Menu
Research official documentation for technologies in a spec, generating actionable guides for implementation planning
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | tech-research |
| description | Research official documentation for technologies in a spec, generating actionable guides for implementation planning |
After a spec document is created during brainstorming, use this skill to deeply research the official documentation of technologies mentioned in the spec. This generates a directly actionable technology guide including best practices, syntax, core patterns, and common pitfalls for specific use cases.
Trigger: User requests research, typically after spec approval in brainstorming.
Output: A comprehensive markdown document saved to docs/superpowers/research/YYYY-MM-DD-<topic>-tech-research.md
Next step: The generated guide feeds directly into writing-plans for implementation planning.
流程: brainstorming 创建 spec → 用户选择是否 research → 如是则执行研究 → 输出给 writing-plans
Use when:
Skip when:
Read the spec document and identify all technologies, frameworks, libraries, and tools mentioned.
Important: Do NOT use latest stable versions. Always check the project's actual installed versions first.
npm packages:
npm ls <package-name> --depth=0 | sed -n "s/.*<package-name>@([0-9.]*).*/\1/p"
Python packages:
pip show <package-name> | grep Version
Docker images:
docker images <image-name> --format "{{.Tag}}"
Go modules:
go list -m <module-name>
If a technology is not installed in the project, note it as "not currently in project" — research the version implied by the spec or latest stable if unspecified.
For each technology (with resolved version), dispatch a parallel subagent research task. Group related technologies when they share documentation (e.g., React + React Hooks).
Agent File: agents/tech-researcher.md
Dispatch:
Agent({
description: `Research ${tech.name} for ${specTopic}`,
prompt: readFile("agents/tech-researcher.md") + `\n\nInput:\n- TECHNOLOGY: ${tech.name}\n- PROJECT_VERSION: ${tech.resolvedVersion}\n- SPEC_USE_CASE: ${tech.purposeInSpec}\n- OUTPUT_PATH: docs/superpowers/research/temp-${tech.slug}.md`,
subagent_type: "general-purpose",
name: `researcher-${tech.slug}`
})
Spawn all research agents concurrently. Wait for all to complete before proceeding to synthesis.
Monitoring:
Merge all research into a single markdown document.
See agents/tech-researcher.md "Output Template" section for the complete template structure.
After research is complete:
"Technology research complete and saved to
docs/superpowers/research/<filename>.md. This guide covers [N] technologies with best practices, core patterns, and identified pitfalls.Ready to proceed with writing-plans, or would you like me to dive deeper into any specific technology?"
Use when you have a spec or requirements for a multi-step task, before touching code
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when starting implementation tasks and need to research dependencies and find reference implementations before writing any code
Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service -- even for well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. Your training data may not reflect recent API changes or version updates. Always use for: API syntax questions, configuration options, version migration issues, "how do I" questions mentioning a library name, debugging that involves library-specific behavior, setup instructions, and CLI tool usage. Use even when you think you know the answer -- do not rely on training data for API details, signatures, or configuration options as they are frequently outdated. Always verify against current docs. Prefer this over web search for library documentation and API details.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies