agentleFS
YuuqqYuuqq/know-skills/skills/agent-loop/SKILL.md

agent-loop

Skill0 starsChanged 3 months agoMITView on GitHub

Deprecated alias that forwards to css-professor. Kept only so prompts calling agent-loop (解释 / 审稿 / 选题 / 研究设计) still work; new prompts should invoke css-professor directly. Do not list or install as a standalone skill.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 2

    Distinctive

    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
  1. Very specific:

    When this skill is invoked, act as css-professor:

    line 15
  2. Distinctive:

    Use computational social science only when it adds value, especially for social, platform, organizational, policy, communication, …

    line 20
  3. Very specific:

    Do not output loop.md unless the user explicitly asks for a loop contract.

    line 23
  4. Distinctive:

    Do not load the legacy files.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 9 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

Agent Loop Compatibility Entry

This skill has been redirected. Do not use the old loop.md contract workflow. For current behavior, use the css-professor skill in this same skills directory.

Routing

When this skill is invoked, act as css-professor:

  1. Infer the user's knowledge type.
  2. Select Mode (Classroom Teacher / Research Mentor / Methodology Reviewer) and Depth (Flash / Class / Studio / Review) per css-professor SKILL.md.
  3. Use computational social science only when it adds value, especially for social, platform, organizational, policy, communication, AI-in-society, behavioral, or digital-trace topics.
  4. Do not output loop.md unless the user explicitly asks for a loop contract.
  5. Honor anti-triggers: pure coding/ops and book/course-to-skill pipelines are not owned here.

Resource Handling

Load the css-professor resources by relative reference (do not assume a fixed absolute path — host agents resolve skill-relative paths):

  • ../css-professor/SKILL.md — primary skill contract (Mode, Depth, Hard Load Table).
  • ../css-professor/assets/professor-answer-template.md — structured answer spine for Studio/Review when needed.
  • ../css-professor/references/quality-checklist.md — validity and evidence checks.
  • ../css-professor/references/method-branches.md — method-specific evidence rules; matching branch only.
  • ../css-professor/references/examples.md — routing calibration samples.
  • ../css-professor/references/chinese-academic-style.md — Chinese academic register.

The original agent-loop resources (loop-template.md, method-branches.md, review-checklist.md, example-loops.md) have been retired. The methodologically valuable parts were folded into css-professor/references/. Do not load the legacy files.

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.