agentleFS
Sign inStart free
JunMA98JunMA98/Computer-science-claude-skills/skills/code-to-paper/SKILL.md

code-to-paper

Skill3 starsChanged 8 months agoMITView on GitHub

Use when turning an existing codebase, experiment set, or system into a paper plan and you need contribution framing, evidence mapping, figure planning, and missing-experiment detection.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    do not inflate implementation work into unsupported novelty claims

    line 41
  2. Distinctive:

    prefer narrower defensible contributions over broad weak stories

    line 42

≈ “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.

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

Purpose

Translate implemented work into a paper-ready argument with clear claims and supporting evidence.

When To Use

  • writing a paper from an already-working repo or prototype
  • deciding whether current code and results are strong enough for submission
  • mapping experiments and artifacts into sections, tables, and figures
  • finding missing evidence before drafting a paper around the work

Inputs

  • codebase structure and current system behavior
  • experiment logs, result tables, figures, or demos
  • target venue or paper type if known

Outputs

  • contribution framing and paper outline
  • claim-to-evidence map
  • figure and table plan
  • list of missing experiments, baselines, or ablations
  • recommended paper scope for the current evidence level

Workflow

  1. Identify what the code actually demonstrates today.
  2. Convert implemented capabilities into candidate claims.
  3. Match each claim to evidence, tables, figures, or missing experiments.
  4. Build an outline around the strongest supported narrative.
  5. Flag overclaims and scope the paper to what can be defended.

Constraints

  • do not inflate implementation work into unsupported novelty claims
  • prefer narrower defensible contributions over broad weak stories
  • separate evidence already available from evidence still needed
  • make missing baselines and ablations explicit before drafting aggressively

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.

Check your setup, free