comms
Skill2 starsChanged 6 months agoMITView on GitHub
Stakeholder communication templates for IT operations. This skill should be used when writing incident notifications, status page updates, maintenance announcements, or any communication to users, management, or other teams about IT service events. Provides severity-based tone guidance and audience-aware messaging.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- musterd-io/musterdtheir own version, first seen Nov 1, 2026
- mikhin/claude-skillstheir own version, first seen Oct 13, 2026
- chriswestt/claude-skillstheir own version, first seen Oct 9, 2026
- grandamenium/cortextostheir own version, first seen Oct 9, 2026
- sandraschi/comms-mcptheir own version, first seen Oct 8, 2026
- skyf0xx/gambittheir own version, first seen Sep 30, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- grandamenium/cortextos★ 106same name
- skyf0xx/gambit★ 29same name
- cacardinal/laila★ 1same name
- michaelsvanbeek/personal-agent-skills★ 1same name
- musterd-io/musterd★ 1same name
- sandraschi/comms-mcp★ 1same name
- chriswestt/claude-skills★ 0same name
- Endika/eskills★ 0same name
- mikhin/claude-skills★ 0same name
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 repository8 other files it gives its agents.
- ai-changeSkill
- change-requestSkill
- done-opsSkill
- incidentSkill
- itilSkill
- postmortemSkill
- problemSkill
- statuspageSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
1
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 58
Every operational communication follows this structure:
“Common” is measured: kept by at least 6 in 10 of the 9 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
IT Operations Communication
Templates and guidance for stakeholder communication during incidents, changes, and maintenance. All output in English by default; preview in the user's language before writing to file.
Related Skills
- /incident — loads this skill for incident notifications
- /statuspage — loads this skill for status page updates
- itil — provides priority classification that determines communication tone
Core Principles
- Impact-focused, not technical — describe what users experience, not what broke internally
- Honest but controlled — acknowledge the issue without exposing sensitive infrastructure details
- Predictable cadence — always include "Next update by [time]" to reduce anxiety
- Severity-appropriate tone — match urgency to priority level
- Audience-aware — tailor detail level to the recipient group
Tone by Priority Level
| Priority | Tone | Cadence | Example Opening |
| P1 | Urgent, direct, action-oriented | Every 15-30 min | "We are experiencing a major service disruption..." |
| P2 | Serious, informative | Every 30-60 min | "We are aware of issues affecting..." |
| P3 | Informative, measured | When meaningful updates occur | "Some users may notice..." |
| P4 | Routine, brief | At resolution | "A minor issue has been identified..." |
Audience Adaptation
| Audience | Detail Level | Focus |
| End users | Minimal technical detail | What is affected, workaround, ETA |
| Management | Business impact + timeline | Revenue/productivity impact, resource allocation, ETA |
| Technical teams | Full technical detail | Systems affected, error codes, diagnostic steps |
| External (statuspage) | Impact-focused, no internal names | Service status, user-facing impact, ETA |
What to Include vs Exclude
| Include | Exclude |
| Affected service (user-facing name) | Internal system names, IP addresses |
| User impact description | Root cause details during active incidents |
| Current status and actions being taken | Names of individuals responsible |
| Estimated time to resolution (if known) | Security-sensitive information |
| Workaround instructions (if available) | Blame or fault attribution |
| Next update time | Speculative root cause |
Communication Structure
Every operational communication follows this structure:
1. Status — current state (one sentence)
2. Impact — what users experience
3. Action — what is being done
4. ETA — when to expect resolution or next update
5. Workaround — if availableAdditional Resources
Reference Files
references/incident-templates.md— Full notification templates for each incident phase (initial, update, resolution), by priority level, for each audience typereferences/statuspage-templates.md— Status page update templates following the Investigating/Identified/Monitoring/Resolved lifecycle, compatible with Atlassian Statuspage and Instatus
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.