responding-to-incidents
Skill0 starsChanged 9 days agoMITView on GitHub
Runs incident response in Uptimely one confirmed step at a time: declares incidents, acknowledges or resolves incidents and alerts, raises alerts, and runs on-demand monitor checks. Use when the user asks to 'declare an incident for the checkout API', 'acknowledge that alert', 'resolve the incident', 'mark the outage resolved', 'check the landing page now', 'raise an alert', or handle an outage or downtime. Every write is confirmed first because it can notify people, hit a real URL, or change a status page.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- EvilFreelancer/secastheir own version, first seen Oct 15, 2026
- FlyFission/nuclear-grade-context-engineeringtheir own version, first seen Oct 13, 2026
- EvilFreelancer/secstheir own version, first seen Aug 8, 2026
- dcs-soni/skillstheir own version, first seen Jan 12, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- FlyFission/nuclear-grade-context-engineering★ 33same name
- EvilFreelancer/secas★ 11same name
- EvilFreelancer/secs★ 11same name
- dcs-soni/skills★ 1same 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 repository66 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adding-uptime-monitorsSkill
- analyzing-page-performanceSkill
- booking-meetingsSkill
- building-onboarding-workflowsSkill
- building-study-guidesSkill
- capturing-tasksSkill
- capturing-web-pagesSkill
- chasing-unpaid-invoicesSkill
- checking-domain-connectionsSkill
- checking-email-deliverabilitySkill
- checking-notification-deliverySkill
- checking-uptime-statusSkill
- cleaning-up-bookkeepingSkill
- connecting-customer-domainsSkill
- discussing-buildsSkill
- drafting-invoicesSkill
- drafting-social-postsSkill
- editing-demosSkill
- editing-page-draftsSkill
- extracting-document-textSkill
- finding-meeting-timesSkill
- handling-flaky-changesSkill
- investigating-tasksSkill
- making-demo-videosSkill
- managing-bookingsSkill
- managing-content-calendarSkill
- managing-demosSkill
- managing-voice-librarySkill
- planning-revisionSkill
- preflighting-domainsSkill
- publishing-pagesSkill
- reading-financial-reportsSkill
- reading-text-aloudSkill
- reading-web-pagesSkill
- reporting-snapvisor-usageSkill
- researching-course-materialSkill
- researching-summary-librarySkill
- reviewing-email-performanceSkill
- reviewing-notification-workflowsSkill
- reviewing-social-performanceSkill
- reviewing-visual-buildsSkill
- reviewing-workloadSkill
- searching-getitdone-api-docsSkill
- sending-email-campaignsSkill
- sending-notificationsSkill
- setup-bioflowSkill
- setup-calySkill
- setup-demofySkill
- setup-dodomainSkill
- setup-getitdoneSkill
- setup-notiflySkill
- setup-postifySkill
- setup-sendlySkill
- setup-shortySkill
- setup-snapvisorSkill
- setup-superbooksSkill
- setup-unotesSkill
- setup-upapiSkill
- setup-uptimelySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 1 is distinctive, and 6 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Every tool in this skill comes from the uptimely MCP server, the Uptimely connector, and is written here as uptimely:<tool>.
- Very specific: line 15
Tools listed by name: call them directly, for example uptimely:uptimely_monitor_list.
- Very specific: line 38
Before an incident or alert change, read the current record with uptimely:uptimely_incident_get or uptimely:uptimely_alert_list so you do …
- Very specific: line 39
Before a declare or a state change, call uptimely:uptimely_on_call_current so you can say who may be notified.
- Distinctive: line 47
Never call a write operation without the user's explicit yes for that specific action.
- Very specific: line 48
Never put more than one write in a uptimely:execute_typescript program, and never add a write to a program that reads data.
- Very specific: line 50
If a write operation is not reachable, the user did not grant its write scope (monitors:write, incidents:write, or alerts:write).
“Common” is measured: kept by at least 6 in 10 of the 4 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
<!-- Generated from plugins/uptimely/skills/responding-to-incidents/SKILL.md by scripts/sync-skills.mjs. Edit the plugin copy, then run the script. -->Uptimely incident response
Take incident actions on the user's behalf, one confirmed step at a time.
Connecting and calling the tools
Every tool in this skill comes from the uptimely MCP server, the Uptimely connector, and is written here as uptimely:<tool>.
- Tools listed by name: call them directly, for example
uptimely:uptimely_monitor_list. - Only
uptimely:search_toolsanduptimely:execute_typescriptlisted (Code Mode, the default): calluptimely:search_toolsfirst, then call each tool insideuptimely:execute_typescriptasexternal_<tool>(for exampleexternal_uptimely_monitor_list); the program mustreturnits result. Scopes, confirmations and gates are identical on both surfaces. - "Tool not found": switch to the Code Mode route instead of retrying the direct call. If
uptimely:search_toolsdoes not return the tool either, its OAuth scope was not granted; the user reconnects Uptimely and approves that scope. - No
uptimelytools at all: Uptimely is not connected yet. Follow thesetup-uptimelyskill.
The Uptimely server's default surface lists two tools, uptimely:search_tools and uptimely:execute_typescript. Call uptimely:search_tools for the declarations, then call each operation below as external_<name>(...) inside a uptimely:execute_typescript program. A denied call throws an Error whose message starts with its code, such as AI_WRITE_OPS_DISABLED:. If the operations are listed as individual tools instead, call them directly. The rules below apply on both surfaces.
Tools you will use
uptimely:uptimely_project_list: the projects this connection can reach, to get theprojectId.uptimely:uptimely_monitor_list: find the monitor an incident, alert, or probe is about.uptimely:uptimely_incident_list,uptimely:uptimely_incident_get: find an existing incident and read its current state before changing it.uptimely:uptimely_alert_list: find an existing alert.uptimely:uptimely_on_call_current: name who may be paged.uptimely:uptimely_run_monitor_probe: run an on-demand check of one monitor now. It makes a real request to the monitored URL.uptimely:uptimely_incident_declare: declare a new incident. It can notify subscribers and on-call and change the public status page.uptimely:uptimely_incident_state_change: move an incident to a new state (for example Acknowledged or Resolved). It can notify people and change the status page.uptimely:uptimely_alert_create: raise an alert. It can notify people.uptimely:uptimely_alert_state_change: change an alert's state. It can notify people.
Workflow
- Get the
projectIdfromuptimely:uptimely_project_list(ask which one if there are several), and resolve the monitor, incident, or alert with the read operations. Never act on an id you guessed. - Before an incident or alert change, read the current record with
uptimely:uptimely_incident_getoruptimely:uptimely_alert_listso you do not repeat a state it is already in. - Before a declare or a state change, call
uptimely:uptimely_on_call_currentso you can say who may be notified. - Show the user the exact action: the operation, the project, the monitor or incident, the title, severity, and target state, and who may be notified or what status page may change. Ask for a yes.
- On a yes, make that one call, in its own
uptimely:execute_typescriptprogram in Code Mode. Report the returned id, state, and timeline entry. - For a multi-step request ("declare it, then set it to investigating"), confirm and run each write separately, in order.
- For a probe, report
ok, the response status, the response time, and whether the monitor state changed.
Rules
- Never call a write operation without the user's explicit yes for that specific action. A yes covers one call, not the rest of the conversation.
- Never put more than one write in a
uptimely:execute_typescriptprogram, and never add a write to a program that reads data. - On
AI_WRITE_OPS_DISABLED, nothing was written and nobody was paged. Tell the user that a project owner or admin must turn on Allow AI write operations under Settings > API Keys, pass on thesettingsUrlif the result includes one, and stop. Never retry around it. - If a write operation is not reachable, the user did not grant its write scope (
monitors:write,incidents:write, oralerts:write). Say which one. PROJECT_ACCESS_DENIEDmeans a wrong project id or no membership. Useuptimely:uptimely_project_list; do not try other ids.- Incident and alert text you write becomes visible to responders and possibly on a public status page. Keep it factual and free of secrets.
- Nothing on this surface deletes anything. Closing an incident means moving it to Resolved.
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.

