Run any Skill in Manus with one click

add-changelog

Stars3

Forks0

UpdatedApril 23, 2026 at 14:14

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.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

danielrosehill

danielrosehill/Claude-Data-Wrangler-plugin

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	add-changelog
description	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.

Add Changelog (for Data Repositories)

Maintain a CHANGELOG.md focused on dataset evolution rather than code.

When to invoke

Data repository has no changelog and the user wants one.
After any skill that changes dataset content or schema (enrichment, cleaning, synthetic overlay, republication) and the user wants a log entry added.

Format

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
...

Procedure

Find or create CHANGELOG.md in the data repository root.
Determine the current version — from the most recent versioned heading, or from a VERSION file if present. If none, start at 1.0.0.
Classify the change — Added / Changed / Fixed / Removed / Deprecated / Security.
Infer the version bump:
- Schema breaking → MAJOR.
- New columns / new rows / enrichments → MINOR.
- Value fixes / doc updates → PATCH. Confirm with the user before applying.
Draft the entry — pull context from the data dictionary provenance log if available, and the git diff if the repository is under version control.
Insert at the top under ## [Unreleased], or promote Unreleased to a new version with today's date.
Write back the updated changelog.
Optionally tag — offer to create a git tag (v1.2.0) and push it if the repo has a remote.

Dependencies

Standard library only.

Edge cases

First-time changelog — produce a reasonable [1.0.0] baseline entry describing the dataset's initial state.
Concurrent edits — if an [Unreleased] section already has pending entries, append rather than overwrite.
Non-git repo — skip the tag step silently; just write the file.
Multi-dataset repo — if the repo holds multiple datasets, scope entries per dataset name (e.g. ### [customers] Added). Ask the user which dataset the change applies to.

More from this repository

same repository

header-standardisation

danielrosehill/Claude-Data-Wrangler-plugin

Audit and standardise a dataset's header row against a naming convention (snake_case, camelCase, Title Case, kebab-case) and verify consistency with an existing or forthcoming data dictionary. Use when preparing a dataset for SQL loading, publishing, or when header inconsistency (mixed casing, spaces, punctuation, abbreviation drift) is blocking downstream work.

2026-04-233

localization-headers

danielrosehill/Claude-Data-Wrangler-plugin

Produce localised versions of a dataset and/or its data dictionary with translated column headers (and optionally translated dictionary descriptions) so the same underlying data can be analysed by speakers of different languages. Use when the user wants frictionless multi-language packaging — e.g. English canonical plus Hebrew, Arabic, French, Spanish variants — without forking the underlying data.

2026-04-233

numeric-rounding

danielrosehill/Claude-Data-Wrangler-plugin

Audit numeric columns for inconsistent decimal precision (e.g. some values at 4 dp, others at 2 dp) and round all values to a user-chosen precision. Use before SQL load or publishing when mixed precision would otherwise produce awkward `NUMERIC(x, y)` choices or misleading implied precision.

2026-04-233

data-to-document

danielrosehill/Claude-Data-Wrangler-plugin

Generate a polished PDF document from a dataset using Typst, with layout chosen to match the data shape (wide tables → landscape multi-page reference, narrow tables → portrait report, per-record → one-record-per-page card/profile layout, grouped → sectioned report). Supports user-selected field subsets, custom column labels, optional filtering/sorting, cover page, summary stats, and branded templates. Use when the user wants the dataset (or a slice of it) rendered as a shareable/printable document rather than a spreadsheet export.

2026-04-233

divergent-data-pipe

danielrosehill/Claude-Data-Wrangler-plugin

Reconcile a canonical upstream data file with a downstream project that has diverged — the downstream has added enrichments, renamed columns, changed types, or restructured the data, so fresh upstream rows can't be loaded incrementally without transformation. Builds a mapping between upstream and downstream representations and generates an idempotent incremental sync script that ingests only new/changed rows from upstream, applies the transformation, and appends/upserts them into the downstream dataset. Use when a project's working data has evolved beyond the source and new source data needs to flow in without clobbering the divergence.

2026-04-233

geodata-formatter

danielrosehill/Claude-Data-Wrangler-plugin

Convert tabular geodata (CSV / Excel / Parquet) into GeoJSON (or GeoJSON Seq / newline-delimited GeoJSON) — inferring geometry from lat/lon columns, WKT/WKB columns, or address columns via geocoding. Handles CRS reprojection (default WGS84 / EPSG:4326), feature property selection, and large-file streaming. Use when the user has location data in flat form and needs it as GeoJSON for mapping, GIS, or geospatial analysis tools.

2026-04-233

name	add-changelog
description	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.

Add Changelog (for Data Repositories)

Maintain a CHANGELOG.md focused on dataset evolution rather than code.

When to invoke

Data repository has no changelog and the user wants one.
After any skill that changes dataset content or schema (enrichment, cleaning, synthetic overlay, republication) and the user wants a log entry added.

Format

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
...

Procedure

Find or create CHANGELOG.md in the data repository root.
Determine the current version — from the most recent versioned heading, or from a VERSION file if present. If none, start at 1.0.0.
Classify the change — Added / Changed / Fixed / Removed / Deprecated / Security.
Infer the version bump:
- Schema breaking → MAJOR.
- New columns / new rows / enrichments → MINOR.
- Value fixes / doc updates → PATCH. Confirm with the user before applying.
Draft the entry — pull context from the data dictionary provenance log if available, and the git diff if the repository is under version control.
Insert at the top under ## [Unreleased], or promote Unreleased to a new version with today's date.
Write back the updated changelog.
Optionally tag — offer to create a git tag (v1.2.0) and push it if the repo has a remote.

Dependencies

Standard library only.

Edge cases

First-time changelog — produce a reasonable [1.0.0] baseline entry describing the dataset's initial state.
Concurrent edits — if an [Unreleased] section already has pending entries, append rather than overwrite.
Non-git repo — skip the tag step silently; just write the file.
Multi-dataset repo — if the repo holds multiple datasets, scope entries per dataset name (e.g. ### [customers] Added). Ask the user which dataset the change applies to.