx skills add questflowai/investorskills --skill muddy-waters-forensic -a claude-code`. Or copy the skill folder (skills/muddy-waters-forensic in questflowai/investorskills) into .claude/skills/muddy-waters-forensic in your project. Claude Code loads it when a task matches its description.

How do I install Muddy Waters Forensic in Codex?

Run `npx skills add questflowai/investorskills --skill muddy-waters-forensic -a codex`. Or copy the skill folder (skills/muddy-waters-forensic in questflowai/investorskills) into .agents/skills/muddy-waters-forensic in your project. Codex loads it when a task matches its description.

Can I use Muddy Waters Forensic 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 questflowai/investorskills --skill muddy-waters-forensic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/muddy-waters-forensic, .gemini/skills/muddy-waters-forensic, .github/skills/muddy-waters-forensic and .opencode/skills/muddy-waters-forensic in your project.

What does Muddy Waters Forensic need to run?

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

Does Muddy Waters Forensic 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 Muddy Waters Forensic 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 Muddy Waters Forensic use?

Muddy Waters Forensic 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 Muddy Waters Forensic use?

About 527 tokens (SKILL.md is roughly 2.1k 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 Muddy Waters Forensic?

Skills that share tags, products or a category with Muddy Waters Forensic: Arize Evaluator (github/awesome-copilot, 40k stars), Short (sickn33/agentic-awesome-skills, 47k stars), LLM Evaluation (davila7/claude-code-templates, 32k stars) and Agent Evaluation (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Muddy Waters Forensic?

questflowai (a GitHub organization) maintains it in questflowai/investorskills, which has 1,896 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on August 23, 2026.

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