running-brief
Skill1 starsChanged 4 months agoMITView on GitHub
Review the running brief interactively. Clear, snooze, or act on pending items.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- commsSkill
- composeSkill
- daily-briefSkill
- domain-hygieneSkill
- grill-meSkill
- idea-deep-diveSkill
- laila-headless-conductSkill
- laila-judgmentSkill
- laila-ops-debuggingSkill
- level-upSkill
- new-domainSkill
- os-auditSkill
- personaSkill
- quarterly-refreshSkill
- roastSkill
- session-wrapSkill
- setupSkill
- specSkill
- validate-ideaSkill
- whats-nextSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
When triggered with "Running brief", "What's pending?", or $ARGUMENTS = review:
- Distinctive: line 41
No follow-up needed -> Skip (just clear)
- Very specific: line 51
After routing, record routed_to on the cleared item in the JSON (e.g., "routed_to": "reminders:household") to prevent duplicate task …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Running Brief Skill
The Running Brief is a curated, living list of items Laila needs to discuss with Alex. Unlike the raw comms queue, it deduplicates, detects staleness, and stays small (~5-20 actionable items).
State Files
state/running-brief.json— Machine-readable source of truthstate/running-brief.md— Human-readable rendered view
Pipeline
comms monitor -> state/comms-queue.json -> updater script -> running-brief.json/.md
Staleness Detection
- Messaging channels: check whether Alex already sent a reply to the same contact (query the channel's sent messages if the integration allows it)
- Email: checked during interactive review only (requires the mail integration)
- Age-based: items >5 days with no update -> marked stale
- Auto-expire: items >14 days -> auto-cleared
Review Workflow
When triggered with "Running brief", "What's pending?", or $ARGUMENTS = review:
- Read
state/running-brief.json - Present items grouped by domain, active items first, then a stale summary
- For each item, Alex can:
- "done" or "handled" — Clear the item (move to the
clearedarray) - "snooze" or "later" — Reset the staleness timer, keep in the brief
- "not relevant" or "skip" — Clear with a reason
- Take action — Draft a reply, open the email, etc., then clear
- "clear stale" — Bulk-clear all stale items at once
- "done" or "handled" — Clear the item (move to the
- After review, save updated
state/running-brief.jsonand re-render the.md Route actions to task systems — For each cleared item that generated a follow-up action, apply your task-management routing rules:
- Shared with household members -> the shared reminders/task list
- Relates to a CRM entity (Person/Company/Opportunity) -> a CRM task or status update (query your CRM/task system here)
- Domain-specific follow-up -> that domain's task list
- No follow-up needed -> Skip (just clear)
Present routing proposals as a sync table for approval before executing:
| System | Action | Detail | |--------|--------|--------| | Reminders | Add | Household: "Review property declaration form" | | CRM | Update | Application: Acme Health -> Rejected |After routing, record
routed_toon the cleared item in the JSON (e.g.,"routed_to": "reminders:household") to prevent duplicate task creation.
Usage
$ARGUMENTS = reviewor empty: Full interactive review$ARGUMENTS = clear-stale: Auto-clear all stale items$ARGUMENTS = status: Quick count of active/stale items ("Brief status")
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.

