Doubt-Driven Development Skill

Makes Claude doubt and re-check its own work before shipping.

Development / Developer Toolsdevelopmentdeveloper-tools
by AgentVoltv1.0.0Published 1y ago1 install
Free to sign up · every skill included with AgentVolt Pro

Before & after

Same prompt, same agent — the only difference is the skill.

PromptVerify this authentication module before we ship to production
Beforegeneric AI agent
I can review your authentication code. It looks reasonable at first glance. What testing have you already done? Are you using any standard libraries or rolling custom crypto? I'd suggest checking for common vulnerabilities, but to be thorough, it would help to know more about your specific implementation and threat model.
Afterwith Doubt-Driven Development Skill
VERIFICATION CHECKLIST: Authentication Module

→ SECURITY VERIFICATION (DO THIS FIRST)
  ✓ Password hashing: bcrypt or argon2? (if MD5 or SHA1, FAIL)
  ✓ Salt unique per hash? (check db – not stored plaintext)
  ✓ Timing attack vulnerability? (use constant-time comparison)
  ✓ Session token generation: cryptographically secure? (not Math.random())
  ✓ Token storage: httpOnly cookie + secure flag set?
  ✗ TRAP: Many auth breaches from session fixation – always regenerate token on login

→ EDGE CASE COVERAGE
  ✓ Test concurrent login attempts (same user, 2 browsers)
  ✓ Test token expiration (attempt use at expiry+1ms)
  ✓ Test password reset flow (invalid token after use, expiry honored)
  ✓ Test logout across all sessions (one logout doesn't kill others)
  ✓ Test admin escalation (user can't self-promote to admin)
  Question to resolve: LDAP fallback – scope of directory users included?

→ COMPLIANCE & AUDIT
  ✓ Confirm password policy (min 8 chars, no common patterns)
  ✓ Failed attempt logging (locked after 5 tries / 15min window)
  ✓ No credentials in logs (grep for password variables in output)
  ✓ PII properly scoped in error messages (user doesn't see system internals)

→ DEPLOYMENT GATE
  Stop: Run full integration test suite before ship (required pass rate: 100%)
  Stop: Security scan on dependencies (run npm audit / pip audit)
  Action: Coordinate staged rollout – 10% traffic first (1 hour), then 50%, then 100%

About this skill


name: doubt-driven-development-skill description: Use when Makes Claude doubt and re-check its own work before shipping.

Doubt-Driven Development Skill

Part of a Google Director open source agent skills set, this skill forces the agent to question its own assumptions and verify results before declaring a task complete.

What you get

  • SKILL.md within the agent-skills repo, portable across Claude Code, Gemini CLI, and opencode.

Customize your output

  • Adaptable to any verification checklist.

Example output

More carefully verified agent output with fewer silent assumptions.

Best for

Developers wanting more rigorous self-checking from coding agents.

SKILL.md preview

SKILL.md
---
name: doubt-driven-development-skill
description: Use when Claude is about to declare a coding task complete and needs to actively doubt and re-verify its own work first.
version: 1.0.0
category: Development / Developer Tools
author: AgentVolt
license: proprietary
tags:
  - development
  - developer-tools
  - standard
---

# Doubt-Driven Development Skill

Forces a deliberate skepticism pass before any task is marked done, re-checking assumptions and edge cases instead of trusting a first pass that looks correct.

## When to use

… (sign up to view the full skill)
Sign up to view, copy, and install the full skill

More development skills

View all Development skills →