mcpField
B
brutal-honesty-review

brutal-honesty-review

github.com/proffesor-for-testingTesting & quality519178 installsUpdated 1d ago
Repository

About brutal-honesty-review

A direct-feedback skill for reviewing code, quality standards, or vendor claims, with modes selected according to the issue and context. It focuses criticism on the work, requires actionable next steps, and defines situations where this style should not be used.

Key features

  1. 01Choose technical, standards, or claims-review modes
  2. 02Calibrate directness to context
  3. 03Structure findings around problems and fixes
  4. 04Enforce weighted review findings
  5. 05Critique the work, not the person
  6. 06Require consent and observe usage limits

Use cases

  1. 01Review code from senior engineers
  2. 02Examine recurring architectural mistakes
  3. 03Evaluate security issues or vendor claims
  4. 04Give direct feedback after obtaining consent

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/proffesor-for-testing/agentic-qe --skill brutal-honesty-review

After installing, type/brutal-honesty-reviewin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

README.md
resources/
assessment-rubrics.md
review-template.md
schemas/
output.json
scripts/
assess-code.sh
assess-tests.sh
validate-config.json

Details

From the project README

Brutal Honesty Review

<default_to_action> When brutal honesty is needed:

  1. CHOOSE MODE: Linus (technical), Ramsay (standards), Bach (BS detection)
  2. VERIFY CONTEXT: Senior engineer? Repeated mistake? Critical bug? Explicit request?
  3. STRUCTURE: What's broken → Why it's wrong → What correct looks like → How to fix
  4. ATTACK THE WORK, not the worker
  5. ALWAYS provide actionable path forward

Quick Mode Selection:

  • Linus: Code is technically wrong, inefficient, misunderstands fundamentals
  • Ramsay: Quality is subpar compared to clear excellence model
  • Bach: Certifications, best practices, or vendor hype need reality check

Calibration:

  • Level 1 (Direct): "This approach is fundamentally flawed because..."
  • Level 2 (Harsh): "We've discussed this three times. Why is it back?"
  • Level 3 (Brutal): "This is negligent. You're exposing user data because..."

DO NOT USE FOR: Junior devs' first PRs, demoralized teams, public forums, low psychological safety

Minimum Findings Enforcement

All brutal honesty reviews enforce a minimum of 3 weighted findings (CRITICAL=3, HIGH=2, MEDIUM=1, LOW=0.5). If the initial review finds fewer, escalate to deeper analysis. Brutally honest reviewers should ALWAYS find something -- if you can't, explain exactly why with evidence. </default_to_action>

Quick Reference Card

When to Use
ContextAppropriate?Why
Senior engineer code review✅ YesCan handle directness, respects precision
Repeated architectural mistakes✅ YesGentle approaches failed
Security vulnerabilities✅ YesStakes too high for sugar-coating
Evaluating vendor claims✅ YesBS detection prevents expensive mistakes
Junior dev's first PR❌ NoUse constructive mentoring
Demoralized team❌ NoWill break, not motivate
Public forum❌ NoPublic humiliation destroys trust
Three Modes
ModeWhenExample Output
LinusCode technically wrong"You're holding the lock for the entire I/O. Did you test under load?"
RamsayQuality below standards"12 tests and 10 just check variables exist. Where's the business logic?"
BachBS detection needed"This cert tests memorization, not bug-finding. Who actually benefits?"

The Criticism Structure

## What's Broken
[Surgical description - specific, technical]

## Why It's Wrong
[Technical explanation, not opinion]

## What Correct Looks Like
[Clear model of excellence]

## How to Fix It
[Actionable steps, specific to context]

## Why This Matters
[Impact if not fixed]

Mode Examples

Linus Mode: Technical Precision
**Problem**: Holding database connection during HTTP call

"This is completely broken. You're holding a database connection
open while waiting for an external HTTP request. Under load, you'll
exhaust the connection pool in seconds.

Did you even test this with more than one concurrent user?

The correct approach is:
1. Fetch data from DB
2. Close connection
3. Make HTTP call
4. Open new connection if needed

This is Connection Management 101. Why wasn't this caught in review?"
Ramsay Mode: Standards-Driven Quality
**Problem**: Tests only verify happy path

"Look at this test suite. 15 tests, 14 happy path scenarios.
Where's the validation testing? Edge cases? Failure modes?

This is RAW. You're testing if code runs, not if it's correct.

Production-ready covers:
✓ Happy path (you have this)
✗ Validation failures (missing)
✗ Boundary conditions (missing)
✗ Error handling (missing)
✗ Concurrent access (missing)

You wouldn't ship code with 12% coverage. Don't merge tests
with 12% scenario coverage."
Bach Mode: BS Detection
**Problem**: ISTQB certification required for QE roles

"ISTQB tests if you memorized terminology, not if you can test software.

Real testing skills:
- Finding bugs others miss
- Designing effective strategies for context
- Communicating risk to stakeholders

ISTQB tests:
- Definitions of 'alpha' vs 'beta' testing
- Names of techniques you'll never use
- V-model terminology

If ISTQB helped testers, companies with certified teams would ship
higher quality. They don't."

Assessment Rubrics

Code Quality (Linus Mode)
CriteriaFailingPassingExcellent
CorrectnessWrong algorithmWorks in tested casesProven across edge cases
PerformanceNaive O(n²)Acceptable complexityOptimal + profiled
Error HandlingCrashes on invalidReturns error codesGraceful degradation
TestabilityImpossible to testCan mockSelf-testing design
Test Quality (Ramsay Mode)
CriteriaRawAcceptableMichelin Star
Coverage<50% branch80%+ branch95%+ mutation tested
Edge CasesOnly happy pathCommon failuresBoundary analysis complete
StabilityFlaky (>1% failure)Stable but slowDeterministic + fast
BS Detection (Bach Mode)
Red FlagEvidenceImpact
Cargo Cult Practice"Best practice" with no contextWasted effort
Certification TheaterRequired cert unrelated to skillsFilters out thinkers
Vendor Lock-InTool solves problem it createdExpensive dependency

Agent Integration

// Brutal honesty code review
await Task("Code Review", {
  code: pullRequestDiff,
  mode: 'linus',  // or 'ramsay', 'bach'
  calibration: 'direct',  // or 'harsh', 'brutal'
  requireActionable: true
}, "qe-code-reviewer");

// BS detection for vendor claims
await Task("Vendor Evaluation", {
  claims: vendorMarketingClaims,
  mode: 'bach',
  requireEvidence: true
}, "qe-quality-gate");

Agent Coordination Hints

Memory Namespace
aqe/brutal-honesty/
├── code-reviews/*     - Technical review findings
├── bs-detection/*     - Vendor/cert evaluations
└── calibration/*      - Context-appropriate levels
Fleet Coordination
const reviewFleet = await FleetManager.coordinate({
  strategy: 'brutal-review',
  agents: [
    'qe-code-reviewer',    // Technical precision
    'qe-security-auditor', // Security brutality
    'qe-quality-gate'      // Standards enforcement
  ],
  topology: 'parallel'
});

Related Skills


Remember

Brutal honesty eliminates ambiguity but has costs. Use sparingly, only when necessary, and always provide actionable paths forward. Attack the work, never the worker.

The Brutal Honesty Contract: Get explicit consent. "I'm going to give unfiltered technical feedback. This will be direct, possibly harsh. The goal is clarity, not cruelty."

Comments

Markdown supported