Audit Replication
brycewang-stanford/Auto-Empirical-Research-Skills
Validate the replication package for the sewage-house-prices project.
A skill your agent uses when strengthening the reproducibility of an RSS (Robotics: Science and Systems) paper whose evidence lives partly on hardware — platform disclosure ledgers, log-backed trial…
Install Rss Reproducibility
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill rss-reproducibility -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills rss-reproducibility --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/RSS-Skills/skills/rss-reproducibility .claude/skills/rss-reproducibility && rm -rf skills-srcUse ~/.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/
Install the "rss-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/RSS-Skills/skills/rss-reproducibility into .claude/skills/rss-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rss-reproducibility", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/RSS-Skills/skills/rss-reproducibilityType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill rss-reproducibility -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills rss-reproducibility --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/RSS-Skills/skills/rss-reproducibility .agents/skills/rss-reproducibility && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "rss-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/RSS-Skills/skills/rss-reproducibility into .agents/skills/rss-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rss-reproducibility", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill rss-reproducibility -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills rss-reproducibility --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/RSS-Skills/skills/rss-reproducibility .cursor/skills/rss-reproducibility && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "rss-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/RSS-Skills/skills/rss-reproducibility into .cursor/skills/rss-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rss-reproducibility", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/brycewang-stanford/Awesome-Journal-Skills.git --path RSS-Skills/skills/rss-reproducibility--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill rss-reproducibility -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills rss-reproducibility --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/RSS-Skills/skills/rss-reproducibility .gemini/skills/rss-reproducibility && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "rss-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/RSS-Skills/skills/rss-reproducibility into .gemini/skills/rss-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rss-reproducibility", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills rss-reproducibilityInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill rss-reproducibility -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/RSS-Skills/skills/rss-reproducibility .github/skills/rss-reproducibility && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "rss-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/RSS-Skills/skills/rss-reproducibility into .github/skills/rss-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rss-reproducibility", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill rss-reproducibility -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills rss-reproducibility --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/RSS-Skills/skills/rss-reproducibility .opencode/skills/rss-reproducibility && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "rss-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/RSS-Skills/skills/rss-reproducibility into .opencode/skills/rss-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rss-reproducibility", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
rss-reproducibility- GitHub stars
- 1.2k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 684 words
- Files
- 1
- Skills in repo
- 2,387
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when strengthening the reproducibility of an RSS (Robotics: Science and Systems) paper whose evidence lives partly on hardware — platform disclosure ledgers, log-backed trial…
- Log-backed trial claims
- SKILL.md covers Replication tiers — declare…, The platform ledger, Log-backed claims and What to capture during the…, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Seeds and configs for the computational half
What it does
Rss Reproducibility is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when strengthening the reproducibility of an RSS (Robotics: Science and Systems) paper whose evidence lives partly on hardware — platform disclosure ledgers, log-backed trial claims, seeds and configs for the computational half, honest replication tiers, and release plans aligned with the free open-access proceedings culture.
Its SKILL.md is about 1.5k 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, Feature launches and release readiness and Database administration. 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
- Log-backed trial claims
- Seeds and configs for the computational half
- Honest replication tiers
- Release plans aligned with the free open-access proceedings culture
Example prompts
- “/rss-reproducibility”
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.
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
Rss Reproducibility loads about 1.5k tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 684 words of instructions outside code blocks.
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). 684 words, ~1,477 tokens.
Download SKILL.mdSave it as
.claude/skills/rss-reproducibility/SKILL.md (or your agent's skills folder).- name
- rss-reproducibility
- description
- Use when strengthening the reproducibility of an RSS (Robotics: Science and Systems) paper whose evidence lives partly on hardware — platform disclosure ledgers, log-backed trial claims, seeds and configs for the computational half, honest replication tiers, and release plans aligned with the free open-access proceedings culture.
RSS Reproducibility
Make an embodied result checkable. Robotics reproducibility is two different problems wearing one name: the computational half (code, seeds, configs) can be rerun by anyone; the physical half (this robot, this room, this cloth) can only be specified well enough for a peer lab to attempt replication. Treat the halves separately and state which tier each claim sits in.
Replication tiers — declare one per claim
| Tier | What a reader can do | Minimum you must provide |
|---|---|---|
| Rerunnable | Reproduce the number from the release | Code, seeds, configs, data, one entry command |
| Re-collectable | Regenerate equivalent data on similar hardware | Full platform ledger + protocol document |
| Auditable | Verify your numbers follow from your logs | Raw trial logs + analysis scripts |
| Testimonial | Trust the authors | Nothing — and reviewers price it accordingly |
A paper mixing tiers is fine; a paper implying Rerunnable while delivering Testimonial is the credibility failure RSS reviewers punish hardest.
The platform ledger
For the physical half, disclosure is the reproducibility. A peer lab needs:
- Robot make/model and any modifications; end-effector; sensor suite with mounting and calibration procedure; control frequency and stack (firmware through policy).
- Environment specifics that carry load: table friction, lighting, object sourcing (purchasable items beat lab-fabricated ones), workspace dimensions.
- Human procedure: reset steps, intervention rules, operator role — written as instructions, not narrative.
- Timing facts that gate feasibility: wall-clock per trial, total campaign hours, battery/thermal constraints that shaped the protocol.
Log-backed claims
The strongest robotics reproducibility artifact is the raw trial ledger:
trial_0142 cond=gripper_B obj=towel_3 seed=1142
result=fail cause=release_timing video=clips/0142.mp4
notes=operator_intervention:none- One row per attempt, appended at collection time, never edited afterward.
- Analysis scripts consume the ledger and emit every table in the paper — so PDF numbers cannot drift from evidence.
- Ship the ledger (anonymized) in the supplement; it converts "trust us" trial counts into auditable ones.
What to capture during the campaign (not after)
Reproducibility in robotics is mostly a collection-time discipline; these cannot be reconstructed later:
- Per-trial ledger rows (above) appended live, including aborted attempts.
- Camera footage of every trial, named by trial ID — storage is cheaper than a
re-run campaign, and it doubles as
rss-supplementaryraw material. - Calibration snapshots (camera extrinsics, force-torque zeroing) at session start, so drift between sessions is diagnosable.
- Software state per session: commit hash, config checksum, simulator build.
- Environmental incidentals that later become reviewer questions: object wear, lighting changes, floor surface swaps.
- A daily one-paragraph campaign log; six weeks later it is the only honest answer to "why does condition B have 19 trials instead of 25?"
Show full SKILL.md (280 more words)Show less
Computational half: standard, therefore mandatory
- Seeds for every stochastic component (policy training, sampler init, domain randomization) and the variance across them, not one lucky seed.
- Exact dependency manifest, simulator version and physics timestep, GPU/CPU spec, and training wall-clock.
- Config files as the single source of hyperparameters; no numbers living only in the paper text.
Release plan and the venue's open culture
RSS proceedings are free to every reader at roboticsproceedings.org; a paywalled PDF
with closed evidence would be off-culture. Plan the release in two states: anonymized
supplement at submission (rss-supplementary), public repository + ledger + footage
at camera-ready (rss-camera-ready). If something cannot be released (proprietary
platform, safety), say what and why in the paper — a stated gap reads as honesty, a
silent one as concealment.
Vignette: an honest tier map
A paper couples a learned grasp ranker (trained in simulation) with hardware clutter-clearing trials. Its declared map: the simulation training curves and ranker metrics are Rerunnable (seeds, configs, dataset, one command); the hardware success rates are Auditable (ledger plus analysis scripts shipped) and Re-collectable for labs with a comparable arm (platform ledger and protocol document provided); the wear-dependent behavior of one deformable object is Testimonial, and the paper says so in one sentence. Reviewers can now disagree with the evidence, but not discover its limits by surprise — which is the entire game.
Simulator determinism caveats
- Physics engines are only conditionally deterministic: thread counts, contact solver iterations, and hardware can change trajectories under the same seed. Record engine version, timestep, solver settings — and state whether exact replay or statistical equivalence is the reproduction target.
- GPU nondeterminism in training means "same seed" still needs a variance report across seeds to be meaningful.
Output format
[Tier map] <claim -> Rerunnable/Re-collectable/Auditable/Testimonial>
[Platform ledger] complete / gaps: <list>
[Trial ledger] exists+shipped / exists / absent
[Computational gaps] <seeds/configs/versions/variance>
[Release plan] <submission state -> camera-ready state>
[Honesty debt] <implied tier above delivered tier, if any>© 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 RSS-Skills/skills/rss-reproducibility of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Rss 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Rss Reproducibility this skillbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Audit Replicationbrycewang-stanford/Auto-Empirical-Research-Skills | 4.5k | — | ~984 | Automated safety check: Notes | Custom licence | |
| Ectheory Replication And Data Policyfranklee16/academic-research-skills | 223 | 1 repos | ~983 | Automated safety check: Pass | None | |
| Qe Replication And Data Policyfranklee16/academic-research-skills | 223 | 1 repos | ~1.2k | Automated safety check: Pass | None | |
| Methods Reverse Engineeraipoch/medical-research-skills | 2k | — | ~4k | Automated safety check: Pass | MIT | |
| Audit Reproducibilitypedrohcgs/claude-code-my-workflow | 1.7k | — | ~6.4k | Automated safety check: Notes | MIT |
Similar skills
Ectheory Replication And Data Policy
franklee16/academic-research-skills
A skill your agent uses to handle reproducibility and the supplementary-material file for an Econometric Theory (ET) paper — ET has no mandatory data/code archive (theory journal); the relevant…
Qe Replication And Data Policy
franklee16/academic-research-skills
A skill your agent uses to assemble a Quantitative Economics (QE) replication package that passes the Econometric Society Data Editor's pre-acceptance reproducibility check — raw data, code…
Methods Reverse Engineer
aipoch/medical-research-skills
Reverse-engineers the methods section of a biomedical paper into a structured, reproducible workflow.
Audit Reproducibility
pedrohcgs/claude-code-my-workflow
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs.
Apsr Transparency And Data Policy
franklee16/academic-research-skills
A skill your agent uses when preparing the reproducibility / replication materials for an American Political Science Review (APSR) manuscript.
More from brycewang-stanford/Awesome-Journal-Skills
All 2,387 skills in this repoAaag 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…
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…
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…
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…
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…
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…
Related
Categories
Questions about Rss Reproducibility
What does Rss Reproducibility do?
A skill your agent uses when strengthening the reproducibility of an RSS (Robotics: Science and Systems) paper whose evidence lives partly on hardware — platform disclosure ledgers, log-backed trial…. Rss Reproducibility is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when strengthening the reproducibility of an RSS (Robotics: Science and Systems) paper whose evidence lives partly on hardware — platform disclosure ledgers, log-backed trial claims, seeds and configs for the computational half, honest replication tiers, and release plans aligned with the free open-access proceedings culture.
When should I use Rss Reproducibility?
Rss Reproducibility fits situations like: log-backed trial claims; seeds and configs for the computational half; honest replication tiers; release plans aligned with the free open-access proceedings culture.
How do I install Rss Reproducibility in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill rss-reproducibility -a claude-code`. Or copy the skill folder (RSS-Skills/skills/rss-reproducibility in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/rss-reproducibility in your project. Claude Code loads it when a task matches its description.
How do I install Rss Reproducibility in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill rss-reproducibility -a codex`. Or copy the skill folder (RSS-Skills/skills/rss-reproducibility in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/rss-reproducibility in your project. Codex loads it when a task matches its description.
Can I use Rss 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 rss-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/rss-reproducibility, .gemini/skills/rss-reproducibility, .github/skills/rss-reproducibility and .opencode/skills/rss-reproducibility in your project.
What does Rss Reproducibility need to run?
SKILL.md names no scripts, command-line tools or credentials: Rss Reproducibility is instructions for the agent only.
Does Rss 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 Rss 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 Rss Reproducibility use?
Rss 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 Rss Reproducibility use?
About 1.5k tokens (SKILL.md is roughly 5.9k 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 Rss Reproducibility?
Skills that share tags, products or a category with Rss Reproducibility: Audit Replication (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Ectheory Replication And Data Policy (franklee16/academic-research-skills, 223 stars), Qe Replication And Data Policy (franklee16/academic-research-skills, 223 stars) and Methods Reverse Engineer (aipoch/medical-research-skills, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Rss Reproducibility?
brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,228 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.