New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Focs Reproducibility

by brycewang-stanford in brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when hardening a FOCS (IEEE Symposium on Foundations of Computer Science) paper's checkability — the theory analogue of reproducibility — via hypothesis ledgers…

MITAuto-check passedResearch & Science

Install Focs Reproducibility

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill focs-reproducibility -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills focs-reproducibility --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/FOCS-Skills/skills/focs-reproducibility .claude/skills/focs-reproducibility && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
focs-reproducibility
GitHub stars
1.2k
Token cost
~1.4k tokens
SKILL.md length
700 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when hardening a FOCS (IEEE Symposium on Foundations of Computer Science) paper's checkability — the theory analogue of reproducibility — via hypothesis ledgers…

  • Works in 5 steps: The hypothesis ledger → Statement freeze across versions → The imported-theorem audit → …
  • Single-source theorem statements that cannot drift between submission and arXiv versions
  • SKILL.md covers 1. The hypothesis ledger, 2. Statement freeze across…, 3. The imported-theorem audit and 4. Certificates for computed…, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Focs Reproducibility is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when hardening a FOCS (IEEE Symposium on Foundations of Computer Science) paper's checkability — the theory analogue of reproducibility — via hypothesis ledgers, single-source theorem statements that cannot drift between submission and arXiv versions, audits of imported theorems, and certificates for machine-checked steps.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Reproducible research and Academic paper search. It works with arXiv. The repository describes itself as: Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的… The licence is MIT.

When your agent uses it

  • Single-source theorem statements that cannot drift between submission and arXiv versions
  • Audits of imported theorems
  • Certificates for machine-checked steps

Example prompts

  • “/focs-reproducibility”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. The hypothesis ledger
  2. Statement freeze across versions
  3. The imported-theorem audit
  4. Certificates for computed steps
  5. Errata as a first-class object

What it can do on your machine

Read from SKILL.md and the folder at commit 932eb23. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Focs Reproducibility loads about 1.4k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 700 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from brycewang-stanford/Awesome-Journal-Skills at commit 932eb23, republished under its MIT licence (© brycewang-stanford). 700 words, ~1,354 tokens.

Download SKILL.mdSave it as .claude/skills/focs-reproducibility/SKILL.md (or your agent's skills folder).
name
focs-reproducibility
description
Use when hardening a FOCS (IEEE Symposium on Foundations of Computer Science) paper's checkability — the theory analogue of reproducibility — via hypothesis ledgers, single-source theorem statements that cannot drift between submission and arXiv versions, audits of imported theorems, and certificates for machine-checked steps.

FOCS Reproducibility

FOCS has no reproducibility checklist and asks for no artifacts (2026 CFP, checked 2026-07-08). At a proofs venue, "reproducing" a result means an independent expert can re-derive it from the paper alone. That property — checkability — is engineerable, and papers engineered for it survive both refereeing and the decade of scrutiny that follows a FOCS acceptance. Four practices below build it.

1. The hypothesis ledger

Every assumption a theorem consumes should be visible at the theorem, not scattered across ambient conventions declared in Section 2. Keep a ledger during writing:

HypothesisIntroducedUsed byDischarged or standing?
$G$ simple, connected§2 conventionsThm 1, 3; Lem 4.2standing
$\varepsilon < 1/\log n$Thm 3 statementLem 5.1–5.4standing — stated in Thm 3 ✓
oracle access to exact eigenvalues§5 ¶1 (silent!)Lem 5.3must surface in Thm 3

The audit question for each row: does the formal statement of every theorem that transitively needs this hypothesis mention it? Silent standing hypotheses are the most common correctness complaint theory referees file, and the cheapest to fix before submission.

2. Statement freeze across versions

A FOCS project lives as at least three documents — the HotCRP submission, the arXiv/ECCC full version, and eventually the IEEE proceedings version. Theorem statements must be bit-identical across them; a bound that strengthens silently between submission and arXiv is, to a referee who checks, either sloppiness or misconduct. Enforce the freeze mechanically by extracting and diffing labeled statements:

bash
# extract_statements.sh — run against any two versions of the source
for src in "$1" "$2"; do
  awk '/\\begin{(theorem|lemma|corollary)/,/\\end{(theorem|lemma|corollary)/' \
      "$src"/*.tex | tr -d ' \n' | sha256sum
done
# identical hashes => no drift in any formal statement

Legitimate post-submission improvements go into a dated "changes since submission" note in the arXiv version, never into silent edits (see focs-camera-ready for the endgame version ledger).

3. The imported-theorem audit

Most FOCS proofs stand on external results, and the failure mode is citing a theorem for slightly more than it says. Before the freeze, audit every import:

  • Locate the exact statement in the cited source — theorem number, page, and version (arXiv preprints renumber theorems between versions; pin the version, per focs-related-work).
  • Transcribe its hypotheses into your ledger and check your invocation supplies all of them. The classic bug: importing a bound proved for constant-degree instances into an unbounded-degree argument.
  • Check parameter regimes. "For sufficiently large $n$" in the source must be compatible with the $n$ your recursion actually feeds it.
  • If the imported proof is folklore or unpublished, prove it in your appendix; "well known" is not a citation a referee can check.
Show full SKILL.md (308 more words)Show less

4. Certificates for computed steps

When a proof step is a computation (focs-experiments), checkability means a stranger can re-verify without trusting your code: publish the certificate (the enumerated cases, the SAT solver's proof trace, the exact rational arithmetic transcript), ship a minimal independent checker, pin both with hashes, and state in the proof what object certifies what claim. A referee who can re-run a 40-line checker in a minute treats the step as proved; one who is asked to trust an opaque 4,000-line search does not.

5. Errata as a first-class object

Checkability extends past acceptance. FOCS papers are cited for decades, and the community's memory of an error is shaped by how it was handled:

  • Maintain the changelog in the arXiv version as the single erratum channel; a correction buried in a later paper's footnote does not reach readers of the original.
  • Downgrade honestly: if a repaired lemma now yields a weaker bound, the changelog and the abstract both change — leaving a stale headline bound on a corrected paper is the reputational worst case.
  • Notify identifiable downstream users directly when a result they built on moves; theory's dependency graph is small enough that this is feasible and expected.

Pre-freeze checkability review

Run as a dedicated pass, separate from proofreading:

  1. Ledger complete; no silent standing hypotheses (§1).
  2. Statement hashes identical between submission source and full-version source (§2).
  3. Every external import located, transcribed, regime-checked (§3).
  4. Every computed step certified and independently checkable (§4).
  5. One non-author has re-derived the most delicate lemma from the paper text alone — the strongest single predictor that referees will succeed too.

A paper passing all five is not guaranteed acceptance; it is guaranteed not to be rejected for the reasons authors most regret, and it is camera-ready for the public record that FOCS culture expects the full version to become.

© brycewang-stanford, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in FOCS-Skills/skills/focs-reproducibility of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Focs Reproducibility next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Focs Reproducibility compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Focs Reproducibility this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.4kAutomated safety check: PassMIT
Literature ReviewK-Dense-AI/scientific-agent-skills48k1 repos~3.2kAutomated safety check: NotesMIT
Literature Search Methodologyaiming-lab/AutoResearchClaw15k—~709Automated safety check: PassMIT
Paper LensYSQ-boop/paper-lens101—~1.3kAutomated safety check: PassApache-2.0
Read arXiv Paperkarpathy/nanochat59k1 repos~494Automated safety check: PassMIT
Literature Reviewneflibata-feng/MyArxiv-Agent12620 repos~5.9kAutomated safety check: NotesMIT

Similar skills

  • Literature Review

    K-Dense-AI/scientific-agent-skills

    Runs systematic, scoping or narrative literature reviews across PubMed, arXiv, bioRxiv and Semantic Scholar, with citation checks and Markdown or PDF output.

    48k GitHub starsUsed in 1 repo~3.2k tokens
    Research & ScienceAuto-check: notes

  • Literature Search Methodology

    aiming-lab/AutoResearchClaw

    Lays out a systematic literature review method: PICO-based search strategy, inclusion criteria, PRISMA screening, quality assessment tools and synthesis approaches.

    15k GitHub stars~709 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Paper Lens

    YSQ-boop/paper-lens

    Read and critically analyze one academic paper from an arXiv URL/ID or a local PDF, producing a source-grounded Markdown report that can grow from a quick read into a reviewer-level deep review.

    101 GitHub stars~1.3k tokensUpdated 11 days ago
    Documents & OfficeAuto-check passed

  • Read arXiv Paper

    karpathy/nanochat

    Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.

    59k GitHub starsUsed in 1 repo~494 tokens
    Research & ScienceAuto-check passed

  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 20 repos~5.9k tokens
    Research & ScienceAuto-check: notes

  • Openalex Database

    neflibata-feng/MyArxiv-Agent

    Query and analyze scholarly literature using the OpenAlex database.

    126 GitHub starsUsed in 12 repos~3k tokens
    Research & ScienceAuto-check passed

More from brycewang-stanford/Awesome-Journal-Skills

All 2,387 skills in this repo

  • Aaag Data Analysis

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running and reporting the analysis for an Annals of the American Association of Geographers manuscript — spatial statistics and modeling, remote-sensing accuracy, or…

    1.2k GitHub stars~1.3k tokensUpdated 13 days ago
    Auto-check passed

  • Aaag Literature Positioning

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when positioning an Annals of the American Association of Geographers manuscript in the literature — engaging geographic scholarship across the relevant area and the…

    1.2k GitHub stars~1.3k tokensUpdated 13 days ago
    Auto-check passed

  • Aaag Rebuttal

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when responding to an Annals of the American Association of Geographers decision letter (major/minor revision) — building a point-by-point response to the subject editor and…

    1.2k GitHub stars~1.4k tokensUpdated 13 days ago
    Auto-check passed

  • Aaag Research Design

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when defending the research design of an Annals of the American Association of Geographers manuscript — spatial/quantitative analysis and GIScience, remote-sensing and…

    1.2k GitHub stars~1.4k tokensUpdated 13 days ago
    Auto-check passed

  • Aaag Review Process

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript — double-anonymous review routed through a subject editor by…

    1.2k GitHub stars~1.3k tokensUpdated 13 days ago
    Auto-check passed

  • Aaag Submission

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running the final pre-submission preflight for the Annals of the American Association of Geographers via ScholarOne Manuscripts — area/article-type selection…

    1.2k GitHub stars~1.6k tokensUpdated 13 days ago
    Auto-check passed

Works with

Categories

Questions about Focs Reproducibility

What does Focs Reproducibility do?

A skill your agent uses when hardening a FOCS (IEEE Symposium on Foundations of Computer Science) paper's checkability — the theory analogue of reproducibility — via hypothesis ledgers…. Focs Reproducibility is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when hardening a FOCS (IEEE Symposium on Foundations of Computer Science) paper's checkability — the theory analogue of reproducibility — via hypothesis ledgers, single-source theorem statements that cannot drift between submission and arXiv versions, audits of imported theorems, and certificates for machine-checked steps.

When should I use Focs Reproducibility?

Focs Reproducibility fits situations like: single-source theorem statements that cannot drift between submission and arXiv versions; audits of imported theorems; certificates for machine-checked steps.

How do I install Focs Reproducibility in Claude Code?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill focs-reproducibility -a claude-code`. Or copy the skill folder (FOCS-Skills/skills/focs-reproducibility in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/focs-reproducibility in your project. Claude Code loads it when a task matches its description.

How do I install Focs Reproducibility in Codex?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill focs-reproducibility -a codex`. Or copy the skill folder (FOCS-Skills/skills/focs-reproducibility in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/focs-reproducibility in your project. Codex loads it when a task matches its description.

Can I use Focs Reproducibility in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill focs-reproducibility -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/focs-reproducibility, .gemini/skills/focs-reproducibility, .github/skills/focs-reproducibility and .opencode/skills/focs-reproducibility in your project.

What does Focs Reproducibility need to run?

SKILL.md names no scripts, command-line tools or credentials: Focs Reproducibility is instructions for the agent only.

Does Focs Reproducibility access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Focs Reproducibility safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Focs Reproducibility use?

Focs Reproducibility is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Focs Reproducibility use?

About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Focs Reproducibility?

Skills that share tags, products or a category with Focs Reproducibility: Literature Review (K-Dense-AI/scientific-agent-skills, 48k stars), Literature Search Methodology (aiming-lab/AutoResearchClaw, 15k stars), Paper Lens (YSQ-boop/paper-lens, 101 stars) and Read arXiv Paper (karpathy/nanochat, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Focs Reproducibility?

brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,231 GitHub stars. The repository holds 2,387 skills in this directory. The repository was last updated on September 27, 2026.

Source: brycewang-stanford/Awesome-Journal-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.