Agent助手
- 作者仓库星标 4,456
- 作者更新于 实时读取
- 作者仓库 Product-Manager-Skills
- 领域
- 通用
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @deanpeters · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: skill-authoring-workflow
description: Turn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo…
category: 通用
runtime: 无特殊运行时
---
# skill-authoring-workflow 输出预览
## PART A: 任务判断
- 适用问题:通用任务拆解、检查和交付。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Purpose / Key Concepts / Dogfood First”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于通用任务拆解、检查和交付,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Purpose / Key Concepts / Dogfood First”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件;主要在本地完成;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文没有稳定的斜杠命令要求。安装验证后通常全局生效,直接在对话里点名这个 Skill 并描述任务即可。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件。
先用一个小任务确认它会围绕“Purpose / Key Concepts / Dogfood First”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: skill-authoring-workflow
description: Turn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo…
category: 通用
source: deanpeters/Product-Manager-Skills
---
# skill-authoring-workflow
## 什么时候使用
- 把通用方向的常用动作沉淀成 Agent 可调用的技能 适合处理通用任务拆解、检查、交付和复盘,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤;通常不需要额外…
- 面向通用任务拆解、检查和交付,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Purpose / Key Concepts / Dogfood First」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件;主要在本地完成;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "skill-authoring-workflow" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Purpose / Key Concepts / Dogfood First
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Purpose
Create or update PM skills without chaos. This workflow turns rough notes, workshop content, or half-baked prompt dumps into compliant skills/<skill-name>/SKILL.md assets that actually pass validation and belong in this repo.
Use it when you want to ship a new skill without "looks good to me" roulette.
Key Concepts
Dogfood First
Use repo-native tools and standards before inventing a custom process:
scripts/find-a-skill.shscripts/add-a-skill.shscripts/build-a-skill.shscripts/test-a-skill.shscripts/check-skill-metadata.py
Pick the Right Creation Path
- Guided wizard (
build-a-skill.sh): Best when you have an idea but not final prose. - Content-first generator (
add-a-skill.sh): Best when you already have source content. - Manual edit + validate: Best for tightening an existing skill.
Definition of Done (No Exceptions)
A skill is done only when:
- Frontmatter is valid (
name,description,intent,type) - Section order is compliant
- Metadata limits are respected (
name<= 64 chars,description<= 200 chars) - Description says both what the skill does and when to use it
- Intent carries the fuller repo-facing summary without replacing the trigger-oriented description
- Cross-references resolve
- README catalog counts and tables are updated (if adding/removing skills)
Facilitation Source of Truth
When running this workflow as a guided conversation, use workshop-facilitation as the interaction protocol.
It defines:
- session heads-up + entry mode (Guided, Context dump, Best guess)
- one-question turns with plain-language prompts
- progress labels (for example, Context Qx/8 and Scoring Qx/5)
- interruption handling and pause/resume behavior
- numbered recommendations at decision points
- quick-select numbered response options for regular questions (include
Other (specify)when useful)
This file defines the workflow sequence and domain-specific outputs. If there is a conflict, follow this file's workflow logic.
Application
Phase 1: Preflight (Avoid Duplicate Work)
- Search for overlapping skills:
./scripts/find-a-skill.sh --keyword "<topic>"
- Decide type:
- Component: one artifact/template
- Interactive: 3-5 adaptive questions + numbered options
- Workflow: multi-phase orchestration
Phase 2: Generate Draft
If you have source material:
./scripts/add-a-skill.sh research/your-framework.md
If you want guided prompts:
./scripts/build-a-skill.sh
Phase 3: Tighten the Skill
Manually review for:
- Clear "when to use" guidance
- One concrete example
- One explicit anti-pattern
- No filler or vague consultant-speak
Phase 4: Validate Hard
Run strict checks before thinking about commit:
./scripts/test-a-skill.sh --skill <skill-name> --smoke
python3 scripts/check-skill-metadata.py skills/<skill-name>/SKILL.md
python3 scripts/check-skill-triggers.py skills/<skill-name>/SKILL.md --show-cases
Phase 5: Integrate with Repo Docs
If this is a new skill:
- Add it to the correct README category table
- Update skill totals and category counts
- Verify link paths resolve
Phase 6: Optional Packaging
If targeting Claude custom skill upload:
./scripts/zip-a-skill.sh --skill <skill-name>
# or zip one category:
./scripts/zip-a-skill.sh --type component --output dist/skill-zips
# or use a curated starter preset:
./scripts/zip-a-skill.sh --preset core-pm --output dist/skill-zips
Examples
Example: Turn Workshop Notes into a Skill
Input: research/pricing-workshop-notes.md
Goal: new interactive advisor
./scripts/add-a-skill.sh research/pricing-workshop-notes.md
./scripts/test-a-skill.sh --skill <new-skill-name> --smoke
python3 scripts/check-skill-metadata.py skills/<new-skill-name>/SKILL.md
Expected result:
- New skill folder exists
- Skill passes structural and metadata checks
- README catalog entry added/updated
Anti-Pattern Example
"We wrote a cool skill, skipped validation, forgot README counts, and shipped anyway."
Result:
- Broken references
- Inconsistent catalog numbers
- Confusion for contributors and users
Common Pitfalls
- Shipping vibes, not standards.
- Choosing
workflowwhen the task is really a component template. - Bloated descriptions that exceed upload limits.
- Descriptions that say what the skill is but not when Claude should trigger it.
- Descriptions that silently hit the 200-char limit and get cut off mid-thought.
- Letting
intentbecome a substitute for a weak trigger description. - Forgetting to update README counts after adding a skill.
- Treating generated output as final without review.
References
README.mdAGENTS.mdCLAUDE.mddocs/Building PM Skills.mddocs/Add-a-Skill Utility Guide.md- Anthropic's Complete Guide to Building Skills for Claude
scripts/add-a-skill.shscripts/build-a-skill.shscripts/find-a-skill.shscripts/test-a-skill.shscripts/check-skill-metadata.pyscripts/check-skill-triggers.pyscripts/zip-a-skill.sh
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核