ワンクリックで
pm
// Create incident postmortems by reading Slack incident channels and creating structured postmortem documents in Notion. Use when conducting postmortem reviews or documenting incident responses.
// Create incident postmortems by reading Slack incident channels and creating structured postmortem documents in Notion. Use when conducting postmortem reviews or documenting incident responses.
Build pricing pages, pricing cards, and plan displays with Flowglad. Use this skill when creating pricing tables, displaying subscription options, or building plan comparison interfaces.
Install and configure the Flowglad SDK for Next.js, Express, and React applications. Use this skill when adding billing to an app, setting up Flowglad for the first time, or configuring SDK providers and route handlers.
Perform large-scale refactors and renames in TypeScript codebases. Use when renaming symbols across files, doing pattern replacements, changing function signatures, or performing codebase-wide refactors. Prefer AST-aware tools over text-based replacements.
Resolve all failing CI checks and address PR review feedback on the current branch's PR. Runs tests locally, fixes failures, incorporates valid review comments, and resolves addressed feedback. Use when CI is red, after receiving PR feedback, or before merging.
Review pull requests for code quality, security vulnerabilities, best practices, and potential issues. Use when reviewing PRs, examining diffs, or providing code review feedback.
| name | pm |
| description | Create incident postmortems by reading Slack incident channels and creating structured postmortem documents in Notion. Use when conducting postmortem reviews or documenting incident responses. |
Create comprehensive incident postmortem documents by reading Slack incident channels and storing structured postmortems in Notion.
This skill requires the following MCP servers to be configured:
Optional:
Ask the user for the Slack channel name or ID. The channel should be the dedicated incident channel (typically named like #incident-<name> or #inc-<date>-<description>).
Use the Slack MCP to fetch the channel's message history:
mcp__slack__slack_list_channels
Find the channel ID, then fetch history:
mcp__slack__slack_get_channel_history with channel_id
For threaded discussions, also fetch thread replies:
mcp__slack__slack_get_thread_replies with channel_id and thread_ts
Get user information to resolve mentions:
mcp__slack__slack_get_users
From the Slack messages, extract:
Timeline: Key events in chronological order
Root Cause: The underlying technical issue
Impact: The effect on users/systems
Open Questions: Unresolved items from discussion
Action Items: Follow-up tasks with assignees
Create a markdown document following this structure:
# Incident Postmortem: [Brief Title]
**Date:** [Incident Date]
**Severity:** [P0/P1/P2/P3]
**Duration:** [Total incident duration]
**Author:** [Person creating postmortem]
## Summary
[2-3 sentence summary of what happened and the impact]
## Timeline
| Time (UTC) | Event |
|------------|-------|
| HH:MM | Incident detected via [source] |
| HH:MM | Team alerted |
| HH:MM | Investigation began |
| HH:MM | Root cause identified |
| HH:MM | Mitigation deployed |
| HH:MM | Incident resolved |
## Impact
- **Services Affected:** [List of affected services]
- **Users Impacted:** [Number or percentage]
- **Duration:** [How long users were affected]
- **Data Loss:** [Yes/No, details if applicable]
## Root Cause Analysis
### What Happened
[Detailed technical explanation of the failure]
### Why It Happened
[Contributing factors, systemic issues]
### Detection
[How was the incident discovered? Could we have detected it sooner?]
## Telemetry & Monitoring
[If Betterstack MCP is available, include relevant links]
- **Uptime Dashboard:** [Link]
- **Error Metrics:** [Link]
- **Relevant Alerts:** [Link]
## Open Questions
- [ ] [Unresolved question 1]
- [ ] [Unresolved question 2]
## Action Items
| Action | Assignee | Priority | Status |
|--------|----------|----------|--------|
| [Action description] | @[username] | High/Medium/Low | Open |
| [Action description] | @[username] | High/Medium/Low | Open |
## Lessons Learned
### What Went Well
- [Positive aspects of incident response]
### What Could Be Improved
- [Areas for improvement]
## References
- **Incident Channel:** #[channel-name]
- **Related PRs:** [Links to fix PRs]
- **Related Docs:** [Links to relevant documentation]
Use the Notion MCP to create the postmortem in the Notes database:
First, search for the Notes database:
mcp__claude_ai_Notion__notion-search with query: "Notes"
Or use the Notion skill:
Skill: notion-search with "Notes database"
Then create the page with the postmortem content:
mcp__claude_ai_Notion__notion-create-pages with:
- parent: Notes database ID
- title: "Incident Postmortem: [Brief Title]"
- content: [Generated markdown content]
Important: Add the required tags to the page:
engpostmortemIf the Notion MCP supports tags/properties, set them during creation. Otherwise, use the update page tool:
mcp__claude_ai_Notion__notion-update-page with:
- page_id: [created page ID]
- properties: { tags: ["eng", "postmortem"] }
After creating the postmortem:
mcp__slack__slack_post_message with:
- channel: [incident channel ID]
- text: "Postmortem document created: [Notion link]"
Provide to the user: