ai-workflow-kit
AGENTS.md2 starsChanged 8 months agoMITView on GitHub
This repository contains workflow automation skills for AI coding assistants. Skills automate the non-coding parts of an engineer's day: morning planning, EOD reviews, meeting prep, standups, journaling, and more. Skills are in the skills/ directory. Each skill has a SKILL.md file with trigger phrases and a step-by-step workflow. When the user says a trigger phrase (e.g., "good morning", "eod review", "standup"), execute the matching skill. Skills reference generic integration points (calendar, notes, tasks, chat) rather than specific services. Check integrations/active.md…
In this repository14 other files it gives its agents.
- checkinSkill
- code-reviewSkill
- eod-reviewSkill
- journalSkill
- meeting-prepSkill
- morning-kickoffSkill
- plantsSkill
- read-laterSkill
- recipeSkill
- researchSkill
- standupSkill
- todoSkill
- tripSkill
- watchlistSkill
The file
Files
AI Workflow Kit
This repository contains workflow automation skills for AI coding assistants. Skills automate the non-coding parts of an engineer's day: morning planning, EOD reviews, meeting prep, standups, journaling, and more.
How to Use Skills
Skills are in the skills/ directory. Each skill has a SKILL.md file with trigger phrases and a step-by-step workflow. When the user says a trigger phrase (e.g., "good morning", "eod review", "standup"), execute the matching skill.
Integration Layer
Skills reference generic integration points (calendar, notes, tasks, chat) rather than specific services. Check integrations/active.md for which services are configured and how to call them.
Shared Context
shared/context/about-me.md— User's role, preferences, and coding philosophyshared/context/instructions.md— General behavioral instructionsshared/context/writing.md— Writing voice and tone guidelinesshared/personas/— Code review personas (Architect, Nitpicker)
Skill Index
| Skill | Triggers | Description |
| morning-kickoff | "good morning", "start my day" | Daily page with calendar + tasks |
| eod-review | "eod", "wrapping up", "done for today" | Review work, prep tomorrow |
| checkin | "checkin", "how's my day" | Midday progress check |
| standup | "standup", "post update" | Async team updates |
| meeting-prep | "prep for [meeting]" | Gather context for meetings |
| journal | "journal:", "feeling" | Quick journal entries |
| code-review | "review this", "code review" | Multi-persona code review |
| research | "research [topic]" | Deep-dive with synthesis |
| todo | "todo:", "remind me" | Quick task capture |
| read-later | "read later:", "save article" | Save articles with summaries |
| plants | "water plants", "plant check" | Houseplant tracking |
| recipe | "recipe:", "save recipe" | Recipe management |
| watchlist | "want to watch", "rate [movie]" | Movie/show tracking |
| trip | "trip to", "plan trip" | Trip planning |
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.