Agent skill

agent-changelog

Compile an agent-optimized changelog by cross-referencing git history with plans and documentation. Use when asked to "update changelog", "compile history", "document project evolution", or proactively after major milestones, architectural changes, or when stale/deprecated information is detected that could confuse coding agents.

Stars 20
Forks 6

Install this agent skill to your Project

npx add-skill https://github.com/petekp/claude-code-setup/tree/main/skills/agent-changelog

SKILL.md

Agent Changelog

Compile a chronological record of key decisions, architectural changes, and project evolution optimized for coding agent context-building.

Output

Write to AGENT_CHANGELOG.md in the project root. This file helps agents:

  • Understand key decisions and their rationale
  • Identify deprecated patterns/approaches to avoid
  • Grasp the trajectory from past to present to likely future
  • Detect stale documentation that contradicts current reality

Workflow

1. Gather Sources

Collect information from these sources in parallel:

Git history:

bash
git log --oneline --since="6 months ago" | head -100
git log --all --oneline --grep="BREAKING" --grep="deprecate" --grep="remove" --grep="migrate" -i
git tag -l --sort=-creatordate | head -20

Documentation:

  • .claude/plans/ - implementation plans and decisions
  • CLAUDE.md - project instructions
  • README.md - project overview
  • docs/ or similar documentation directories
  • CHANGELOG.md if exists (traditional changelog)

Code signals:

  • @deprecated annotations
  • TODO, FIXME, HACK comments with dates
  • Migration files, upgrade scripts

2. Identify Key Events

Extract events that matter for agent understanding:

Always include:

  • Architectural decisions (new patterns, removed patterns)
  • Breaking changes and migrations
  • Deprecated features/approaches
  • Major dependency changes
  • Directory structure changes
  • API changes (internal or external)

Include if significant:

  • New features that change how agents should work
  • Bug fixes that reveal incorrect assumptions
  • Performance changes that affect approach recommendations

Skip:

  • Minor bug fixes
  • Cosmetic changes
  • Routine dependency updates
  • Individual feature additions (unless architectural)

3. Cross-Reference for Contradictions

For each significant event, check if existing documentation contradicts it:

Event: "Migrated from Redux to Zustand" (commit abc123, 2024-03)

Check: Does any documentation still reference Redux patterns?
- README.md mentions Redux? → Flag as STALE
- CLAUDE.md suggests Redux approach? → Flag as STALE
- Old tutorials in docs/? → Flag as STALE

Track contradictions in a "Stale Information Detected" section.

4. Write the Changelog

Structure the output file:

markdown
# Agent Changelog

> This file helps coding agents understand project evolution, key decisions,
> and deprecated patterns. Updated: [DATE]

## Current State Summary

[2-3 sentences on where the project is NOW - the authoritative current architecture]

## Stale Information Detected

[List any documentation that contradicts current reality - agents should ignore these until fixed]

| Location | States | Reality | Since |
|----------|--------|---------|-------|
| docs/auth.md | "Uses JWT tokens" | Migrated to sessions | 2024-06 |

## Timeline

### [YEAR-MONTH] - [Brief Title]

**What changed:** [Factual description]

**Why:** [Decision rationale if known from plans/commits]

**Agent impact:** [How this affects how agents should work in the codebase]

**Deprecated:** [What approaches/patterns should agents avoid]

---

[Repeat for each significant event, reverse chronological]

## Deprecated Patterns

[Consolidated list of things agents should NOT do, with what to do instead]

| Don't | Do Instead | Deprecated Since |
|-------|------------|------------------|
| Use `OldService` | Use `NewService` | 2024-08 |

## Trajectory

[Brief note on where the project appears to be heading based on recent changes and plans]

5. Validate and Update

After writing:

  • Read existing AGENT_CHANGELOG.md if present and merge, don't duplicate
  • Verify dates against git history
  • Ensure "Stale Information Detected" section is actionable

When to Proactively Run

Suggest running this skill when:

  • A major refactor or migration just completed
  • Plans in .claude/plans/ were recently executed
  • Multiple architectural decisions happened in quick succession
  • Detected documentation that seems to contradict code reality
  • Starting work on a codebase after a long gap
  • Onboarding to an unfamiliar codebase

Guidelines

  • Prioritize accuracy over completeness—wrong history is worse than incomplete
  • Include rationale when available (commit messages, plan docs)
  • Be specific about what agents should avoid, not just what changed
  • Keep entries concise—this is reference material, not storytelling
  • Date everything to help agents judge relevance

Expand your agent's capabilities with these related and highly-rated skills.

petekp/claude-code-setup

ubiquitous-language

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

20 6
Explore
petekp/claude-code-setup

every-style-editor

This skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provides a systematic line-by-line review process for grammar, punctuation, mechanics, and style guide compliance.

20 6
Explore
petekp/claude-code-setup

manage-codex

Autonomous Codex batch orchestrator. Use for "/manage-codex", "manage codex", "use codex", "dispatch to codex", or long-running Codex work.

20 6
Explore
petekp/claude-code-setup

seo-audit

When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup. For AI search optimization, see ai-seo.

20 6
Explore
petekp/claude-code-setup

capture-learning

Analyze recent conversation context and capture learnings to project knowledge files (for project-specific insights) or skills/commands/subagents (for cross-project patterns). Use when the user asks to "capture this learning", "update the docs with this", "remember this for next time", "document this issue", "add this to CLAUDE.md", "save this knowledge", or "update project knowledge". Also triggers after resolving build/setup issues, discovering non-obvious patterns, or completing debugging sessions with valuable insights.

20 6
Explore
petekp/claude-code-setup

swift-apps

Build, refactor, review, and debug native Apple-platform software in Swift. Use when working on `.swift` files, SwiftUI views, Observation-based state, `@Bindable` and binding flow, SwiftData-backed UI, scenes and windows, search/navigation structures, UIKit/AppKit interop, Liquid Glass adoption, macOS-native UX, or SwiftUI performance/accessibility. Trigger on requests to create or polish iOS, iPadOS, macOS, or visionOS features; clean up SwiftUI view structure; diagnose jank or invalidation storms; review app quality; or make a feature feel like a good Apple-platform citizen.

20 6
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results