Docs & Knowledge · daymade/claude-code-skills
teams-channel-post-writer
Creates educational Teams channel posts for internal knowledge sharing about Claude Code features, tools, and best practices. Applies when writing posts, announcements, or documentation to teach colleagues effective Claude Code usage, announce new features, share productivity tips, or document lessons learned. Provides templates, writing guidelines, and structured approaches emphasizing concrete examples, underlying principles, and connections to best practices like context engineering. Activates for content involving Teams posts, channel announcements, feature documentation, or tip sharing.
L2 Local · Restricted workspaceV1 Commit-PinnedWrite FileDual-pass Audit
Control levels describe skill capabilities and suggested control measures; they do not represent quality or safety certifications, nor do they dictate usability. Usage decisions rest entirely with users and administrators. Different agent hosts apply varying constraints; do not assume hosts provide automatic protection. Third-party skill copyrights belong to their original authors. Use at your own risk.
1How It Works & Mechanism
It is a purely prompt-orchestrated skill: it contains no scripts or executable code. Its full capability is composed of 'a template + a writing guideline + a 5-step workflow', producing Markdown text rather than any programmatic output.
teams-channel-post-writer/SKILL.md
Start with the template in `assets/post-template.md` and fill in:
The entire directory contains only 3 files (SKILL.md / assets/post-template.md / references/writing-guidelines.md), with no scripts/ directory and no .py/.sh files.
The structure is standardized into 9 fill-in-the-blank sections (Headline → Hook → What It Is → How It Works → Why It Matters → Example in Action → Configuration → Call to Action → Further Reading), turning 'announcement writing' into a repeatable fill-in-the-blank task—the core mechanism ensuring output consistency.
teams-channel-post-writer/SKILL.md
1. **Title**: Use an emoji and clear description 2. **Introduction**: Include release date and brief context 3. **What it is**: 1-2 sentence explanation 4. **How to use it**: Show "Normal vs Better" pattern with explicit instructions 5. **Why use it**: Explain the underlying principle with 4 key benefits 6. **Examples**: Provide 3+ realistic, concrete prompts 7. **Options/Settings**: List key configurations or parameters 8. **Call-to-action**: End with actionable next step 9. **Learn more**: Link to authoritative resources
The template itself serves as a ready-to-copy skeleton file, where placeholder formats (📝 Normal / ⭐ Better, strictly 4 Benefits, strictly 3 example prompts) strictly mirror the 9-step requirements in SKILL.md.
teams-channel-post-writer/assets/post-template.md
📝 **Normal:** "[Example of typical approach]" ⭐ **Better:** "[Example of improved approach with explicit instructions]"
Template lines from '- **Benefit 1**: Explanation' to '- **Benefit 4**' and the three tiers of '- `option1` - Description' directly correspond to the '4 key benefits' and 'Key configurations' in steps 5 and 7 of SKILL.md.
Using 'Normal vs Better' rather than 'Wrong vs Correct' is a strict design decision aimed at preventing readers from feeling criticized—this is the most distinctive difference between this skill and generic announcement prompts, and it is codified in the quality checklist.
teams-channel-post-writer/references/writing-guidelines.md
### 2. Show, Don't Just Tell - Use "Normal vs Better" comparisons instead of "Wrong vs Correct" - Include 3+ concrete example prompts users can adapt - Provide realistic use cases from actual development workflows
Key Principles in SKILL.md also emphasize: 'Always include concrete examples users can adapt. Use "Normal vs Better" comparisons to demonstrate improvements without making readers feel criticized.'
There are mandatory pre-writing research requirements (check official release dates/versions, test behavior hands-on, locate authoritative sources, ensure info is up-to-date), treating 'accuracy' as a prerequisite for posting rather than an afterthought.
teams-channel-post-writer/SKILL.md
**Research checklist:** - [ ] Found official release date/version number - [ ] Verified feature behavior through testing or documentation - [ ] Identified authoritative sources to link to - [ ] Understood the underlying principle or best practice
Corresponds to the 4 steps in '## Research Requirements' within the guidelines file, with the last item being 'Check for updates: Ensure information is current'.
Content must 'connect to underlying principles' rather than merely describing features, explicitly using context engineering as an example (e.g., analogizing Explore agent to context offloading)—which is the core educational value advocated by this skill.
teams-channel-post-writer/SKILL.md
### Connect to Principles Don't just describe features—explain the underlying best practices. For example, connect the Explore agent to "context offloading" principles in context engineering.
Elaborated in `references/writing-guidelines.md`, while SKILL.md provides this as an illustrative example.
2Core Capabilities
01Ready-to-use Teams post template (9-section structure)
025-step workflow (Understand topic → Plan content → Draft with template → Review against guidelines → Save & share)
03Skeletons for two content patterns (Feature Announcement in 5 sections / Best Practice Guide in 6 sections)
04Tone and style guidelines (educational, professional yet approachable, actionable, concise and scannable)
05Formatting conventions (emoji in headers only, 📝/⭐ for Normal/Better, code blocks for prompts, numbered steps)
06Pre-publication quality checklist
07Fact-checking requirements (dates/versions sourced from changelog, verified working examples, links to authoritative sources)
3External Dependencies
| Kind | Dependency / Endpoint |
|---|---|
| network | 官方文档 / changelog（工作流要求去查发布日与版本号并引用权威来源；具体站点由使用者决定，skill 未硬编码端点） |
4Recommended Governance & Evidence
Suggested Controls for Safe Operation
For Agent Runtime
Restrict working directory
For Administrators
Retain operation logs
Evidence & Triggers (File Paths & Excerpts)
- 本地工作目录: File read/write & artifact generation: The draft is written to a local Markdown file by the agent (not by any bundled script): SKILL.md instructs 'Save the final post to you
Audit Notes: Evaluation basis: All 3 files in the directory are plain Markdown—no scripts/, no .py/.sh, and no executable code. There are no network request calls, credential or environment variable reads, or system commands. The only side effect is the agent saving the completed draft to a local Markdown file per instruction (hence categorized as 🔵 'Local read/write only, no network egress, no credentials' rather than 🟢 'No local file modifications'). Researching official documentation relies on the host agent's native tools; this skill hardcodes no endpoints or scraping logic. Key operational note: colleagues will treat the produced posts as factual reference, so the 'verify before posting' rule must be strictly adhered to.
5Second-Pass Verification
- [ok] 是否真的没有可执行资产（找反例：隐藏脚本、打包物、内联代码块） — glob/find 结果仅 3 个 .md 文件；全目录 grep '.py|.sh|#!/|subprocess|urllib|requests|eval(|exec(' 零命中；三个文件中的代码块全部是 Markdown 结构示例（如 '1. What is it? (with release date)'）。无隐藏资产。
- [ok] 『外部资源/工具』是否只有一项（是否漏掉了隐含依赖） — 第一遍只列了『官方文档/changelog（无固定端点）』。第二遍重新逐行核对：SKILL.md 提到 tree/ls 之类工具？无；提到任何 CLI？无；提到任何 URL 或域名？无（grep 'http' 全目录零命中）；提到任何包？无。规范里的外部资源要求是『Link to authoritative external resources when applicable』，由使用者填。结论：外部依赖仅此一项，且无端点可列。
- [ok] 模板与规范是否真的和 SKILL.md 的九步一致（防止文档内部互相矛盾） — 逐项对应：九步的 1-9 全部在 post-template.md 有对应占位（标题/New in [Tool] ([Date])/What is it?/📝Normal+⭐Better/Why use it? + 4 Benefit/Example prompts ×3/Key settings 3 档/Try it next time/Learn more）；规范文件的 Feature Announcements 5 段与 Best Practices 6 段模式是同一结构的两种裁剪，不冲突。
- [discrepancy] marketplace 关键词是否与正文内容相符 — .claude-plugin/marketplace.json 中该条目 keywords 含 'adaptive-cards'，但全目录 grep 'adaptive'（不分大小写）在 SKILL.md、assets/post-template.md、references/writing-guidelines.md 中零命中：正文只教 Markdown 排版（emoji/粗体/代码块/列表），从未涉及 Microsoft Adaptive Card 的 JSON schema 或发送方式。即登记词超出实际内容，属 marketplace 元数据的轻微夸大；相应地『发到 Teams』这一步在 skill 内没有任何机制或指引（只写 Markdown 文件、由人自行粘贴）。
- [ok] 『Save the final post』这一步是否有落盘机制（是否只是文字要求） — 确认为纯文字要求，无脚本执行：SKILL.md 第 5 步只写 'Save the final post to your team's documentation location with a descriptive filename like "Claude Code Tips.md" or "[Topic Name].md"'，落盘动作由宿主的文件写入工具完成。因此 security.file_writes 记的是 agent 级行为而非 skill 代码行为，已在字段中如此标注。
- [ok] pin commit 与 skill.path 是否与任务书一致 — git rev-parse HEAD = d5c4678cb5d4fd6acc9c922690df035dbd33d247；目录位于仓库根，相对路径 teams-channel-post-writer；本目录最后提交 878f947（2026-09-07）。GitHub API 复核 MIT / stars 1392 / pushed 2026-09-15T09:30:04Z。
6Verdict & Scenarios
Best for: Ideal for: Anyone within an internal team needing to clearly explain 'a new Claude Code feature or a practical best practice' to colleagues—especially well-suited for engineering teams accustomed to template-driven knowledge sharing and technical writers seeking consistent internal voice. As a pure-prompt asset with zero setup cost and zero runtime risk, it serves as an immediate starting baseline for customized writing guidelines.
Not for: Not suitable for: Programmatic posting or Teams card integration scenarios (provides no transmission channel or Adaptive Card support); scenarios requiring AI image generation or visual formatting (handles text structure only); external-facing marketing copy (the Normal/Better pedagogical paradigm mismatches external marketing); topics unrelated to Claude Code, where research requirements and principle connections lose their grounding.
Install Agent-Ready
① Verified Mirror 2026-09-15
Option A · Direct DownloadDownload teams-channel-post-writer.tar.gz
sha256:
Option B · Copy Guide for Agent9aefc4bf9f7ae3af…Agents automatically download and verify mirrors from this JSON guide.
② Upstream GitHub
GitHub Repo ↗
Pinned to commit d5c4678cb5.