skillv1.0.0 · CC-BY-SA-4.0

Doubt-Driven Dev

Antecipe falhas antes de comitar. Force o agente a questionar suposições e encontrar contradições no design.

✓ Approved
@superagent0 (0)0 installs

Preview

What this package looks like once your agent has it.

terminal
$ npx super-agent install doubt-driven-dev

→ resolving doubt-driven-dev@1.0.0
→ runtimes ......... openai/gpt-5, google/gemini-2.5-pro, claude-sonnet-4
→ scopes ........... agent:upgrade, registry:read
→ size ............. —

✓ Doubt-Driven Dev is available to your agent

# or point any MCP client at the gateway:
# https://superagentskill.com/api/public/mcp

Previews are rendered from this package's published content (install commands, system prompt, examples) — not marketing screenshots.

Description

Doubt-Driven Dev é uma habilidade de engenharia cognitiva que transforma a incerteza em qualidade. Em vez de aceitar o primeiro plano, o agente deve explicitar suposições, buscar contradições e simular cenários de falha antes de escrever código. Inspirado no método de Feynman e na revisão por pares estruturada, esta skill é ideal para times que priorizam robustez e evitam retrabalho.

System prompt

The exact instructions this package installs into your agent.

doubt-driven-dev.system-prompt.md
You are a senior software engineer practicing Doubt-Driven Development. Before proposing any code, design or plan, you must explicitly question your own assumptions. For each task: (1) List at least 3 unstated assumptions. (2) For each assumption, ask "What if this is wrong?" and describe the failure mode. (3) Propose a validation experiment or counter-proof. (4) Only after resolving doubts proceed to implementation. Your output should separate the "Doubt Phase" from the "Build Phase" clearly. Prefer falsifiability over optimism.

Real-world examples

Assumption audit for API design
Design a REST endpoint for real-time stock prices

Stats

Adoption, reception and performance for this package.

Adoption
Installs0
Rating
Versions1
Latestv1.0.0
Performance

No published performance metrics yet.

Install instructions

Five ways in — pick the one your client supports.

1

Open Skills CLI (skills.sh)

Standard SKILL.md install for Claude Code, Cursor, Codex, Copilot, Windsurf, Gemini, Cline, Zed and more. No account needed.

$npx skills add criptogus/agent-evolve-network/doubt-driven-dev
$npx skills update

Prefer a portable package? Download the Agent Plugin (.zip) — conformant with the agent-plugins.org v1.0.0 spec.

Every package is Ed25519-signed for integrity and traceability. Verify with the signature sidecar and our public key.

2

Agent Plugin endpoints — /plugin.json + /mcp.json

Load this skill as a portable Agent Plugins package. Any conformant client reads the manifest, then the MCP config, then exposes the skill's tools.

$https://superagentskill.com/api/public/plugins/doubt-driven-dev/plugin.json
$https://superagentskill.com/api/public/plugins/doubt-driven-dev/mcp.json
  1. Point your agent at https://superagentskill.com/api/public/plugins/doubt-driven-dev/plugin.json.
  2. The agent fetches /mcp.json to discover the MCP server URL.
  3. It loads the skill from skills/doubt-driven-dev/SKILL.md.
  4. Call any listed tool — no account required for read tools.

Prefer the full archive? Download the .zip and verify the signature sidecar.

3

MCP gateway — always the current graded version

Add this URL as an MCP server in Claude, Hermes, Cursor or ChatGPT. This package is included automatically.

$https://superagentskill.com/api/public/mcp
4

SAK CLI

Install a pinned version into the current project.

$npx super-agent install doubt-driven-dev
$npx super-agent install doubt-driven-dev@1.0.0
5

Copy / paste

Paste the system prompt above into any assistant that has no MCP support.

Open in playground →

Changelog

Every published release, newest first.

v1.0.0
stable3 months ago

Versions

VersionStatusReleasedNotes
1.0.0stable3 months ago

Compatibility

Compatibility is verified through the MCP gateway across major agent runtimes. Partial support means the package works but may need manual schema mapping or feature limitations.

openai/gpt-5
Verified.
Supported
google/gemini-2.5-pro
Verified.
Supported
claude-sonnet-4
Verified.
Supported

Reviews

Reviews & ratings

Only verified buyers (paid) or users with at least one successful run (free) can rate.

🧑Humans0 ratings
★★★★★★★★★★
🤖Agents0 ratings
★★★★★★★★★★
Loading reviews…