internal-comms
Skill2 starsChanged 4 months agoMITView on GitHub
Write clear, well-structured internal communications — incident reports, post-mortems, launch announcements, team updates, all-hands summaries, 3P updates (Progress/Plans/Problems), project status updates, leadership briefings, and FAQs. Use when the user needs to communicate something to their team, engineering org, or company — especially under time pressure or when the message needs to be precise and well-received.
193 other projects use a version of this.
Adopted by
Most recently taken up by
- rvdbreemen/OTGW-firmwaretheir own version, first seen Nov 8, 2026
- BrightGold70/skillstheir own version, first seen Nov 8, 2026
- ppswdev/pp_skillstheir own version, first seen Nov 8, 2026
- Liang-MH/skillstheir own version, first seen Nov 8, 2026
- amanuelmamo7/Skillstheir own version, first seen Nov 7, 2026
- The-AIOS/aiostheir own version, first seen Nov 3, 2026
Used with
Projects with it also use skill-share, academy-guide and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ArogyaReddySkillskill-share
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Also in 23 projects that use this
AnthropicSkillacademy-guide
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.
Also in 7 projects that use this
ArogyaReddySkillraffle-winner-picker
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
Also in 27 projects that use this
JetBrainsSkillslack-gif-creator
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack.
Also in 126 projects that use this
mjunaidcaSkillbuilding-chatgpt-apps
Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode configuration. NOT when building standard MCP servers without widgets (use building-mcp-servers skill instead).
Also in 4 projects that use this
mjunaidcaSkillbuilding-chat-interfaces
Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with AI agents, adding auth to chat, injecting user/page context, or implementing httpOnly cookie proxies. Covers ChatKitServer, useChatKit, and MCP auth patterns. NOT when building simple chatbots without persistence or custom agent integration.
Also in 4 projects that use this
- +6 more from mjunaidca
Other versions193 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 193
- anthropics/skills★ 189ksame name
- ComposioHQ/awesome-claude-skills★ 75ksame name
- ComposioHQ/awesome-codex-skills★ 17ksame name
- composio-community/awesome-codex-skills★ 16ksame name
- Prat011/awesome-llm-skills★ 1.7ksame name
- google/adk-js★ 1.5ksame name
- ChenglinPoly/infiAgent★ 1.2ksame name
- polyuiislab/infiAgent★ 1.2ksame name
- JetBrains/skills★ 386same name
- zephyrwang6/myskill★ 339same name
183 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository48 other files it gives its agents.
- agent-memorySkill
- ai-engineerSkill
- api-designSkill
- autoplanSkill
- backend-devSkill
- benchmarkSkill
- brand-guidelinesSkill
- code-reviewerSkill
- commit-messageSkill
- database-architectSkill
- data-engineerSkill
- debuggerSkill
- design-explorerSkill
- devex-engineerSkill
- devops-platformSkill
- doc-coauthoringSkill
- forward-deployment-engineerSkill
- frontend-designSkill
- java-developmentSkill
- land-and-deploySkill
- mcp-builderSkill
- office-hoursSkill
- pdfSkill
- performance-optimizerSkill
- plan-ceo-reviewSkill
- plan-design-reviewSkill
- plan-eng-reviewSkill
- pptxSkill
- product-engineerSkill
- prompt-engineerSkill
- python-developmentSkill
- qa-engineerSkill
- react-developmentSkill
- release-engineerSkill
- research-agentSkill
- retro-engineerSkill
- safety-guardrailsSkill
- security-engineerSkill
- skill-creatorSkill
- spec-authorSkill
- sre-canarySkill
- system-designSkill
- technical-writerSkill
- test-writerSkill
- theme-factorySkill
- typescript-developmentSkill
- webapp-testingSkill
- xlsxSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 184 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Write for the reader's context, not your own.
- Distinctive: line 17
One message, one action: Every communication has exactly one thing it wants the reader to do: approve, acknowledge, unblock, attend, or …
- Distinctive: line 20
Never bury the ask: If you need something from the reader, state it in the first 2 sentences or in a clearly labeled "Action Required" …
- Distinctive: line 29
Use when: a production incident, outage, data issue, or security event occurred and needs to be documented.
- Distinctive: line 82
Use when: weekly or sprint team updates, project status reports, engineering manager updates to leadership.
- Distinctive: line 112
Use when: shipping a feature, releasing a product, reaching a milestone — communicating to the broader team or company.
- Distinctive: line 154
Use when: updating executives, board members, or senior leadership on a project, initiative, or situation.
- Distinctive: line 196
Use when: summarizing a company meeting, all-hands, or town hall for those who couldn't attend or as a written record.
- Distinctive: line 236
Use when: a change, launch, or situation is generating repeated questions and you need a single source of truth.
“Common” is measured: kept by at least 6 in 10 of the 184 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Internal Communications
Internal comms fail in two ways: too long (nobody reads them) or too vague (nobody acts on them). The goal is a message that gets read, understood, and acted upon — by the right people, in the right amount of time.
Write for the reader's context, not your own. The reader is busy, has incomplete context, and will skim before they read. Lead with the conclusion.
Internal Comms Principles
- Lead with the bottom line. The most important thing goes first. Background and rationale come after. Executives and busy engineers read the first paragraph and stop.
- One message, one action. Every communication has exactly one thing it wants the reader to do: approve, acknowledge, unblock, attend, or stay informed. Name it explicitly.
- Shorter is always harder to write and easier to read. Spend the extra time to cut.
- Tone matches urgency and audience. A P0 incident update is clinical and fast. A team launch announcement is warm and energetic. Read the room.
- Never bury the ask. If you need something from the reader, state it in the first 2 sentences or in a clearly labeled "Action Required" section.
- Facts over feelings in incident reports. What happened, what broke, what was the impact, what we did, what we're doing to prevent recurrence. No blame. No speculation.
Communication Types
1. Incident Report / Post-Mortem
Use when: a production incident, outage, data issue, or security event occurred and needs to be documented.
Format:
## Incident Report — [Service/Feature] — [Date]
**Severity:** P0 / P1 / P2
**Status:** Resolved / Ongoing / Monitoring
**Duration:** [start time] → [end time] ([X hours Y minutes])
**Impact:** [Who was affected, how many users, what they couldn't do]
---
### Timeline
| Time (UTC) | Event |
|---|---|
| HH:MM | Monitoring alert fired for [metric] |
| HH:MM | On-call engineer paged |
| HH:MM | Root cause identified: [one sentence] |
| HH:MM | Fix deployed to production |
| HH:MM | Service confirmed healthy |
### Root Cause
[One paragraph. What broke, why it broke, what conditions triggered it.]
### Impact
- **Users affected:** [number or percentage]
- **Duration of impact:** [X hours Y minutes]
- **Services affected:** [list]
- **Data loss:** [Yes/No — if yes, describe]
### What We Did
[Ordered list of actions taken during the incident]
### Action Items
| Action | Owner | Due Date | Status |
|---|---|---|---|
| [Prevent recurrence action] | @engineer | YYYY-MM-DD | Open |
| [Monitoring improvement] | @engineer | YYYY-MM-DD | Open |
### What Went Well
- [Something the team handled well]
### What Could Be Improved
- [Process or system gap revealed by this incident]Tone: Clinical, factual, blameless. No speculation about causes that aren't confirmed. No emotion.
2. 3P Update (Progress / Plans / Problems)
Use when: weekly or sprint team updates, project status reports, engineering manager updates to leadership.
Format:
## [Team/Project Name] — Week of [Date]
### 🟢 Progress (what shipped or was completed)
- [Shipped feature X to 100% of users — link]
- [Completed migration of Y service to new infrastructure]
- [Closed 12 P1 bugs from last sprint]
### 📋 Plans (what's happening next week)
- [Ship feature Z — targeting Thursday]
- [Begin load testing for the Q3 launch]
- [1:1s with all team members re: H2 goals]
### 🔴 Problems (blockers, risks, things leadership should know)
- **[BLOCKER]** Design review for feature Z still pending — need approval from @designlead by Tuesday or we slip the Thursday target
- **[RISK]** Vendor API rate limits may affect the integration launch — investigating alternative approach
- **[FYI]** Two engineers on PTO next week, capacity is reduced
**Requests:** [What you need from the reader — approval, unblocking, decision]Tone: Direct, concise. Problems section is the most important — don't soften it. Leaders need accurate signal, not reassurance.
3. Launch Announcement
Use when: shipping a feature, releasing a product, reaching a milestone — communicating to the broader team or company.
Format:
## 🚀 [Feature/Product Name] is live
**What shipped:** [One sentence — what users can now do that they couldn't before]
**Why it matters:** [One sentence on the business or user impact]
**Who it affects:** [All users / Enterprise customers / Internal teams / etc.]
---
### What's new
[2-4 bullet points. Concrete, specific, user-facing.]
- Users can now [specific action]
- [Metric improvement]: [X% faster / Y fewer steps / Z hours saved]
- [New capability]: [describe]
### How to access it
[Clear instructions — link, navigation path, or contact]
### Numbers (if available)
- [Metric 1]: [value]
- [Metric 2]: [value]
### What's next
[One sentence on the next milestone or what the team is working on now]
---
**Questions?** [Slack channel / DRI name / documentation link]
**Feedback?** [How to submit it]Tone: Energetic but not hype-y. Lead with what users can do, not what the team built. Concrete metrics > adjectives.
4. Leadership Update / Executive Briefing
Use when: updating executives, board members, or senior leadership on a project, initiative, or situation.
Format:
## [Project/Initiative] — [Date]
**Status:** On Track / At Risk / Off Track
**Owner:** [Name]
**Ask:** [One sentence — what decision or action is needed from leadership]
---
### Summary (3 sentences max)
[What we're doing, where we are, what we need.]
### Progress vs. Plan
| Milestone | Target | Status |
|---|---|---|
| [Milestone 1] | [Date] | ✅ Complete |
| [Milestone 2] | [Date] | 🟡 At Risk — [one sentence why] |
| [Milestone 3] | [Date] | ⬜ Not started |
### Key Risks
| Risk | Impact | Mitigation |
|---|---|---|
| [Risk description] | High / Medium / Low | [What we're doing about it] |
### Decision Needed
[If applicable: what decision, by when, what the options are]
### For More Detail
[Link to full project doc, dashboard, or Slack channel]Tone: Concise, precise. No padding. Executives read this in 90 seconds or less — every word must earn its place.
5. All-Hands / Town Hall Summary
Use when: summarizing a company meeting, all-hands, or town hall for those who couldn't attend or as a written record.
Format:
## [Company/Team] All-Hands — [Date]
**Attendees:** [X people] | **Recording:** [link if available]
---
### Key Announcements
1. [Most important announcement — one sentence]
2. [Second announcement]
3. [Third announcement]
### By the Numbers
- [Metric that was shared] — [value]
- [Metric] — [value]
### Q&A Highlights
**Q: [question that came up]**
A: [answer given]
**Q: [question]**
A: [answer]
### What's Next
- [Next milestone or event]
- [Deadline or decision coming up]
### Resources
- [Link to slides]
- [Link to recording]
- [Link to further reading]6. FAQ / Common Questions Response
Use when: a change, launch, or situation is generating repeated questions and you need a single source of truth.
Format:
## FAQ — [Topic]
*Last updated: [date] | Questions? [Slack channel or contact]*
---
**Q: [Most common question]**
A: [Direct answer. One paragraph max. Link to more detail if needed.]
---
**Q: [Second most common question]**
A: [Answer]
---
**Q: What if I have a question not covered here?**
A: [How to get help — Slack channel, DRI, form, etc.]Tone: Clear and direct. Answer what was actually asked, not a softer version of it. If the answer is "we don't know yet," say so.
Writing Checklist (Apply to Every Communication)
Before writing:
- What is the single most important thing this message needs to communicate?
- What action (if any) do I need from the reader?
- Who is the audience and what do they already know?
While writing:
- Does the first paragraph contain the most important information?
- Is the ask or action item explicitly stated?
- Is every sentence necessary?
- Are there any weasel words? ("somewhat", "might", "could consider")
- Is the tone right for the urgency and audience?
Before sending:
- Read it as the busiest possible recipient — does it land in 30 seconds?
- Would someone who missed all context understand what happened and what's needed?
- Is there anything that could be misread or cause alarm without context?
- Are all facts verified? No speculation presented as fact?
Tone Guide by Situation
| Situation | Tone | Key words to use | Key words to avoid |
| P0 incident | Clinical, factual, calm | "confirmed", "identified", "resolved" | "disaster", "crazy", "somehow" |
| Launch announcement | Warm, energetic, specific | "now", "ship", "live" | "excited to announce", "proud to share" |
| Bad news / setback | Direct, honest, forward-looking | "we missed", "here's what happened", "here's the plan" | "unfortunately", "regrettably", "challenging" |
| Leadership update | Precise, concise, confident | "on track", "at risk", "decision needed" | "I feel", "hopefully", "things are going well" |
| Team recognition | Specific, genuine | Name the person, name the impact | "great job", "amazing work" (without specifics) |
Definition of Done — Internal Comms
- Communication type identified — correct template applied
- Bottom line / key message stated in first 1-2 sentences
- Ask or action item explicitly named (or confirmed there is none)
- Facts verified — no speculation presented as fact
- Tone matches audience and urgency
- All weasel words removed
- Unnecessary context trimmed — reader doesn't need the full story to act
- Relevant links included for those who want more detail
- Clear contact or channel for questions
- Proofread — no typos in names, dates, or metrics
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

