osx-generate-changelog

Solid

Generate CHANGELOG.md from archived OpenSpec changes (Keep a Changelog format). Run via /osx-changelog [filter].

AI & Automation 6 stars 1 forks Updated 1 weeks ago MIT

Install

View on GitHub

Quality Score: 82/100

Stars 20%
28
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

Generate CHANGELOG.md from archived OpenSpec changes using Keep a Changelog format. **IMPORTANT: This skill processes ARCHIVED changes only.** Changes must be archived via `osc-archive-change` (originally `openspec-archive-change`) before they appear in the changelog. Active (unarchived) changes are not included. **Prerequisite**: Changes must be archived in `openspec/changes/archive/YYYY-MM-DD-<name>/` --- ## Input Optionally specify filters. If omitted, processes all archived changes. **Arguments**: `[filter]` **Examples**: - `/{{CMD_PREFIX}}changelog` - Generate from all archived changes - `/{{CMD_PREFIX}}changelog --since 2025-01-01` - Changes after date - `/{{CMD_PREFIX}}changelog add-dark-mode` - Only specific change(s) --- ## Steps ### 1. Discover archived changes ```bash find openspec/changes/archive -type d -name "[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]-*" | sort ``` Returns directories like `openspec/changes/archive/2026-02-12-add-dark-mode/`. ### 2. Apply filters **Date filter** (`--since YYYY-MM-DD`): parse date from directory name (first 10 chars); include only changes after the specified date. **Specific changes**: filter to only the named change(s); match against the `<name>` portion of directory. ### 3. Read proposal files For each archived change, read `proposal.md`: ``` openspec/changes/archive/YYYY-MM-DD-<name>/proposal.md ``` Extract from each proposal: - **## Summary**: First paragraph for changelog entry - **## Proposed Change**: De...

Details

Author
amauryconstant
Repository
amauryconstant/openspec-extended
Created
7 months ago
Last Updated
1 weeks ago
Language
TypeScript
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category