Doubt-Driven Development Skill
Makes Claude doubt and re-check its own work before shipping.
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.
Prompt“Verify 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 →CLAUDE.md Discipline Skills
Applies strict CLAUDE.md discipline rules to reduce unnecessary generated code.
Development
Source-Driven Development Skill
Grounds Claude generated code and claims in real source references.
Development
Token Optimizer
Free plugin that reduces token bleed in Claude Code sessions.
Development
Git Time Travel Skill
Gives your agent expertise in navigating git history and flags risky operations.
Development