agentleFS
L4pisLazuliL4pisLazuli/grounded-paper-skills/.claude/skills/paper-survey/SKILL.md

paper-survey

Skill0 starsChanged 3 months agoMITView on GitHub

Extract faithful math and pseudocode into `algorithm.md` and map `survey/repro/` to it. Use when reproducing a method, writing algorithm notes, or working under `sources/*/survey/`.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. DrNbnonono/skills★ 2same name
    2. hhyy0401/claude-skills★ 1same name
    3. zeros335882878/dsh-paper-survey★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If equations or algorithms are marked [extraction uncertain], or math needs re-extract, read /paper-extract (arXiv source first).

    line 11
  2. Very specific:

    Do not put web supplements or illustrative examples in algorithm.md

    line 29
  3. Very specific:

    Every #^ citation in algorithm.md resolves to a block ID that exists in the target file

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Survey mode (method reproduction)

If equations or algorithms are marked [extraction uncertain], or math needs re-extract, read /paper-extract (arXiv source first).

Templates: _templates/algorithm.md, _templates/repro-readme.md.

Replace every {{...}} in copied templates. Do not copy unused placeholder text into real notes.

Artifacts

  • survey/algorithm.md — math / pseudocode faithful to the paper
  • survey/repro/ — reproduction workspace (any language)

algorithm.md

  • Extract math and pseudocode without altering meaning
  • If extracted/ marks [extraction uncertain] on equations or algorithms, cross-check against the math reference priority before cleaning — arXiv source _raw/arxiv/ (preferred), then _raw/mathpix/, then the PDF original. On fetch failure, follow /paper-extract fallback and never substitute an arbitrary source (do not promote broken extract to source of truth)
  • Include a symbol table (symbol / meaning / citation anchor)
  • Attach a citation to each block whose ID already exists in extracted/ (_raw used for checking is not a citation target)
  • Implementation assumptions not in the paper: say "Not stated in the attached source" and keep them out of algorithm.md (put them in repro notes)
  • Do not put web supplements or illustrative examples in algorithm.md

repro/

  • Language and build are free per paper; a README stub is required (_templates/repro-readme.md)
  • README must map algorithm.md sections ↔ modules/functions
  • Tests and validation data must mirror paper settings / boundary conditions (no junk placeholders)

Done when

  • survey/algorithm.md and survey/repro/README.md exist
  • Every #^ citation in algorithm.md resolves to a block ID that exists in the target file
  • No {{...}} or other template wording remains
  • Frontmatter mode matches the paper; status is surveying (or ready if the user asked to close the survey pass)
  • _index/MOC.md status matches index.md if it was updated

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.