Mle Workflow
affaan-m/ECC
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback.
A skill your agent uses when designing or auditing the evaluation of an ACM CoNEXT paper — matching evidence to claim shape with real testbeds and deployments, honest and tuned baselines…
Install Conext Experiments
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill conext-experiments -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills conext-experiments --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/CoNEXT-Skills/skills/conext-experiments .claude/skills/conext-experiments && 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 "conext-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/CoNEXT-Skills/skills/conext-experiments into .claude/skills/conext-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conext-experiments", 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/CoNEXT-Skills/skills/conext-experimentsType 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 conext-experiments -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills conext-experiments --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/CoNEXT-Skills/skills/conext-experiments .agents/skills/conext-experiments && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "conext-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/CoNEXT-Skills/skills/conext-experiments into .agents/skills/conext-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conext-experiments", 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 conext-experiments -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills conext-experiments --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/CoNEXT-Skills/skills/conext-experiments .cursor/skills/conext-experiments && 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 "conext-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/CoNEXT-Skills/skills/conext-experiments into .cursor/skills/conext-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conext-experiments", 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 CoNEXT-Skills/skills/conext-experiments--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 conext-experiments -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills conext-experiments --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/CoNEXT-Skills/skills/conext-experiments .gemini/skills/conext-experiments && 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 "conext-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/CoNEXT-Skills/skills/conext-experiments into .gemini/skills/conext-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conext-experiments", 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 conext-experimentsInstalls 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 conext-experiments -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/CoNEXT-Skills/skills/conext-experiments .github/skills/conext-experiments && 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 "conext-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/CoNEXT-Skills/skills/conext-experiments into .github/skills/conext-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conext-experiments", 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 conext-experiments -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 conext-experiments --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/CoNEXT-Skills/skills/conext-experiments .opencode/skills/conext-experiments && 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 "conext-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/CoNEXT-Skills/skills/conext-experiments into .opencode/skills/conext-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "conext-experiments", 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
conext-experiments- GitHub stars
- 1.2k
- Token cost
- ~1.4k tokens
- SKILL.md length
- 583 words
- Files
- 1
- Skills in repo
- 2,387
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when designing or auditing the evaluation of an ACM CoNEXT paper — matching evidence to claim shape with real testbeds and deployments, honest and tuned baselines…
- Auditing the evaluation of an ACM CoNEXT paper — matching evidence to claim shape with real testbeds and deployments
- SKILL.md covers Match evidence to claim shape, Real testbeds and deployments…, Honest, tuned baselines and Measurement statistics and…, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Honest and tuned baselines
What it does
Conext Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the evaluation of an ACM CoNEXT paper — matching evidence to claim shape with real testbeds and deployments, honest and tuned baselines, measurement statistics and uncertainty, trace and config provenance, and contamination-aware ablations for ML-for-networking work.
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 Data & Analytics, covering Deployment and Statistics. 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
- Auditing the evaluation of an ACM CoNEXT paper — matching evidence to claim shape with real testbeds and deployments
- Honest and tuned baselines
- Measurement statistics and uncertainty
- Trace and config provenance
Example prompts
- “/conext-experiments”
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
Conext Experiments loads about 1.4k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 583 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). 583 words, ~1,365 tokens.
Download SKILL.mdSave it as
.claude/skills/conext-experiments/SKILL.md (or your agent's skills folder).- name
- conext-experiments
- description
- Use when designing or auditing the evaluation of an ACM CoNEXT paper — matching evidence to claim shape with real testbeds and deployments, honest and tuned baselines, measurement statistics and uncertainty, trace and config provenance, and contamination-aware ablations for ML-for-networking work.
CoNEXT Experiments
Build the evaluation a networking reviewer will actually interrogate. CoNEXT's evidence culture is systems-and-measurement: claims are backed on the real target platform — a testbed, deployment, or trace — with honest baselines and reported uncertainty, not simulation standing in for hardware or a single number with no variance. Because a one-shot major revision is decided on a list of minimum necessary changes, an evaluation gap you leave now often becomes a mandatory fix under a tight window later.
Match evidence to claim shape
| Claim shape | Evidence CoNEXT expects |
|---|---|
| A mechanism is faster/cheaper on real hardware | A run on the real target (switch, NIC, kernel, testbed) under its real constraints, vs. a tuned baseline, with effect sizes |
| A phenomenon exists in the wild | A measurement campaign with documented vantage points, capture dates, and a reproducible extraction methodology |
| An architecture scales | Scalability evidence (real deployment or faithful emulation) across the relevant range, not a point claim |
| An operator intervention helps | Evidence at operationally relevant scale, with the counterfactual measured or bounded |
| A learned component adds value | An ablation isolating the learned part from the mechanism, plus a contamination check |
Real testbeds and deployments over simulation
- Evaluate on the platform the paper is about. If the claim is about switch behavior, run it on the switch (or a faithful hardware testbed); if about a protocol on real paths, use a testbed or trace-driven replay. Simulation-only systems claims are a classic CoNEXT revision risk.
- Describe the testbed so it can be rebuilt: topology, hardware models, firmware/OS versions, link rates, buffer depths, and background traffic. A reviewer who cannot picture the setup cannot trust the numbers.
- State what is emulated vs. real, and why the emulation is faithful for the claim.
Honest, tuned baselines
- Compare against the strongest reasonable baseline, tuned with an equal, documented budget — not a strawman default. "The baseline is not tuned/fair" is one of the most common CoNEXT push-backs.
- Report the baseline's configuration alongside yours so the comparison is auditable.
- Where a fair baseline does not exist, say so and justify the comparison you made.
Show full SKILL.md (239 more words)Show less
Measurement statistics and uncertainty
- Report multiple runs and variability (confidence intervals, percentiles/CDFs for latency, not just means). Tail behavior is often the point in networking.
- Use corrected comparisons when testing many conditions; a measurement reviewer notices uncorrected multiple testing.
- Prefer effect sizes and distributions over a single bar; a CDF that shows the whole distribution pre-empts questions a mean hides.
Trace and config provenance (pin it now)
- Record capture vantage points and dates, the extraction/anonymization methodology, and the exact configs used. These cannot be reconstructed after the fact — pin them at collection time.
- For anything derived from operator or third-party data, document the access terms and what can be released (this interacts with double-anonymity and reproducibility).
- Keep the raw-to-result pipeline scripted so the numbers in the paper regenerate from the trace.
Contamination-aware ML-for-networking ablations
If the paper uses a learner or LLM on networking data:
- Isolate the learned component with an ablation (e.g., replace it with a heuristic) so the reviewer sees its marginal value over the mechanism.
- Guard against contamination/leakage: ensure test paths/traces/time windows are disjoint from training, and that a temporal split reflects real deployment.
- Pin model identifiers and dates and cache raw model outputs; a package that needs live API
calls re-samples rather than reproduces (see
conext-reproducibility). - Apply the model-swap test: if the networking lesson does not survive swapping the model, the
paper may belong at an ML venue (see
conext-topic-selection).
Pre-submission evaluation audit
[Claim coverage] every claim has a matching measurement on the real target? yes/no
[Platform realism] real hardware/testbed/trace, or simulation standing in? note each
[Baselines] strongest reasonable, equally tuned, config reported? yes/no
[Uncertainty] multiple runs, CIs/CDFs, corrected comparisons? yes/no
[Provenance] vantage points, dates, configs, firmware/OS pinned? yes/no
[ML checks] ablation + contamination guard + model-swap survives? n/a or yes/noOutput format
[Evaluation status] solid / gaps
[Claim-evidence matrix] <claim -> measurement + platform + baseline + uncertainty>
[Platform] real target used? emulation justified?
[Provenance] traces/configs/firmware pinned for reproducibility
[Revision risk] <the gap most likely to become a minimum-necessary change>© 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 CoNEXT-Skills/skills/conext-experiments of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Conext Experiments 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 |
|---|---|---|---|---|---|---|
| Conext Experiments this skillbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Mle Workflowaffaan-m/ECC | 275k | 1 repos | ~5.6k | Automated safety check: Pass | MIT | |
| Upgrading Mwaa Environmentsaws/agent-toolkit-for-aws | 2.8k | — | ~7.3k | Automated safety check: Pass | Apache-2.0 | |
| Senior Data Scientistborghei/Claude-Skills | 881 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Iot Anomaliesruvnet/ruflo | 74k | — | ~210 | Automated safety check: Pass | MIT | |
| ML Antipattern Validatoraiskillstore/marketplace | 430 | — | ~1.1k | Automated safety check: Pass | None |
Similar skills
- Official
Upgrading Mwaa Environments
aws/agent-toolkit-for-aws
Upgrades an MWAA environment to a newer Airflow version — within 2.x, within 3.x, or across the 2.x-to-3.x boundary.
Senior Data Scientist
borghei/Claude-Skills
A skill your agent uses when the user asks to "design an experiment", "build a predictive model", "run A/B test analysis", "perform causal inference", "engineer features", "evaluate model…
Iot Anomalies
ruvnet/ruflo
Detect and classify telemetry anomalies on Cognitum Seed devices.
ML Antipattern Validator
aiskillstore/marketplace
Prevents 30+ critical AI/ML mistakes including data leakage, evaluation errors, training pitfalls, and deployment issues.
Prefect
Kilo-Org/kilo-marketplace
Prefect is a modern workflow orchestration framework for Python data pipelines.
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 Conext Experiments
What does Conext Experiments do?
A skill your agent uses when designing or auditing the evaluation of an ACM CoNEXT paper — matching evidence to claim shape with real testbeds and deployments, honest and tuned baselines…. Conext Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the evaluation of an ACM CoNEXT paper — matching evidence to claim shape with real testbeds and deployments, honest and tuned baselines, measurement statistics and uncertainty, trace and config provenance, and contamination-aware ablations for ML-for-networking work.
When should I use Conext Experiments?
Conext Experiments fits situations like: auditing the evaluation of an ACM CoNEXT paper — matching evidence to claim shape with real testbeds and deployments; honest and tuned baselines; measurement statistics and uncertainty; trace and config provenance.
How do I install Conext Experiments in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill conext-experiments -a claude-code`. Or copy the skill folder (CoNEXT-Skills/skills/conext-experiments in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/conext-experiments in your project. Claude Code loads it when a task matches its description.
How do I install Conext Experiments in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill conext-experiments -a codex`. Or copy the skill folder (CoNEXT-Skills/skills/conext-experiments in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/conext-experiments in your project. Codex loads it when a task matches its description.
Can I use Conext Experiments 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 conext-experiments -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/conext-experiments, .gemini/skills/conext-experiments, .github/skills/conext-experiments and .opencode/skills/conext-experiments in your project.
What does Conext Experiments need to run?
SKILL.md names no scripts, command-line tools or credentials: Conext Experiments is instructions for the agent only.
Does Conext Experiments 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 Conext Experiments 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 Conext Experiments use?
Conext Experiments 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 Conext Experiments use?
About 1.4k tokens (SKILL.md is roughly 5.5k 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 Conext Experiments?
Skills that share tags, products or a category with Conext Experiments: Mle Workflow (affaan-m/ECC, 275k stars), Upgrading Mwaa Environments (aws/agent-toolkit-for-aws, 2.8k stars), Senior Data Scientist (borghei/Claude-Skills, 881 stars) and Iot Anomalies (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Conext Experiments?
brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,219 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.