briefing-writer
Skill8 starsChanged 33 days agoMITView on GitHub
Assemble morning briefing sections into a structured markdown file. Use when writing the final briefing output after all data sources have been gathered.
In this repository21 other files it gives its agents.
- commands/agents.mdAGENTS.md
- rules-core/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-registrySkill
- careful-modeSkill
- cast-auditSkill
- cast-conventionsSkill
- deep-researchSkill
- freeze-modeSkill
- git-activitySkill
- laconicSkill
- mergeSkill
- orchestrateSkill
- planSkill
- python-conventionsSkill
- seo-checklistSkill
- seo-index-censusSkill
- shipSkill
- stack-referenceSkill
- typescript-conventionsSkill
- wizardSkill
The file
Files
Briefing Writer
Assemble gathered data sections into a structured morning briefing file.
Instructions
You will receive data sections (git activity, action items, CAST intelligence) as markdown fragments. Assemble them into this template:
# Morning Briefing — [Weekday], [Month Day Year]
*Generated [HH:MM] · [N] items across [N] sources*
## Git Activity (Yesterday)
[git data or "No commits yesterday"]
## Open Action Items
*From recent meeting notes and TODOs*
[action items data or "No open action items"]
## CAST Intelligence
- **Dirty repos:** [list or "All clean"]
- **Open PRs:** [list or "None"]
- **Yesterday's spend:** [sessions/tokens/usage or "No data"]
- **Blocked agents:** [list or "None"]Output Rules
- Get today's date:
date "+%A, %B %d %Y"anddate +%Y-%m-%d - Write to:
~/.claude/briefings/YYYY-MM-DD-morning.md - Never overwrite — if file exists, append
_2suffix - Count total items across all sections (git commits + action items + CAST alerts) for the header line
- Count sources that returned data (not errors) for the header line
- Each section must appear even if empty — show the "no data" message rather than omitting
After Writing
Confirm: Morning briefing written to ~/.claude/briefings/YYYY-MM-DD-morning.md
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.

