productivity-suite
Skill4 starsChanged 6 months agoMITView on GitHub
ADD/ADHD Aide and executive function replacement AI covering 20+ specialist skills. Replaces the brain systems that make starting, planning, organizing, executing, and finishing hard. Use for breaking down overwhelming tasks into atomic steps, project planning and roadmapping, context preservation across sessions, file and digital organization, research synthesis, guided execution with checkpoints, completion verification, mode switching between brainstorm/execute/debug states, and full autonomous project execution. Trigger keywords: overwhelmed, don't know where to start, plan this, break this down, organize, I keep forgetting, where was I, get this done, execute this plan, what should I work on, help me focus, verify this is done, brain dump, I'm stuck, project roadmap, research this first, ADHD, executive function, context lost, pick up where I left off.
In this repository10 other files it gives its agents.
- all-marketingSkill
- coding-suiteSkill
- design-studioSkill
- devops-suiteSkill
- dispatchSkill
- founders-suiteSkill
- game-devSkill
- marketing-suiteSkill
- purple-teamSkill
- research-labSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 85
All sub-skill instructions are in references/skills-catalog.md.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Productivity Suite
Executive function replacement for humans whose brains make starting, organizing, and finishing hard.
This suite does not assume you know what you want to do next. It does not assume you remember what you were doing. It does not assume you can break a big scary task into small ones on your own. It handles all of that.
How to Use This Skill
- Identify where you're stuck from the routing table below
- Load the matching sub-skill from
references/skills-catalog.md - Execute following the sub-skill's workflow
Quick Routing Table
🧠 "I don't know where to start" — Task Initiation
| Situation | Load |
| Big scary thing, no idea how to begin — just describe it | task-breakdown |
| Need an atomic step-by-step plan before touching anything | concise-planning |
| Have a plan file already, need to execute it | execute-plan |
| Writing a plan to hand off or save for later | plan-writing |
🗺️ "I need to see the big picture" — Project Architecture
| Situation | Load |
| New project — figure out phases, milestones, what comes first | gsd → roadmap phase |
| Create a new track (feature, bug, chore, refactor) with spec + phases | conductor-new-track |
| Need to research what I'm building before starting | gsd → research phase |
| Synthesize research into a clear action plan | gsd → synthesize phase |
⚡ "Just make it happen" — Execution Mode
| Situation | Load |
| Full project pipeline: research → plan → execute → verify | gsd (whole system) |
| Execute a plan with automatic checkpoints | gsd → execute phase |
| Check if the plan itself is solid before executing | gsd → plan-check phase |
| Run a simple batch of tasks and report when done | execute-plan |
🔁 "Where was I?" — Working Memory
| Situation | Load |
| Save current context before ending a session | context-save |
| Restore context from a previous session | context-restore |
| Manage context window in a long session | context-window |
| Persistent memory across conversations | conversation-memory |
📁 "My files are a disaster" — Digital Organization
| Situation | Load |
| Organize files, folders, clean up Downloads, find duplicates | file-organizer |
| Generate doc templates, notes structure, project docs | doc-templates |
✅ "Is this actually done?" — Completion & Verification
| Situation | Load |
| Verify work is actually complete before claiming done | verify-completion |
| Run GSD verification pass on a finished phase | gsd → verify phase |
🎛️ "I need to switch gears" — Mode Switching
| Situation | Load |
| Brainstorm vs. implement vs. debug vs. review — switch modes explicitly | behavioral-modes |
🚀 "Just build the whole thing" — Autonomous Mode
| Situation | Load |
| Autonomous multi-agent full project execution (PRD → deployed product) | loki-mode |
Loading Sub-Skills
All sub-skill instructions are in references/skills-catalog.md.
productivity-suite/
├── SKILL.md ← You are here (routing hub)
└── references/
└── skills-catalog.md ← Full instructions for all skillsAlways read the relevant section of skills-catalog.md before executing any task.
Skill Sorting Notes
Skills from source folders routed elsewhere:
twilio-communications→ coding-suite (API integration)notion-template-business→ founders-suite (digital product business)changelog-automation→ devops-suite (release workflow)team-collaboration-standup-notes→ devops-suite (engineering standup)gsd-codebase-mapper→ coding-suite (code architecture)gsd-integration-checker→ coding-suite (integration testing)gsd-debugger→ coding-suite (systematic debugging)
Universal Productivity Standards
Start before you're ready — The planning phase IS the work. Don't wait until conditions are perfect. A bad plan you execute beats a perfect plan you don't start.
Atomic tasks only — If a task takes more than 25 minutes to describe, it's not a task. It's a project. Break it down further.
Externalize everything — Don't trust working memory. Write it down, save context, make notes. Your brain is for thinking, not storing.
One thing at a time — Multitasking is a myth. Serial focus wins. The mode you're in (brainstorm / execute / review) determines everything about how you should behave.
Done means verified — "I think it's done" is not done. Done means you ran the check and saw the output.
Momentum over perfection — Progress compounds. An imperfect thing shipped beats a perfect thing planned. Reduce friction, reduce scope, increase shipping rate.
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.

