agentleFS
LeonardSEOLeonardSEO/ambitious-math-research/skills/research-brief/SKILL.md

research-brief

Skill0 starsChanged 33 days agoMITView on GitHub

Turn a mathematical problem into an exact research brief, motivating launch prompt, or concise goal draft. Use when preparing or revising an investigation; proof execution and proof auditing have separate skills.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use weekly-review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • QuixiAISkill

    weekly-review

    Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 1

    Distinctive

    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
  1. Distinctive:

    Keep the output direct and pasteable.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research Brief

Produce an actionable brief that treats serious progress as attainable and preserves the user's exact mathematical target.

Build the brief

  • Reuse the user's definitions, current results, scope, budgets, and working files. Resolve substantive ambiguity before spending research effort; ordinary implementation choices do not need another approval.
  • State the theorem or counterexample sought, including load-bearing hypotheses, quantifiers, and degenerate cases. Separate the target from assumptions permitted in a proof.
  • Specify what establishes completion. Distinguish a useful lemma, an equivalent reformulation, a finite check, and a complete resolution. If the assignment is a partial theorem or an audit, use that actual assignment as the completion condition.
  • Name the immediate mathematical bottleneck and a genuinely diverse initial portfolio. Let the executing agent adapt its route rather than prescribe a fixed agent allocation.
  • Give direction with confidence: pursue promising constructions fully, diagnose failed steps concretely, and continue to the next useful attempt. A problem's open status alone is not a stopping argument.
  • For a prove-or-disprove assignment, keep both outcomes available. A solvability assumption may frame search, but it is never a premise proving the theorem and does not authorize inventing a result.
  • Include the user's pause and budget boundaries and a precise checkpoint on interruption. Never substitute endless activity for a mathematical completion condition.

Use the launch template when a full launch prompt is requested. Adapt it to the problem and omit irrelevant parts. For a requested goal, use the one-line goal template; return one physical line and one paragraph. Drafting a goal is not authorization to activate it. Use the host's goal tools only on an explicit request.

Keep the output direct and pasteable. Do not describe confidence as a guarantee of success or spend the response explaining why the problem is hard.

Consult the workflow map only to choose a next skill. The map is not an instruction to load the whole package.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.