aiopshwang/data-analysis-ml-agent-skills / skills/shipping-reproducible-results
shipping-reproducible-results
VerifiedPackage completed data analysis and ML work so an independent recipient can reproduce the claimed results, verify artifact lineage, and operate the handoff within its stated scope. Use when finalizing a project, study, model package, or review bundle; not for deploying to a live system.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.3 KB |
| agents/openai.yaml | config | 265 B |
| assets/reproduction-handoff.md | markdown | 3.2 KB |
| assets/run-manifest.yaml | config | 1.4 KB |
| references/reproduction-contract.md | markdown | 4.6 KB |
assets/reproduction-handoff.md
View on GitHub# Reproduction and Handoff Record
## Release identity
- **Project / release:**
- **Version / commit:**
- **Release owner and date:**
- **Status:** reproduced / ready for independent reproduction / replayable with constraints / archival evidence only
- **Independent runner:**
- **Clean-room run ID and date:**
- **Decision supported by this release:**
## Supported scope
- **Question and claims:**
- **Population, unit, and time window:**
- **Authoritative outputs:**
- **Exploratory outputs:**
- **Explicitly unsupported uses:**
## Canonical entry point
```text
COMMAND_FROM_CLEAN_STATE
```
- **Expected runtime / compute / external cost:**
- **Required access and credential owner:**
- **Output and cache locations:**
- **Failure behavior:**
## Artifact and lineage map
| Artifact | Role | Version / hash | Produced by | Upstream IDs | Canonical? | Privacy / retention |
|---|---|---|---|---|---:|---|
| | | | | | | |
## Input contract
| Input | Snapshot / query identity | Schema / row checks | Access procedure | Mutability risk |
|---|---|---|---|---|
| | | | | |
## Environment contract
- **Runtime and lockfile:**
- **OS / container:**
- **Native libraries:**
- **Accelerator / driver:**
- **Locale / timezone:**
- **Required environment variable names:**
- **Seeds and remaining nondeterminism:**
## Acceptance criteria
| Output or invariant | Expected identity / value | Comparison method | Tolerance | Actual | Pass? |
|---|---|---|---|---|---:|
| | | | | | |
## Completion matrix
| Stage | Required? | Evidence / log ID | Independently run? | Result | Constraint or owner |
|---|---:|---|---:|---|---|
| Environment creation | | | | | |
| Input acquisition and verification | | | | | |
| Preprocessing / features | | | | | |
| Model loading or training | | | | | |
| Evaluation and independent validation | | | | | |
| Final output generation | | | | | |
| Expected-output comparison | | | | | |
## Human decisions and manual steps
| Date | Actor / role | Decision or edit | Input artifact | Output artifact | Rationale |
|---|---|---|---|---|---|
| | | | | | |
## Known limitations and rejected approaches
- **Missing or unproven stages:**
- **Data and ground-truth limitations:**
- **Nondeterministic behavior:**
- **Rejected hypotheses / failed experiments that matter:**
- **Evidence that would change the result:**
## Operations and ownership
| Concern | Signal / trigger | Required action | Owner / escalation |
|---|---|---|---|
| Source or schema drift | | | |
| Performance or claim drift | | | |
| Dependency or artifact expiry | | | |
| Retraining / revalidation | | | |
| Retirement | | | |
## Release checks
- [ ] No secrets or credential values
- [ ] No unintended private or personal data
- [ ] No machine-specific absolute paths
- [ ] Canonical artifacts are unambiguous
- [ ] Declared dependencies and licenses are present
- [ ] Public release history was checked for sensitive artifacts
- [ ] Recipient acknowledged constraints and ownership
## Sign-off
| Role | Name | Decision | Date | Conditions |
|---|---|---|---|---|
| Release owner | | | | |
| Independent runner | | | | |
| Receiving owner | | | | |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |