Use this skill when creating or working with CHANGELOG fragments. CHANGELOG fragments are ongoing documentation of changes, stored in the `CHANGELOG/` directory.
Creates dated changelog fragments in the `CHANGELOG/` directory to document changes without merge conflicts. Claude uses this when implementing features, fixes, or significant changes that should be permanently documented with searchable, chronological history.
/plugin marketplace add lefant/claude-code-plugins/plugin install lefant@lefant-claude-code-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
examples/chore-example.mdexamples/feature-example.mdexamples/fix-example.mdtemplate.mdUse this skill when creating or working with CHANGELOG fragments. CHANGELOG fragments are ongoing documentation of changes, stored in the CHANGELOG/ directory.
Access this skill with: /skill changelog-fragments
Using changelog fragments prevents merge conflicts in CHANGELOG.md when multiple feature branches are developed in parallel. Each change creates its own fragment file, which stays as permanent documentation rather than being archived.
Fragments are named using date-based patterns:
YYYY-MM-DD_brief-description.md2025-11-19_branch-management-research.md2025-11-05_sync-database-tracking.md2025-11-03_test-env-migration.mdThis naming convention:
Fragments follow this structure:
---
date: YYYY-MM-DD
author: Your Name (optional)
type: feature|fix|chore|docs|refactor|test|perf
related_issues: []
related_prs: []
related_devlog: thoughts/shared/devlog/YYYY-MM-DD_implementation.md (optional)
---
Brief summary of the change (1-3 sentences). Focus on what changed and why it matters.
## Details (optional)
More detailed explanation if needed:
- Bullet points for key changes
- Important technical decisions
- Breaking changes or migration notes
For simple changes, a minimal format is acceptable:
---
date: 2025-11-19
type: fix
---
Fixed bug in test configuration where environment variables were not properly validated.
Create a CHANGELOG fragment for:
Skip fragments for:
Fragments are ongoing documentation and stay in the CHANGELOG/ directory permanently. They provide:
grep through fragments)To find when something changed:
grep -r "search term" CHANGELOG/
To see all changes of a specific type:
grep "^type: feature" CHANGELOG/*.md
To list recent changes chronologically:
ls -1 CHANGELOG/2025-*.md | tail -10
Template location: lefant-claude-code-plugins/lefant/skills/changelog-fragments/template.md
Example fragments: See lefant-claude-code-plugins/lefant/skills/changelog-fragments/examples/ for:
feature-example.md - Feature implementation with database trackingfix-example.md - Bug fix with environment variable mismatchchore-example.md - Simple maintenance taskWhen using /devlog for shared implementations:
thoughts/shared/devlog/YYYY-MM-DD_implementation.mdCHANGELOG/YYYY-MM-DD_implementation.mdrelated_devlog field in fragment frontmatterExample workflow:
# After implementing a feature and creating devlog
# thoughts/shared/devlog/2025-11-20_oauth-token-refresh.md
# Create corresponding fragment
# CHANGELOG/2025-11-20_oauth-token-refresh.md
---
date: 2025-11-20
type: feature
related_devlog: thoughts/shared/devlog/2025-11-20_oauth-token-refresh.md
---
Implemented automatic OAuth token refresh for expired Notion connections. Users no longer need to manually reconnect when tokens expire.
When creating a fragment:
YYYY-MM-DDrelated_devlog field)CHANGELOG/ directoryThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.