doubt-driven-development
doubt-driven-development is a Multi-agent review & consensus skill for AI agents, published by addyosmani in the agent-skills repository on GitHub. Skillspace rates doubt-driven-development D (68/100) and it passed the safety scan; a judge model has also reviewed it.
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production auth, security-sensitive logic, a high-stakes migration, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 93,916
Placed #1 of 6 in the judged category final for Multi-agent review & consensus.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #1 of 6 in the judged category final for Multi-agent review & consensus.
- Trigger
90 90 - Instructions
90 90 - Specificity
92 92 - Safety
80 80 - Disclosure
78 78 - Maintenance
80 80
Gives the literal adversarial prompt template and explains why the claim must be withheld from the reviewer, plus honest limits on nesting inside subagents.
Not checked yet
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.