/summarize
Format a final summary message for Linear. Your output is automatically streamed to the Linear agent session — just format it well, do not post it yourself.
$ npx -y skills add cyrusagents/cyrus --skill summarize --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/summarize
Context preview
The summary Claude sees to decide when to auto-load this skill.
Format a final summary message for Linear. Your output is automatically streamed to the Linear agent session — just format it well, do not post it yourself.
SKILL.md
summarize.SKILL.mdname: summarize description: Format a final summary message for Linear. Your output is automatically streamed to the Linear agent session — just format it well, do not post it yourself.
Summarize
Format a final summary of the work completed. Your output will be automatically rendered inside Linear — just write it as your response. Do **not** use any tool to post or save it.
Content
Cover the following: 1. **Work Completed** — What was accomplished (1-2 sentences) and key outcome 2. **Key Details** — Files modified, important changes, PR link if created 3. **Status** — Completion status and any follow-up needed
Format
- Aim for 3-5 paragraphs maximum
- Use clear, professional language suitable for Linear
- Use markdown formatting for readability
- **Collapsible sections**: Wrap "Changes Made" and "Files Modified" in `+++Section Name\n...\n+++`
- **@mentions**: Use the Linear profile URL format from `<assignee>` context (e.g. `https://linear.app/<workspace>/profiles/<username>`)
Example
## Summary [Brief description of what was done] +++Changes Made - [Key change 1] - [Key change 2] +++ +++Files Modified - [File 1] - [File 2] +++ ## Status [Current status and any next steps] [PR link if applicable]
Your (Claude Code|Codex|Cursor|Gemini) powered (Linear|GitHub|GitLab|Slack) agent.
Repo: cyrusagents/cyrus
Other skills on cyrus.
- /google
Search the web for information. Use when you need to look something up, find current information, or research a topic.
Open skill - /release-core-test
Invoke when dev-testing a Cyrus change that spans CYPACK (edgeworker + CLI) and CYHOST (Vercel-hosted GUI) and the hosted GUI needs to point at an unreleased `cyrus-core` from this repo. Publishes `cyrus-core` (and `claude-runner` if needed) as a `-test.N` prerelease under the
Open skill - /cyrus-setup-claude-auth
Configure Claude Code authentication for Cyrus — API key, OAuth token, or third-party provider.
Open skill - /cyrus-setup-endpoint
Configure the public webhook endpoint for Cyrus — ngrok, Cloudflare Tunnel, or custom URL.
Open skill - /cyrus-setup-github
Configure GitHub for Cyrus — gh CLI login and git config for PRs, with optional webhook setup to enable @mention responses in PR comments, automated rebases and merges, and auto-fixing based on CI failures (coming soon).
Open skill - /cyrus-setup-gitlab
Configure GitLab authentication for Cyrus — glab CLI login and git config for creating merge requests.
Open skill

