agentleFS
wangyi0403wangyi0403/dl-research-workflow/.agents/skills/research-publication/SKILL.md

research-publication

Skill4 starsChanged 41 days agoMITView on GitHub

Prepare or audit a reproducible research release package, including code/data documentation, licenses, cards, checksums, and archive metadata. Publishing needs authorization.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    Verify licenses and third-party attribution for code, data, models, templates, fonts, and figures.

    line 9
  2. Distinctive:

    Create a separate local staging copy and exclude or redact credentials, personal paths, internal URLs, machine identifiers and private logs …

    line 10
  3. Very specific:

    Use references/release-checklist.md as the final gate.

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

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

Research Publication

  1. Define release scope and separate public, restricted, licensed, sensitive, and non-redistributable assets.
  2. Verify licenses and third-party attribution for code, data, models, templates, fonts, and figures.
  3. Create a separate local staging copy and exclude or redact credentials, personal paths, internal URLs, machine identifiers and private logs there. Preserve research originals, source histories and checkpoints; never sanitize by deleting or overwriting them in place.
  4. Reproduce the principal result from documented environment, config, seed, and artifact versions when feasible.
  5. Provide checksums, provenance, citation metadata, limitations, safety notes, and known failure modes.
  6. Stage the release locally for review. In research-deep-learning-project, record the checklist, decisions, and exceptions in docs/12_release_readiness.md; otherwise use the project's designated release artifact. Check the current explicit authorization for external uploads, DOI creation, publication or visibility changes; ask only for missing scope or an explicitly required action-time confirmation.

Use references/release-checklist.md as the final gate.

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.