M91 Alerting
How software or AI reaches a human when it needs one and gets the answer back. Use it wherever a program needs a person to decide, approve, answer, verify, take over, act physically or simply know, and also for alerting, on-call, paging, escalation and failure handling. Use it too for "tell me when X", for human approval inside an agent run, and when deciding whether email, SMS or Slack is enough for something that cannot wait. An M91 alert rings every phone in a channel at full volume, through silent mode and Do Not Disturb, repeats until somebody answers, escalates to a phone call and return
Install
npx skills add MSG91/m91-skill --skill m91-alertinggit clone --depth 1 https://github.com/MSG91/m91-skill.git /tmp/m91-skill
mkdir -p ~/.claude/skills
cp -r /tmp/m91-skill/. ~/.claude/skills/m91-alertingPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# M91: when software needs a human ``` Software works → hits a moment only a person can handle → M91 rings their phone → they tap an answer → the software reads it → the software continues ``` The job is done when **the software continues**. Delivering the alert is not enough. Every alert you add needs three things: someone who is asked, an answer that comes back, and a way for it to end. **You work autonomously.** Find the moments, choose the design, write the code, test it and report what you did. Do not stop to ask for approval or guidance. The one thing you cannot produce is a **credential** (a send link, an API key, or both), because a person creates it in the M91 app on their phone. Write everything so it reads credentials from configuration, finish the rest of the work without them, and ask for them in your final message (step 6). | Section | Read it when | |---|---| | 1. Find every moment a person is needed | always, before writing any code | | 2. Pick the credentials | before you choose where the link is stored | | 3. Design each alert | for each moment | | 4. Get the answer back | when code waits on the answer | | 5. Teach the people | always, because the integration is not done without it | | 6. Prove it and report | at the end | | Facts that break integrations | before you send any request | Reference (fetch only what you need. When it disagrees with this file, the document is right; say which two lines disagree):
Details
- Skill name
m91-alerting- Repository
- MSG91/m91-skill
- Repo updated
- 26 October 2026
FAQ
What does the M91 Alerting skill do?
How software or AI reaches a human when it needs one and gets the answer back. Use it wherever a program needs a person to decide, approve, answer, verify, take over, act physically or simply know, and also for alerting, on-call, paging, escalation and failure handling. Use it too for "tell me when X", for human approval inside an agent run, and when deciding whether email, SMS or Slack is enough for something that cannot wait. An M91 alert rings every phone in a channel at full volume, through silent mode and Do Not Disturb, repeats until somebody answers, escalates to a phone call and return
How do I install the M91 Alerting skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add MSG91/m91-skill --skill m91-alerting. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is M91 Alerting popular?
It lives in MSG91/m91-skill, which has 46 GitHub stars and 0 forks, and is included in 2 curated skill lists.
Related skills
ObsidianDataWeave
57howdeploy/ObsidianDataWeave
Claude Code adapter for ObsidianDataWeave workflows
Timeboxed Execution
84wenjimods/timeboxed-execution
Run deadline-bound or scope-sensitive agent tasks with explicit done conditions, protected verification time, evidence gates, and safe-stop rules. Use for rapid implementation, debugging, integration, delegated work, feasibility gates, or tasks where scope drift, false completion, repeated failure, or deadline overruns are material risks.
Market Daily Review
53quantskills/skill-market-daily-review
Generate A-share end-of-day market review reports with Pandadata data, covering trade-date checks, index performance and valuation, market breadth, limit-up/down sentiment, industries/concepts, 龙虎榜, block trades, margin financing, northbound holdings, risk notes, and optional scheduled after-close automation. Use when the user asks for 今日复盘, 收盘总结, 每日市场报告, A股复盘, 龙虎榜复盘, 北向资金动向, or to set up an automated daily market review.
Journal Recommender
66zero565656/journal-recommender
Use when the user asks for journal recommendation, 选刊, 投稿期刊筛选, 期刊匹配, 适合投稿的期刊, 投哪个期刊, or wants 3-5 suitable journals for a manuscript based on an abstract, discipline, CAS/JCR ranking, impact factor, Aims & Scope, review speed, OA/APC, and publication-risk checks.
Plandeck
68OthmanAdi/plandeck
A live visual Kanban board and continuity layer for long-running agentic tasks. Nobody wants to read a markdown plan or stare at raw HTML while an agent grinds for an hour, so Plandeck turns the plan into a board that organizes itself. Use it when a task is multi-step, long-running, or needs visual planning. Break the work into cards, declare which card depends on which, and Plandeck computes the critical path, auto-promotes cards to Ready as their dependencies clear, rolls up story-point estimates into an honest percent complete, and names the one next action. Plans, observed transitions, and
Pda Reframing
59emory/ASD-AuDHD-PAI-Skills
Rephrase tasks and requests by avoiding Demand Avoidance triggers for someone with PDA autism spectrum disorder. It transforms demands into exploration and autonomous actions.
Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.