get-moving
Skill0 starsChanged 19 days agoMITView on GitHub
Get moving when stuck, overwhelmed or avoiding a task: name what kind of stuck it is, shrink the goal to one physical next action, and run one 25-minute round with a finish line. Use when the user says they are stuck, overwhelmed, do not know where to start, have too much to do, keep putting something off, or asks 'what should I do next'. Not for picking a skill (use-levistack) or planning a whole project (write-plan).
In this repository57 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/comments.mdcCursor rule
- .cursor/rules/commit-messages.mdcCursor rule
- .cursor/rules/git-workflow.mdcCursor rule
- .cursor/rules/manage-stack.mdcCursor rule
- .cursor/rules/no-worktrees.mdcCursor rule
- manage-stackSkill
- convert-as-skillSkill
- create-agentSkill
- create-agents-mdSkill
- create-commandSkill
- create-hookSkill
- create-ruleSkill
- create-skillSkill
- retrospectiveSkill
- super-architectureSkill
- super-cachingSkill
- super-elixirSkill
- super-nodejsSkill
- super-protobufSkill
- super-tech-blueprintSkill
- atomic-semantic-commitSkill
- code-reviewSkill
- create-bruno-collectionSkill
- create-documentationSkill
- create-ticketsSkill
- ready-specSkill
- write-adrSkill
- write-changelogSkill
- write-mr-descriptionSkill
- write-planSkill
- write-postmortemSkill
- write-runbookSkill
- noslopSkill
- output-saversSkill
- safe-refactorSkill
- tddSkill
- verifySkill
- later-listSkill
- standupSkill
- challenge-meSkill
- codebase-learnerSkill
- researchSkill
- second-opinionSkill
- traceSkill
- color-kitSkill
- design-system-kitSkill
- diagramSkill
- infographicSkill
- product-polish-workflowSkill
- prototype-wireframeSkill
- ui-ux-kitSkill
- evidenceSkill
- find-skillsSkill
- handoffSkill
- rumblingSkill
- use-levistackSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 26
When everything feels equally urgent, pick one physical action and start it.
- Very specific: line 30
Read before asking: Check the cwd, git status, the latest handoff note and LATER.md if they exist.
- Very specific: line 43
Run the round: Do only that action for 25 minutes.
- Distinctive: line 56
If the action is still vague, shrink it again.
- Distinctive: line 57
Do not plan the whole project.
- Distinctive: line 58
Do not ask more than one question.
≈ “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
Get moving
When everything feels equally urgent, pick one physical action and start it. One round, one finish line.
Steps
- Read before asking. Check the cwd,
git status, the latest handoff note andLATER.mdif they exist. They often already say what the goal and the last step were. Name the kind of stuck. Pick one. Say it in one line.
Kind Sign Move Too many things Three or more goals compete Ask "which one hurts most if it waits a day?" Put the rest on later-listVague goal The goal needs more than one sentence Split it. Pick one half. If it is still unclear, use challenge-meBlocked Waiting on a person, an answer or access The next action is the message that unblocks it. Draft it now Avoiding The task is clear but does not start Shrink the action until it feels too small to skip Lost the thread Came back after a break Read the handoff note or the last commit, then take the next unchecked step - Write one next action. It starts with a verb, takes under 25 minutes, and can start right now. "Open
auth.tsand write the failing test for expired tokens", not "work on auth". - Set the finish line. One line: what exists when this round is done.
- Run the round. Do only that action for 25 minutes. A tangent goes to
later-list, not into the work. - Close the round. Continue, switch or stop. Before you leave, write the next action down (in the handoff note,
LATER.mdor the reply).
Output
Stuck: <kind> — <one line why>
Next action (25 min): <verb + object + where>
Done for this round: <finish line>Pitfalls
- If the action is still vague, shrink it again. "Open the file" counts.
- Do not plan the whole project. One step.
- Do not ask more than one question. If the workspace answers it, do not ask.
Related skills
later-list: a tangent shows up during the round.challenge-me: the goal is too vague to name a first step.write-plan: the goal is large and needs a real plan.handoff: you stop for the day.use-levistack: you know the task but not which skill fits.
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.