wi-writer — ai-agent wi-writer, govctl, community, ai-agent, ide skills, governance

v1.0.0

关于此技能

非常适合需要结构化工作项管理和明确的验收标准的开发代理。 Write well-structured work items with proper acceptance criteria. Use when: (1) Creating work items, (2) Adding acceptance criteria, (3) User mentions work item, task, WI, or ticket

# 核心主题

govctl-org govctl-org
[99]
[8]
更新于: 3/10/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 4/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Concrete use-case guidance Explicit limitations and caution
Review Score
4/11
Quality Score
44
Canonical Locale
en
Detected Body Locale
en

非常适合需要结构化工作项管理和明确的验收标准的开发代理。 Write well-structured work items with proper acceptance criteria. Use when: (1) Creating work items, (2) Adding acceptance criteria, (3) User mentions work item, task, WI, or ticket

核心价值

赋予代理创建和管理具有明确描述、可执行的验收标准和使用治理即代码工具和命令(如govctl)进行进度跟踪的工作项,实现高效的软件开发和协作。

适用 Agent 类型

非常适合需要结构化工作项管理和明确的验收标准的开发代理。

赋予的主要能力 · wi-writer

使用明确的描述和验收标准创建工作项
跟踪进度并更新工作项日志
向工作项添加注释和参考以获得更好的上下文

! 使用限制与门槛

  • 需要govctl命令行工具
  • 特定于治理即代码工作流

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The page lacks a strong recommendation layer.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

wi-writer 是什么?

非常适合需要结构化工作项管理和明确的验收标准的开发代理。 Write well-structured work items with proper acceptance criteria. Use when: (1) Creating work items, (2) Adding acceptance criteria, (3) User mentions work item, task, WI, or ticket

如何安装 wi-writer?

运行命令:npx killer-skills add govctl-org/govctl。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

wi-writer 适用于哪些场景?

典型场景包括:使用明确的描述和验收标准创建工作项、跟踪进度并更新工作项日志、向工作项添加注释和参考以获得更好的上下文。

wi-writer 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

wi-writer 有哪些限制?

需要govctl命令行工具;特定于治理即代码工作流。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add govctl-org/govctl。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    wi-writer 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

wi-writer

安装 wi-writer,这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Work Item Writer

Write work items with clear descriptions and actionable acceptance criteria.

Quick Reference

bash
1govctl work new --active "<title>" 2govctl work set <WI-ID> description "Task scope description" 3govctl work add <WI-ID> acceptance_criteria "<category>: <description>" 4govctl work add <WI-ID> journal "Progress update" --scope module 5govctl work add <WI-ID> notes "Key observation" 6govctl work add <WI-ID> refs RFC-NNNN 7govctl work tick <WI-ID> acceptance_criteria "<pattern>" -s done 8govctl work move <WI-ID> done

Work Item Structure

Title

Concise, action-oriented. Describes what will be done.

  • Good: "Add validation for clause cross-references"
  • Bad: "Fix stuff" or "Work on the thing"

Description

Purpose: Task scope declaration — what needs to be done.

Replace the placeholder immediately. One paragraph explaining:

  • What the work accomplishes
  • Why it's needed
  • Any relevant context

Important: Description is for task scope, NOT execution tracking. Use journal for progress and outcomes, and notes for durable learnings.

Journal

Purpose: Execution process tracking — how the work is progressing.

Journal entries record progress updates, bug fixes, and verification results during execution. Each entry has:

  • date (required): ISO date "YYYY-MM-DD"
  • scope (optional): Topic/module identifier
  • content (required): Markdown text with details
bash
1# Add journal entry (date is auto-filled to today) 2govctl work add <WI-ID> journal "Added journal section rendering to work item output." 3 4# With scope (topic/module tag) 5govctl work add <WI-ID> journal "Fixed parser edge case" --scope parser 6 7# Multi-line via stdin 8govctl work add <WI-ID> journal --scope render --stdin <<'EOF' 9Completed the rendering pipeline. 10All snapshot tests updated. 11EOF

When to add journal entries:

  • After completing a significant chunk of work
  • When fixing bugs during implementation
  • After running verification gates
  • After a failed attempt that changed the next step

Notes

Purpose: Durable learnings — constraints, decisions, and retry rules to remember before the next step.

Notes are concise points recorded anytime, not just at completion. Use for:

  • Why an approach failed
  • What not to retry
  • Constraints or decisions future steps must obey
bash
1govctl work add <WI-ID> notes "Remember to update migration guide" 2govctl work add <WI-ID> notes "API is now async"

Acceptance Criteria

Every criterion MUST have a category prefix for changelog generation:

PrefixChangelog SectionAliases
add:Addedfeat:, feature:, added:
fix:Fixedfixed:
change:Changedchanged:, refactor:, perf:
remove:Removedremoved:
deprecate:Deprecateddeprecated:
security:Securitysec:
chore:(excluded)test:, docs:, ci:, build:
bash
1# Feature work 2govctl work add <WI-ID> acceptance_criteria "add: Implement clause validation" 3govctl work add <WI-ID> acceptance_criteria "add: Error messages include clause ID" 4 5# Bug fix 6govctl work add <WI-ID> acceptance_criteria "fix: Duplicate clause detection" 7 8# Internal 9govctl work add <WI-ID> acceptance_criteria "chore: All tests pass" 10govctl work add <WI-ID> acceptance_criteria "chore: govctl check passes"

References

Link to governing artifacts:

bash
1govctl work add <WI-ID> refs RFC-0001 2govctl work add <WI-ID> refs ADR-0023

Field Semantics Summary

FieldPurposeUpdate Pattern
descriptionTask scope declarationDefine once, rarely change
journalExecution process trackingAppend on each progress
notesDurable learningsAdd when future steps must remember something
acceptance_criteriaCompletion criteriaDefine then tick

Per ADR-0026: Keep description focused on "what", journal on "what happened", and notes on "what to remember next".

Writing Rules

Acceptance Criteria Quality

Each criterion should be:

  • Specific — "Add validate_refs() function" not "Add validation"
  • Testable — Can be verified as done/not-done with no ambiguity
  • Independent — Each criterion stands alone
  • Categorized — Always include the category prefix

Completion Flow

Work items cannot be marked done without ticking all criteria:

bash
1# Tick criteria as you complete them 2govctl work tick <WI-ID> acceptance_criteria "<pattern>" -s done 3 4# When all criteria are done, close the work item 5govctl work move <WI-ID> done

The chore: Pattern

Always add at least one chore: criterion for validation:

bash
1govctl work add <WI-ID> acceptance_criteria "chore: govctl check passes"

This ensures validation is an explicit gate, not an afterthought.

Common Mistakes

MistakeFix
Missing category prefixAlways use add:, fix:, chore:, etc.
Placeholder description left inReplace immediately with real description
Vague criteria: "Feature works"Specific: "add: CLI returns exit code 0 on success"
No chore: criterionAdd "chore: govctl check passes" or "chore: all tests pass"
No refs to governing artifactsLink RFCs/ADRs with work add <WI-ID> refs
Description used for trackingUse journal field for execution progress per ADR-0026
No journal entries for long taskAdd journal entries for significant progress updates

相关技能

寻找 wi-writer 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具