loose-mode
Skill4 starsChanged 4 months agoMITView on GitHub
Use when the user explicitly asks to enter or continue loose mode. Do not infer it from an ordinary request for ideas, options, strategy, or an overview.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- bib-auditSkill
- bootstrap-dispatcher-runtimeSkill
- ci-debugSkill
- cloud-filesSkill
- connect-googleSkill
- daily-planSkill
- distill-to-ruttersSkill
- email-clientSkill
- email-triageSkill
- find-handoff-candidatesSkill
- formal-prose-reviewSkill
- get-weatherSkill
- git-workflowSkill
- hook-makerSkill
- initialize-tddSkill
- install-launchersSkill
- latex-workshopSkill
- list-managerSkill
- llm-wakeupSkill
- make-tex-docstringSkill
- math-dependency-graphSkill
- milestone-loggingSkill
- node-certifySkill
- node-driftSkill
- notation-reviewSkill
- online-calendarSkill
- pdf-to-markdownSkill
- prepare-handoffSkill
- proof-auditSkill
- recurring-tasksSkill
- refactor-nodeSkill
- regenerate-blueprintsSkill
- relocate-nodesSkill
- semantic-integrationSkill
- send-feedbackSkill
- setup-interface-managerSkill
- skill-makerSkill
- technical-flow-reviewSkill
- tight-modeSkill
- tool-applicabilitySkill
- update-standardsSkill
- using-compassSkill
- wrap-upSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
If constructing a new argument, plan, or design, use a planning skill if available.
- Very specific: line 33
Don't switch modes unless told to.
≈ “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
<!-- BEGIN BLUEPRINT INTERFACES -->Generated from
blueprint.yaml. Do not edit this block by hand.
Used Interfaces: none
<!-- END BLUEPRINT INTERFACES -->Core principle
Prioritize strategy, decomposition, and options over rigor. Move fast, cover ground, identify the main obstacle and promising routes.
Rules
- Break the problem into components; identify the main obstacle or blocker.
- Suggest promising approaches; connect to relevant tools, libraries, literature, or precedent.
- Emphasize structure: what the subproblems are, what could address each, how the pieces fit together.
- Match the technical level of the conversation — don't over-explain basics unless asked.
- Distinguish
Verified/Likely/Speculativewhen proposing approaches. - If constructing a new argument, plan, or design, use a planning skill if available.
Output style
Short, useful, bulleted. Use headings when helpful:
Main obstacle · Main idea · Possible approaches · What would need to be shown or built · How the pieces fit together
Mode switching
Don't switch modes unless told to. If ambiguous, stay in loose mode (it's the default). To switch: tight mode: <question>.
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.