Agent skill

Assumption Challenger

by alirezarezvani in alirezarezvani/claude-cto-team

Identify and challenge implicit assumptions in plans, proposals, and technical decisions.

MITAuto-check passedSales & Support

Install Assumption Challenger

skills CLI
$ npx skills add alirezarezvani/claude-cto-team --skill assumption-challenger -a claude-code

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

GitHub CLI
$ gh skill install alirezarezvani/claude-cto-team assumption-challenger --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/alirezarezvani/claude-cto-team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/assumption-challenger .claude/skills/assumption-challenger && 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
assumption-challenger
GitHub stars
117
Token cost
~2.4k tokens
SKILL.md length
999 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Identify and challenge implicit assumptions in plans, proposals, and technical decisions.

  • Works in 12 steps: Timeline Assumptions → Resource Assumptions → Technical Assumptions → …
  • Strategic-cto-mentor needs to surface hidden assumptions and wishful thinking before they become costly mistakes
  • SKILL.md covers When to Use, Why Assumptions Matter, Assumption Categories and Assumption Identification…, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Assumption Challenger is an agent skill from alirezarezvani/claude-cto-team. Identify and challenge implicit assumptions in plans, proposals, and technical decisions. Use when strategic-cto-mentor needs to surface hidden assumptions and wishful thinking before they become costly mistakes.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `challenge-questions.md`).

It sits in Sales & Support, covering Proposals and quotes. The repository describes itself as: Your personal CTO Team for Claude Code . These Subagents will help you challenging yourself while you plan and execute. The licence is MIT.

When your agent uses it

  • Strategic-cto-mentor needs to surface hidden assumptions and wishful thinking before they become costly mistakes
  • Tasks that involve Proposals and quotes

Example prompts

  • “/assumption-challenger”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. Timeline Assumptions
  2. Resource Assumptions
  3. Technical Assumptions
  4. Business Assumptions
  5. External Assumptions
  6. Surface Assumptions
  7. Categorize Assumptions
  8. Assess Each Assumption
  9. Prioritize Challenges
  10. The Optimistic Timeline
  11. The Magical Hiring
  12. The Simple Integration

What it can do on your machine

Read from SKILL.md and the folder at commit a5bbb78. 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

Assumption Challenger loads about 2.4k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 999 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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 alirezarezvani/claude-cto-team at commit a5bbb78, republished under its MIT licence (© alirezarezvani). 999 words, ~2,410 tokens.

Download SKILL.mdSave it as .claude/skills/assumption-challenger/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
assumption-challenger
description
Identify and challenge implicit assumptions in plans, proposals, and technical decisions. Use when strategic-cto-mentor needs to surface hidden assumptions and wishful thinking before they become costly mistakes.

Assumption Challenger

Systematically identifies and stress-tests assumptions that are treated as facts but may not be validated.

When to Use

  • Validating roadmaps and project plans
  • Reviewing architecture proposals
  • Assessing build vs buy decisions
  • Evaluating timelines and budgets
  • Challenging strategic initiatives

Why Assumptions Matter

Most project failures trace back to invalid assumptions:

  • Timeline assumptions: "We can ship in 6 weeks" (based on nothing)
  • Resource assumptions: "We'll hire 3 engineers" (in a tight market)
  • Technical assumptions: "The API can handle 10K requests/sec" (never tested)
  • Business assumptions: "Users will adopt this feature" (never validated)

The cost of invalid assumptions compounds over time. A bad assumption in week 1 can waste months of work.


Assumption Categories

1. Timeline Assumptions

Assumptions about how long things will take.

Common patterns:

  • "This should only take 2 weeks"
  • "We'll have the integration done by launch"
  • "The team can absorb this additional scope"

Challenge questions:

  • What's this estimate based on? Past experience or hope?
  • What similar work have we done? How long did it actually take?
  • What's not included in this estimate? (Testing, documentation, deployment)
  • What happens if this takes 2x longer?
2. Resource Assumptions

Assumptions about team capacity and availability.

Common patterns:

  • "We'll hire 2 senior engineers by Q2"
  • "The DevOps team can support this"
  • "Sarah can lead this while maintaining her other work"

Challenge questions:

  • What's the hiring timeline? What if we can't find the right people?
  • What's the team's current utilization? Where does time come from?
  • Who's the backup if the key person is unavailable?
  • What happens if the team is 50% of expected capacity?
3. Technical Assumptions

Assumptions about system capabilities and constraints.

Common patterns:

  • "The database can handle the load"
  • "We can integrate with their API easily"
  • "Our architecture supports this use case"

Challenge questions:

  • Has this been tested at the required scale?
  • What are the documented limits? What happens at those limits?
  • What's the failure mode? How do we recover?
  • Have we talked to the API provider about our usage patterns?
4. Business Assumptions

Assumptions about market, users, and business outcomes.

Common patterns:

  • "Users want this feature"
  • "This will reduce churn by 20%"
  • "The market will wait for our solution"

Challenge questions:

  • What evidence supports this? User research? Data?
  • What if users don't adopt this? What's the fallback?
  • What are competitors doing in this space?
  • How will we know if this assumption is wrong?
5. External Assumptions

Assumptions about factors outside your control.

Common patterns:

  • "The vendor will have the feature ready"
  • "Regulations won't change"
  • "The market will remain stable"

Challenge questions:

  • What's our contingency if this doesn't happen?
  • What's the vendor's track record on commitments?
  • What early warning signs would indicate this is wrong?
  • What's the cost of being wrong?

Assumption Identification Process

Step 1: Surface Assumptions

Read the proposal and identify statements that are treated as facts but aren't validated:

Flag statements containing:

  • "We will..." (without evidence)
  • "We can..." (without proof)
  • "Users want..." (without data)
  • "It should..." (without testing)
  • "We expect..." (without basis)
  • "We assume..." (at least they're honest)
Step 2: Categorize Assumptions

For each assumption, categorize:

CategoryRisk if WrongValidation Difficulty
TimelineProject delayMedium (compare to past)
ResourceExecution failureMedium (check market)
TechnicalSystem failureHigh (requires testing)
BusinessWasted investmentHigh (requires market validation)
ExternalPlans disruptedVariable
Step 3: Assess Each Assumption

For each significant assumption:

markdown
### Assumption: [Statement]

**Category**: [Type]
**Stated or Implicit**: [Was it stated or hidden?]

**Evidence Supporting**:
- [Evidence 1]
- [Evidence 2]

**Evidence Against**:
- [Counter-evidence 1]
- [Counter-evidence 2]

**Risk if Wrong**:
- [Impact on timeline]
- [Impact on cost]
- [Impact on success]

**Validation Method**:
- [How to test this assumption]
- [Cost/time to validate]

**Verdict**:
[ ] Valid - Evidence supports
[ ] Questionable - Needs validation
[ ] Invalid - Evidence contradicts
[ ] Unknown - Cannot assess
Step 4: Prioritize Challenges

Focus on assumptions that are:

  1. High impact - Project fails if wrong
  2. Low evidence - Based on hope, not data
  3. Testable - Can be validated before commitment

Challenge Patterns

Show full SKILL.md (415 more words)Show less
The Reality Check

Compare assumption to external data.

Template:

"You assume [X]. Industry data shows [Y]. What makes you different?"

Example:

"You assume you can hire 3 senior engineers in 2 months. The average time-to-hire for senior engineers in your market is 4-6 months. What's your strategy to beat that?"

The History Test

Compare to organization's past performance.

Template:

"You assume [X]. Last time you attempted [similar thing], it took [Y]. What's changed?"

Example:

"You assume 8 weeks for the microservices migration. Your last infrastructure migration took 5 months. What's different this time?"

The Stress Test

Push assumption to failure point.

Template:

"You assume [X]. What happens when [stress scenario]?"

Example:

"You assume the system handles 10K concurrent users. What happens during a flash sale with 50K? What's the failure mode?"

The Dependency Audit

Trace assumption to its dependencies.

Template:

"For [assumption] to be true, what else must be true?"

Example:

"For your 6-week timeline to work, you need: (1) API specs finalized by week 1, (2) no scope changes, (3) 100% team availability, (4) no production incidents. How realistic is that?"

The Inverse Test

Consider what happens if assumption is wrong.

Template:

"If [assumption] is wrong, what's the impact? What's your Plan B?"

Example:

"If users don't adopt this feature, what's the fallback? Have you defined failure criteria?"


Wishful Thinking Indicators

Red flags that suggest assumption is based on hope rather than evidence:

1. The Optimistic Timeline
  • "Should only take..."
  • "If everything goes well..."
  • "We can do it if we're focused..."

Reality: Things rarely go perfectly. Add 30-50% buffer.

2. The Magical Hiring
  • "We'll just hire..."
  • "Once we have the team..."
  • "We're planning to bring on..."

Reality: Hiring takes 3-6 months for senior roles. Onboarding adds another 2-3 months to productivity.

3. The Simple Integration
  • "It's just an API call..."
  • "Should be straightforward..."
  • "They have good documentation..."

Reality: Integrations always have edge cases, rate limits, and unexpected behaviors.

4. The Obvious Market
  • "Everyone needs this..."
  • "Users have been asking for..."
  • "It's clear that..."

Reality: "Everyone" is not a market segment. Validate with actual user research.

5. The Linear Scaling
  • "If we can do X, we can do 10X..."
  • "We'll scale as needed..."
  • "Growth shouldn't be a problem..."

Reality: Scaling is non-linear. What works at 10K users may fail at 100K.


Output Format

When challenging assumptions, provide:

markdown
# Assumption Analysis: [Plan/Proposal Name]

## Summary
- **Total Assumptions Identified**: [Count]
- **High-Risk Assumptions**: [Count]
- **Requires Immediate Validation**: [Count]

## Critical Assumptions (Must Validate Before Proceeding)

### Assumption 1: [Statement]

**Category**: Timeline / Resource / Technical / Business / External
**Stated or Implicit**: Stated / Implicit

**The Problem**:
[Why this assumption is questionable]

**Evidence For**:
- [Supporting evidence]

**Evidence Against**:
- [Counter-evidence]

**If Wrong, Impact**:
- Timeline: [Impact]
- Budget: [Impact]
- Success: [Impact]

**How to Validate**:
- [Validation method]
- [Time required]
- [Cost]

**Verdict**: Valid / Questionable / Invalid / Unknown

---

### Assumption 2: [Statement]
[Same format]

---

## Medium-Risk Assumptions (Should Validate)
[List with brief analysis]

## Low-Risk Assumptions (Monitor)
[List]

## Recommendations

### Before Proceeding
1. [Validation action 1]
2. [Validation action 2]

### Risk Mitigation
1. [Mitigation for assumption 1]
2. [Mitigation for assumption 2]

### Contingency Plans Needed
1. [Plan B for assumption 1]
2. [Plan B for assumption 2]

Integration with Validation

The assumption-challenger skill feeds into the broader validation workflow:

Proposal/Plan
     │
     ▼
[assumption-challenger] → List of assumptions with verdicts
     │
     ▼
[antipattern-detector] → Identified anti-patterns
     │
     ▼
[validation-report-generator] → Final 8-section report

References

© alirezarezvani, 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/assumption-challenger of alirezarezvani/claude-cto-team.

  • SKILL.md
  • challenge-questions.md

Open the folder on GitHubat commit a5bbb78

Compare with similar skills

Assumption Challenger 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.

Assumption Challenger compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Assumption Challenger this skillalirezarezvani/claude-cto-team117—~2.4kAutomated safety check: PassMIT
Doc Coauthoringaws-samples/sample-strands-agent-with-agentcore19541 repos~3.2kAutomated safety check: PassMIT
Audit Onboarding Proposalhoangnb24/repository-harness1.2k—~4kAutomated safety check: PassMIT
No Negative EchoLB623/no-negative-echo897—~965Automated safety check: PassMIT
GEO Service Proposal Generatorzubair-trabzada/geo-seo-claude11k—~3kAutomated safety check: NotesMIT
Architectural ProposalsFritzAndFriends/SharpSite1452 repos~1.6kAutomated safety check: PassMIT

Similar skills

  • Doc Coauthoring

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Guide users through a structured workflow for co-authoring documentation.

    195 GitHub starsUsed in 41 repos~3.2k tokens
    Sales & SupportAuto-check passed
  • Audit Onboarding Proposal

    hoangnb24/repository-harness

    Use only when the user explicitly invokes $audit-onboarding-proposal.

    1.2k GitHub stars~4k tokensUpdated 5 days ago
    Sales & SupportAuto-check passed
  • No Negative Echo

    LB623/no-negative-echo

    Prevent 此地无银三百两式 residue: finalize artifacts without echoing rejected session-only alternatives into labels, metadata, commits, PRs, or handoffs.

    897 GitHub stars~965 tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed
  • GEO Service Proposal Generator

    zubair-trabzada/geo-seo-claude

    Builds a client-ready AI-search-optimization proposal from an existing GEO audit, with pricing tiers, an ROI estimate and a markdown document ready to send.

    11k GitHub stars~3k tokensUpdated today
    Sales & SupportAuto-check: notes
  • Architectural Proposals

    FritzAndFriends/SharpSite

    How to write comprehensive architectural proposals that drive alignment before code is written

    145 GitHub starsUsed in 2 repos~1.6k tokens
    Sales & SupportAuto-check passed
  • Counter Proposal Generator

    zubair-trabzada/ai-legal-claude

    Generates specific counter-proposals for every unfavorable clause, with replacement language, negotiation talking points, and a ready-to-send email template

    1.8k GitHub stars~2.4k tokensUpdated 6 mo ago
    Sales & SupportAuto-check passed

More from alirezarezvani/claude-cto-team

All 12 skills in this repo
  • Antipattern Detector

    alirezarezvani/claude-cto-team

    Detect common technical and organizational anti-patterns in proposals, architectures, and plans.

    117 GitHub stars~2.1k tokensUpdated 9 mo ago
    Auto-check passed
  • Architecture Pattern Selector

    alirezarezvani/claude-cto-team

    Recommend architecture patterns (monolith, microservices, serverless, modular monolith) based on scale, team size, and constraints.

    117 GitHub stars~1.6k tokensUpdated 9 mo ago
    Auto-check passed
  • Cost Estimator

    alirezarezvani/claude-cto-team

    Infrastructure and development cost estimation for technical projects.

    117 GitHub stars~3k tokensUpdated 9 mo ago
    Auto-check passed
  • ML Cv Specialist

    alirezarezvani/claude-cto-team

    Deep expertise in ML/CV model selection, training pipelines, and inference architecture.

    117 GitHub stars~3.1k tokensUpdated 9 mo ago
    Auto-check passed
  • Request Analyzer

    alirezarezvani/claude-cto-team

    Analyze incoming user requests to detect intent, request type (design/validate/debug/document), complexity level, and identify vague requirements or buzzwords that need clarification.

    117 GitHub stars~1.3k tokensUpdated 9 mo ago
    Auto-check passed
  • Roadmap Generator

    alirezarezvani/claude-cto-team

    Generate phased implementation roadmaps with Epic/Story/Task breakdown, effort estimates, and validation checkpoints.

    117 GitHub stars~1.9k tokensUpdated 9 mo ago
    Auto-check passed

Categories

Questions about Assumption Challenger

What does Assumption Challenger do?

Identify and challenge implicit assumptions in plans, proposals, and technical decisions. Assumption Challenger is an agent skill from alirezarezvani/claude-cto-team. Identify and challenge implicit assumptions in plans, proposals, and technical decisions.

When should I use Assumption Challenger?

Assumption Challenger fits situations like: strategic-cto-mentor needs to surface hidden assumptions and wishful thinking before they become costly mistakes; tasks that involve Proposals and quotes.

How do I install Assumption Challenger in Claude Code?

Run `npx skills add alirezarezvani/claude-cto-team --skill assumption-challenger -a claude-code`. Or copy the skill folder (skills/assumption-challenger in alirezarezvani/claude-cto-team) into .claude/skills/assumption-challenger in your project. Claude Code loads it when a task matches its description.

How do I install Assumption Challenger in Codex?

Run `npx skills add alirezarezvani/claude-cto-team --skill assumption-challenger -a codex`. Or copy the skill folder (skills/assumption-challenger in alirezarezvani/claude-cto-team) into .agents/skills/assumption-challenger in your project. Codex loads it when a task matches its description.

Can I use Assumption Challenger 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 alirezarezvani/claude-cto-team --skill assumption-challenger -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/assumption-challenger, .gemini/skills/assumption-challenger, .github/skills/assumption-challenger and .opencode/skills/assumption-challenger in your project.

What does Assumption Challenger need to run?

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

Does Assumption Challenger 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 Assumption Challenger 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 Assumption Challenger use?

Assumption Challenger 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 Assumption Challenger use?

About 2.4k tokens (SKILL.md is roughly 9.6k 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 Assumption Challenger?

Skills that share tags, products or a category with Assumption Challenger: Doc Coauthoring (aws-samples/sample-strands-agent-with-agentcore, 195 stars), Audit Onboarding Proposal (hoangnb24/repository-harness, 1.2k stars), No Negative Echo (LB623/no-negative-echo, 897 stars) and GEO Service Proposal Generator (zubair-trabzada/geo-seo-claude, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Assumption Challenger?

alirezarezvani (a GitHub user) maintains it in alirezarezvani/claude-cto-team, which has 117 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on December 18, 2025.

Source: alirezarezvani/claude-cto-team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.