analyticsengineering/ae-toolkit / skills/freshness-investigation
freshness-investigation
VerifiedInvestigates whether analytical data is ready by separating configured schedules and freshness expectations from locally observed timestamps and run artifacts. Use when data appears stale, late, incomplete, or unavailable, and before raising a freshness threshold or silencing a failing check; it explains timing evidence and gaps without inventing runtime history or querying external systems.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.2 KB |
| references/diagrams.md | markdown | 3.2 KB |
| references/operating-rules.md | markdown | 23.3 KB |
| references/privacy.md | markdown | 2.0 KB |
| references/severity-model.md | markdown | 1.5 KB |
| references/terminology.md | markdown | 1.9 KB |
| references/warehouse-portability.md | markdown | 4.9 KB |
| scripts/infer_conventions.py | script | 55.6 KB |
| scripts/inspect_dbt.py | script | 20.2 KB |
| scripts/inspect_git.py | script | 8.5 KB |
| scripts/inspect_repo.py | script | 13.5 KB |
| scripts/project_context.py | script | 27.4 KB |
| scripts/redact_secrets.py | script | 15.2 KB |
references/severity-model.md
View on GitHub# Review Severity Model
Use the highest severity justified by demonstrated impact. Do not inflate severity from style preference alone.
## Levels
- **Blocker** — Likely data loss, unauthorized disclosure, destructive production action, materially wrong published data, or an unusable critical pipeline. Must be resolved before release.
- **High** — Probable correctness, security, reliability, or cost failure with broad or important impact. Resolve before release unless an owner explicitly accepts the risk.
- **Medium** — Real but bounded issue affecting maintainability, observability, performance, or edge-case correctness. Plan a fix and verify it.
- **Low** — Small improvement with limited impact. Fix opportunistically.
- **Note** — Context, praise, question, or non-actionable observation. Not a defect.
## Required finding shape
Every actionable finding contains:
1. **Evidence** — Exact file, query, model, field, metric, or observed behavior. Separate fact from inference.
2. **Risk** — Who or what can be affected, how, and under which conditions.
3. **Recommendation** — Smallest practical change that addresses the cause.
4. **Verification** — Specific test, query, comparison, or acceptance criterion proving the change.
Include severity and confidence (`high`, `medium`, or `low`). State missing evidence rather than guessing. Combine duplicate findings and order results by severity, then confidence.
## Clean reviews
If no actionable findings are supported, say so. Still list verification performed, evidence gaps, and residual risks.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |