Automated summary

Performs an independent audit of reproducibility and release evidence for a model, dataset, run, or deployment, then returns a PASS, FAIL, or ABSTAIN verdict.

Strengths

Requires an evidence index with exact paths, revisions, hashes, and timestamps before any conclusion
Explicitly labels each value as measured, derived, unknown, or contradicted
Rejects self-approval by the experimenter or deployer and routes each gap to a named upstream owner
Clearly separates ABSTAIN (insufficient evidence) from FAIL (a known gate is violated)

Limitations

Assumes the referenced artifacts (requirements lock, validation reports, manifests) already exist and are accessible
Produces no measurements itself, so without supplied evidence the verdict defaults to ABSTAIN
Relies on internal reference files (audit-report, release-gates) whose contents are not detailed in the SKILL.md

When to use it

Use it when you need an evidence-backed decision on whether a model, dataset, run, or deployment may pass a release gate.

When not to use it

Avoid it for training, fixing, or mutating artifacts, or when no verifiable evidence exists and a binary answer is expected.

Security analysis

Safe

Quality score82/100

The skill is an audit checklist for ML release and reproducibility claims. It declares no tools, requests no execution, and contains no destructive, exfiltration, obfuscation, or safety-disabling instructions. Its only external references are documentation files for audit reporting, claims, gates, and privacy/licensing.

No concerns found

How this analysis is made

Examples

Release readiness check

Audit whether we can ship recommender-v3 to production. Requirements lock is at reqs/requirements.lock, run record in MLflow run 8f2c1a, artifact hashes in artifacts/manifest.json. Give me PASS, FAIL, or ABSTAIN with blocking evidence.

Reproducibility verification

Check whether the results in reports/validation-2024-11.md can be reproduced from the recorded environment and model revision. Flag leakage, split mismatches, and missing provenance with exact paths and hashes.

License and privacy gate

Before promoting this dataset, reconcile the licensing and privacy evidence in docs/privacy-review.pdf and licenses/ against the claims in research/claims.md, and tell me which upstream owner must fix any gap.

name: ml-stack-audit description: Independently audit ML release and reproducibility claims when a user asks whether a model, dataset, run, artifact, or deployment is ready; reconcile provenance, hashes, privacy, licenses, and gates with PASS, FAIL, or ABSTAIN.

Independent release audit

Name: ML Release Audit & Reproducibility
Author: Skills Guide Bot

Require requirements lock, data audit, validation report, research claims, model revisions, run and tracking records, artifact hashes, privacy/licensing evidence, deliverable schema, promotion state, and immutable manifests.

Workflow

Build an evidence index with exact paths, URLs, revisions, hashes, timestamps, and owners.
Reconcile every requirement, claim, dataset split, model/tokenizer, environment, metric, artifact, and approval against measured evidence.
Check reproducibility, leakage, privacy, license, schema, provenance, and promotion gates; label measured, derived, unknown, and contradicted values.
Review release target and rollback state independently; do not accept the experimenter's or deployer's self-approval.
Return exactly PASS, FAIL, or ABSTAIN, blocking evidence, remediation, and next owner: ml-stack-deployment only after PASS, otherwise the named upstream owner.

Boundary and outputs

Never fill missing evidence with assumptions, mutate artifacts, or approve an unobserved operation. ABSTAIN means evidence is insufficient; FAIL means a known gate is violated. Return an audit report with exact paths and hashes. Next owner is ml-stack-deployment after PASS, ml-stack-experiment for reproducibility gaps, ml-stack-data for leakage/privacy gaps, or ml-stack-hub for metadata/licensing gaps.

See audit report, claims and provenance, release gates, and privacy and licensing.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/ml-release-audit-reproducibility-mu6guq3x/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/ml-release-audit-reproducibility-mu6guq3x/download' --output '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x/SKILL.md.part' && mv '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x/SKILL.md.part' '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x/SKILL.md' && test -s '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/ml-stack-audit' && cp -R '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x' '.claude/skills/ml-stack-audit'

Cursor

test -f '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x/SKILL.md' && test -s '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/ml-stack-audit' && cp -R '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x' '.cursor/skills/ml-stack-audit'

Codex

test -f '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x/SKILL.md' && test -s '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/ml-stack-audit' && cp -R '.skill-downloads/ml-release-audit-reproducibility-mu6guq3x' '.agents/skills/ml-stack-audit'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/ml-release-audit-reproducibility-mu6guq3x'

openskills read 'ml-release-audit-reproducibility-mu6guq3x'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/ml-release-audit-reproducibility-mu6guq3x/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Create Interactive Maps with kepler.gl

Data & AI

Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.

Claude CodeCursorCodexintermediateSafe 11,995

Skills Guide Bot