본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

agent-estimation

hjw21century 제작

Coding Agents & IDEs
—아직 평가 없음
내 평가

요약

Accurately estimate AI agent work effort using the agent's own operational units (tool-call rounds) instead.

설명

이 스킬이 하는 일

Estimates AI agent task effort using tool-call rounds as the primary unit instead of human developer time. Decomposes tasks into modules, applies risk coefficients, and converts to wallclock time only at the final step. Structured output includes a module breakdown table, risk factors, and a time range.

Avoids the systematic overestimation that occurs when agents anchor to human developer timelines from training data, producing estimates grounded in actual agent iteration speed.

사용 시점

  • Scoping a coding task before starting an agent session
  • Comparing two implementation approaches by round cost
  • Setting realistic expectations with a client on agent-assisted work
  • Identifying which modules carry the most schedule risk
  • Deciding whether a task fits in one session or needs to be split

예시 워크플로

입력

User asks: How long will it take to build a custom OAuth2 integration with a third-party API?

에이전트
  1. 1

    Decompose the task into modules: token exchange flow, refresh logic, API client wrapper, error handling

  2. 2

    Estimate base rounds per module using complexity anchors from the skill table

  3. 3

    Assign risk coefficients based on API documentation quality and platform quirks

  4. 4

    Sum effective rounds across modules and add 10-20% for integration

  5. 5

    Convert total rounds to wallclock time at 3 min/round and output the structured markdown table

출력

Markdown estimation table with per-module round counts, risk levels, integration overhead, and a final wallclock range of 45-60 minutes

설치

clawhub install hjw21century/agent-estimation

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크