agentleFS
curv-institutecurv-institute/atlas/.claude/skills/research/SKILL.md

research

Skill0 starsChanged 4 months agoMITView on GitHub

Autonomously work a research task end-to-end following the operating-guide lifecycle - scope, cheap pilot first, preregister, build/run, gate, then convene /council to verify - looping on the verdict (fix→re-loop, solid→record & next, obstruction/refuted→document & next). Use when the user says "/research", "work this task autonomously", or hands over a goal/backlog. Honors OPERATING_GUIDE.md and OWNERSHIP.md.

189 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use Problem-Solving Techniques, daily-arxiv and 10 more.

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.
  • truongtv22Skill

    Problem-Solving Techniques

    Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.

    Also in 6 projects that use this

  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 49 projects that use this

  • parcadeiSkill

    ast-grep-find

    AST-based code search and refactoring via ast-grep MCP

    Also in 4 projects that use this

  • SireJeffSkill

    context-optimize

    Context Optimization - Orchestrate RPI workflow TODO generation with interactive scoping

    Also in 4 projects that use this

  • +5 more from Lambenthan

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 2

    Distinctive

    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
  1. Very specific:

    Check ownership: - run /mediate first if the task may touch another thread's area (OWNERSHIP.md).

    line 12
  2. Distinctive:

    Never run the full/expensive job before the pilot + prereg.

    line 27
  3. Distinctive:

    Keep a short ledger of task → verdict → artifact so the loop is resumable.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 170 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 - work a task end-to-end with the lifecycle

Drive a research task through the OPERATING_GUIDE.md §1 lifecycle, self-paced and resumable. The bias is rigor over speed: a candidate only becomes a claim after it survives /council.

Per task

  1. Check ownership - run /mediate first if the task may touch another thread's area (OWNERSHIP.md).
  2. Scope - state the question and what would falsify it.
  3. Cheap pilot - the smallest run that could show the effect or kill the idea. If it would take hours / heavy compute, stop and confirm (and consider /optimize).
  4. Preregister - freeze hypothesis, metric, units, N, and the pass/fail threshold in a committed PREREGISTRATION.md before the full run.
  5. Build & run - reproducible from a named artifact (code + data + commit). Deterministic seeds.
  6. Gate - an evaluator computes the pre-stated verdict to gate_evaluation.json (once-only).
  7. /council - adversarially verify before recording. Re-derive load-bearing numbers independently.
  8. Record in CURRENT_STATE.md, additively:
    • Solid → live claim (with scope + artifact + commit). Next task.
    • Fix needed → fix and re-loop from the gate.
    • Obstruction / refuted → document the obstruction (a valid outcome) and move on.

Discipline

  • Never run the full/expensive job before the pilot + prereg.
  • An API/tooling error is an interruption, never evidence - resume the undone work, don't conclude.
  • Keep a short ledger of task → verdict → artifact so the loop is resumable.
  • Pipe large run output to files; report summaries (don't flood context).

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.