Agent SkillsPaca-AI/paca › paca-estimate

paca-estimate

GitHub

基于斐波那契量表为Paca任务估算故事点。通过加载项目上下文、参考历史完成任务及分析复杂度/不确定性/测试面/集成点,提供校准后的估算值,并将结果写回任务描述。

skills/paca-estimate/SKILL.md Paca-AI/paca

Trigger Scenarios

任务缺少估算 冲刺规划前 团队需要优先级排序的规模评估 要求对积压工作进行规模估算

Install

npx skills add Paca-AI/paca --skill paca-estimate -g -y
More Options

Use without installing

npx skills use Paca-AI/paca@paca-estimate

指定 Agent (Claude Code)

npx skills add Paca-AI/paca --skill paca-estimate -a claude-code -g -y

安装 repo 全部 skill

npx skills add Paca-AI/paca --all -g -y

预览 repo 内 skill

npx skills add Paca-AI/paca --list

SKILL.md

Frontmatter
{
    "name": "paca-estimate",
    "description": "Estimate story points for Paca tasks using the Fibonacci scale, calibrated against recently completed reference tasks and project tech stack. Use when tasks are missing estimates, before sprint planning, when the team needs sizing for prioritization, or when asked to size a backlog.",
    "compatibility": "Requires Paca MCP server. Run \/paca-setup if Paca tools are not available."
}

You are estimating effort for tasks in Paca. Use Paca MCP tools throughout — never create local files.

If no task is specified, call list_tasks and focus on tasks in the current sprint or backlog that have no estimate yet — those are the most urgent to address.


Step 1 — Load project context

  1. Resolve task reference(s) from the user's message:
    • #42, ABC-42get_task_by_number
    • No reference → list_tasks; focus on unestimated tasks
  2. Call list_documents and search for documents titled or tagged with "estimation", "velocity", "definition of ready", "tech stack", or "architecture". Read the most relevant ones with get_document. Knowing the tech stack and team conventions is the difference between a calibrated and a random estimate.
  3. Call list_tasks filtered to recently completed (done) tasks to find reference points — "Task X was 3 pts, this feels similar" is more reliable than estimating in a vacuum.

Step 2 — Estimate each task

For each task, call get_task and reason through four dimensions:

  • Implementation complexity — number of layers touched, algorithmic difficulty
  • Uncertainty — how well-understood the work is; unknown → estimate higher
  • Test surface — unit tests, integration tests, edge cases to cover
  • Integration points — external APIs, databases, other services, third-party SDKs

Scale (Fibonacci): 1 · 2 · 3 · 5 · 8 · 13

  • 1–2 pts: simple, well-understood, < 1 day
  • 3–5 pts: moderate complexity or some unknowns, 1–3 days
  • 8 pts: complex or high uncertainty — consider whether /paca-breakdown would reduce risk
  • 13 pts: too large to estimate reliably — strongly recommend breaking down first

Calibrate against the reference tasks you found: if a reference task was 3 pts and this one feels about twice as hard, say 5–8 pts.

Show estimates with one-line justifications and ask the user to confirm or adjust.

Step 3 — Write estimates back

For each confirmed estimate, call update_task:

  • Prepend **Estimate:** N pts as the first line of the description (or update the custom field if the project has one — check list_custom_fields to see)
  • Include a one-line rationale so the reasoning is preserved

Report back: table of task number, title, and estimate for each task updated.


If Paca MCP is not connected

Paca MCP tools are not available. Run /paca-setup to configure the connection.


Tool reference

Tasks: get_task · get_task_by_number · list_tasks · update_task · list_task_statuses · list_custom_fields
Documents: list_documents · get_document
Projects: list_projects

Version History

  • 1a37f10 Current 2026-07-05 14:57

Same Skill Collection

skills/paca-breakdown/SKILL.md
skills/paca-clarify/SKILL.md
skills/paca-do/SKILL.md
skills/paca-doc/SKILL.md
skills/paca-epic/SKILL.md
skills/paca-prioritize/SKILL.md
skills/paca-setup/SKILL.md
skills/paca-sprint/SKILL.md
skills/paca-test/SKILL.md
skills/paca/SKILL.md

Metadata

Files
0
Version
1a37f10
Hash
63dbe5c8
Indexed
2026-07-05 14:57

Accueil - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-09 05:38
浙ICP备14020137号-1 $Carte des visiteurs$