Stats
Actions
Tags
From Claude-Data-Wrangler
Add or update a CHANGELOG.md in a data repository, recording dataset versions, schema changes, row-count deltas, enrichments applied, and re-publications. Follows Keep-a-Changelog conventions adapted for datasets. Use when the user wants versioned documentation of how a dataset has evolved over time.
How this skill is triggered — by the user, by Claude, or both
Slash command
/Claude-Data-Wrangler:add-changelogThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Maintain a `CHANGELOG.md` focused on dataset evolution rather than code.
Maintain a CHANGELOG.md focused on dataset evolution rather than code.
Adapted from Keep a Changelog, with dataset-specific sections:
# Changelog
All notable changes to this dataset are documented here.
This format is adapted from Keep a Changelog; versions follow SemVer-ish rules:
- MAJOR: breaking schema or semantic changes (column removed/renamed, unit change).
- MINOR: new columns, new rows, compatible enrichments.
- PATCH: fixes to existing values, documentation updates, no schema change.
## [Unreleased]
## [1.2.0] — 2026-04-23
### Added
- `currency_code`, `currency_symbol` columns via `enrich-with-currency` (ISO 4217).
- 1,204 new rows from 2026-Q1 source pull.
### Changed
- `revenue` column parsed from text to numeric; original preserved as `revenue_raw`.
- Country names standardised to ISO 3166 short names.
### Fixed
- 17 rows with `country = "USA"` corrected to "United States".
### Provenance
- Skills used: `standardise-country-names`, `add-iso3166`, `enrich-with-currency`, `text-to-numeric`.
- Data dictionary updated: 2026-04-23.
## [1.1.0] — 2026-03-15
...
CHANGELOG.md in the data repository root.VERSION file if present. If none, start at 1.0.0.## [Unreleased], or promote Unreleased to a new version with today's date.v1.2.0) and push it if the repo has a remote.Standard library only.
[1.0.0] baseline entry describing the dataset's initial state.[Unreleased] section already has pending entries, append rather than overwrite.### [customers] Added). Ask the user which dataset the change applies to.npx claudepluginhub danielrosehill/claude-code-plugins --plugin Claude-Data-WranglerSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.