adhd-priorities
Skill0 starsChanged 45 days agoMITView on GitHub
Use when deciding priorities of any kind, including projects and tasks.
In this repository10 other files it gives its agents.
- attorney-packetSkill
- co-parent-replySkill
- incident-logSkill
- narrative-writerSkill
- proof-checkSkill
- repo-structure-auditSkill
- review-criticallySkill
- source-mapSkill
- timeline-builderSkill
- visual-explainerSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Keep important work. Recommend delegation for urgent but unimportant work, and deferral or removal for work that is neither.
- Distinctive: line 60
Start with rank one. Energy, interest, time, tools, and location may select another task within a genuinely tied highest-priority band.
- Distinctive: line 62
Do not save, schedule, delegate, contact anyone, or alter the user's task system unless asked.
≈ “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
ADHD Priorities
Rank every supplied task and make the top three easy to start. Keep importance separate from ease of activation.
Rank
Clarify vague tasks into concrete outcomes without losing their original identity. Ask about missing deadlines or dependencies only when they could materially change the order; otherwise state relevant assumptions.
Keep important work. Recommend delegation for urgent but unimportant work, and deferral or removal for work that is neither. Urgency requires an external deadline, safety issue, expiring opportunity, or someone currently blocked; self-imposed pressure alone does not qualify.
Score retained tasks using evidence, from 0 to 3 per dimension:
| Dimension | 0 | 1 | 2 | 3 |
| Consequence of delay | No meaningful effect | Minor inconvenience | Meaningful cost, stress, or lost progress | Serious harm, major loss, or failed core commitment |
| Real deadline | None | More than 7 days away | 2–7 days away | Overdue, within 48 hours, or expiring window |
| Unblock value | Standalone | One later step | Several steps or one waiting person | Critical dependency for substantial work or multiple people |
Priority = Consequence + Deadline + Unblock value. Sort descending; break ties by consequence, earlier real deadline, then unblock value. Label any safety or severe-deadline override. Explain the decisive evidence in words; show scores and supporting reasons only when requested.
Output
Account for every supplied task exactly once, including lists longer than 12. Keep continuous rank numbers across sections; acknowledge any merged duplicates. Use short paragraphs, bold task names, and blank space rather than a score table. Omit empty sections.
Keep — top three
Give a brief overview of why these tasks lead. Present up to three tasks in priority order, using this format for each:
1. [Task]
Why: The evidence that puts it here.
Start — [estimated minutes]: A concrete first action.
Stop point: The observable result of that action.
Make starting easier: An optional aid matched to the task's obstacle.
Keep Next — ranks 4–10
Explain briefly why this group matters but trails the top three. List each task in order; individual breakdowns are unnecessary.
Park for Now — remaining tasks
List all remaining retained tasks in order, followed by clearly marked triage recommendations. Explain why they fall outside the top ten or were triaged, grouping different reasons when needed. Parking can include important work; it means lower relative priority, not no importance. Mark dependency holds, proposed delegation, and removal explicitly.
Finish with Order could change if: only when unresolved facts could alter the ranking.
Make starts realistic
Estimate the first action, not the whole task. Aim for 10–15 minutes, allowing shorter actions; account for setup and access. Shrink uncertain work to a feasible step, such as identifying missing inputs or outlining three headings. If no useful step fits, give an honest longer estimate. Match the stop point to that step; a timer does not establish completion time.
Choose starting aids for actual friction: a relevant example for blank-page pressure, gathered materials for setup, one small deliverable for overwhelm, one source for distraction, or a meaningful challenge for low engagement. Suggest a timer, reward, or willing coworking partner only when useful. Do not invent the user's obstacles or rotate aids for novelty; avoid defaulting to a timer.
Start with rank one. Energy, interest, time, tools, and location may select another task within a genuinely tied highest-priority band; explain that choice without changing the strategic ranking. Never promote lower-priority work merely because it is interesting.
Do not save, schedule, delegate, contact anyone, or alter the user's task system unless asked.
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.

