Skip to content
Automation
Skill

/research-first-dev

Research-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs before any implementation begins.

From plugin
babysitter
1.8k200 skills3 agents21 commands1 MCP
Install
$ npx -y skills add a5c-ai/babysitter --skill research-first-dev --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/research-first-dev

Context preview

The summary Claude sees to decide when to auto-load this skill.

Research-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs before any implementation begins.

SKILL.md

research-first-dev.SKILL.md
name: research-first-dev
description: Research-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs before any implementation begins.
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, WebSearch, WebFetch
graph:
  domains: [domain:software-engineering]
  skillAreas: [skill-area:agentic-loops, skill-area:orchestration-loop]
  workflows: [workflow:feature-development]
  topics: [topic:developer-experience]
  roles: [role:tech-lead, role:backend-engineer]
  • Parse the request into specific technical requirements
  • Identify the domain and relevant technology stack
  • List known constraints (time, resources, compatibility)
  • Define success criteria

2. Existing Solution Search

  • Search GitHub for similar implementations
  • Check package registries (npm, PyPI, crates.io, etc.)
  • Review documentation for framework-specific solutions
  • Identify relevant design patterns
  • Check for known anti-patterns to avoid

3. Alternative Brainstorming

  • Generate at least 3 alternative approaches
  • Include a "build" option and at least one "buy/reuse" option
  • Consider unconventional approaches

4. Trade-Off Evaluation

  • Complexity: implementation effort, learning curve
  • Time: development timeline, time-to-value
  • Risk: failure modes, dependency risks, maintenance burden
  • Scalability: growth limits, performance under load
  • Score each alternative on all 4 axes

5. Recommendation

  • Rank alternatives by composite score
  • Provide clear recommendation with justification
  • Include risk mitigation plan for chosen approach
  • Define go/no-go criteria

Iterative Retrieval

  • Start broad, narrow based on findings
  • Use confidence scoring to decide when to stop
  • Maximum 3 retrieval rounds per topic
  • Cache findings for reuse in subsequent phases

When to Use

  • New feature development (always)
  • Architecture changes
  • Technology selection
  • Dependency evaluation
  • Performance optimization strategy

Agents Used

  • `planner` (primary consumer)
  • `architect` (architecture-specific research)
Read more
Ships withbabysitter

Enforce obedience on agentic workforces. Manage extremely complex workflows through deterministic, hallucination-free self-orchestration.

Get the whole plugin

Other skills on babysitter.