agentleFS
simonstrumsesimonstrumse/vibelabs-skills/skills/changelog/SKILL.md

changelog

Skill0 starsChanged 9 months agoMITView on GitHub

Read or update project changelog. Use PROACTIVELY whenever you need context about what was done previously in ANY area of the codebase, and after making changes or decisions worth preserving. This is your strategic memory - use it liberally to avoid redoing work or missing context.

160 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use playtest-report, soak-test and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 12 projects that use this

  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

  • CoralGameSkill

    team-polish

    Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.

    Also in 14 projects that use this

  • +5 more from lilangMax
  • +3 more from CoralGame

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 149 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Update the Current State section: if capabilities changed:

    line 43
  2. Distinctive:

    Add/check items in "What's Working"

    line 45
  3. Distinctive:

    Update "What's Next" priorities

    line 46
  4. Very specific:

    Read the sessions-index.json file in that folder.

    line 82
  5. Distinctive:

    After historical entries, add a Current State section based on:

    line 120
  6. Distinctive:

    NEVER invent context: If you don't know WHY something was done, say "Context unknown"

    line 139
  7. Distinctive:

    Mark uncertainty: Use "inferred", "from session log", "context unknown" labels

    line 141
  8. Distinctive:

    Invite corrections: Add note asking user to fill in missing context

    line 142
  9. Distinctive:

    Before making changes that might conflict with recent decisions

    line 153

“Common” is measured: kept by at least 6 in 10 of the 149 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Changelog Management Skill

You have been invoked to manage the project changelog. This is a strategic memory system, not a tool log.

Your Tasks

If Reading (gathering context):

  1. Identify the relevant changelog:
    • Project root → ./CHANGELOG.md
    • Monorepo apps → apps/<app-name>/CHANGELOG.md
    • Sub-packages → packages/<pkg-name>/CHANGELOG.md
  2. Read the Current State section (top of file) for quick orientation
  3. Search recent History entries for:
    • The specific area/files being modified
    • Related decisions or patterns
    • Known gotchas or technical notes
  4. Report back with relevant context that should inform the current work

If Writing (documenting changes):

  1. Determine what happened this session:
    • Code changes made
    • Decisions reached
    • Direction shifts discussed
    • Insights generated
    • Technical gotchas discovered
  2. Update the Current State section if capabilities changed:
    • Update progress indicators
    • Add/check items in "What's Working"
    • Update "What's Next" priorities
  3. Add a History entry with:
    ## [DATE] - [BRIEF SESSION SUMMARY]
    
    ### Direction & Vision
    - [Strategic shifts, even without code]
    
    ### Changes
    - **[Description]** — `[files]` ([context])
    
    ### Insights
    - [★ Insight blocks or learnings]
    
    ### Technical Notes
    - [Platform quirks, decisions]
    
    ### Pending
    - [ ] [Incomplete items]
  4. Be specific, not vague:
    • ❌ "Fixed auth bug"
    • ✅ "Fixed middleware setting response headers instead of request headers — server components read request headers"

Bootstrap Mode (First-Time Setup)

If no CHANGELOG.md exists, bootstrap from session history:

Step 1: Find the sessions index

The project path determines the sessions folder. Convert the project path to the folder name:

  • /path/to/your/project
  • becomes: ~/.claude/projects/-path-to-your-project/

Read the sessions-index.json file in that folder.

Step 2: Extract session summaries

The index contains entries like:

{
  "sessionId": "abc123",
  "summary": "Human-readable session summary",
  "firstPrompt": "What user first asked",
  "created": "2026-01-14T20:59:20.530Z",
  "gitBranch": "feat/some-feature",
  "messageCount": 10
}

CRITICAL: Only use the summary field - these are factual, already generated. DO NOT invent, deduce, or hallucinate additional details.

Step 3: Create changelog from summaries

Group sessions by date and create entries:

## Historical Sessions (from Claude Code session logs)

> Note: These entries are auto-generated from session summaries.
> Context may be incomplete. Add details if you remember more.

### 2026-01-14
- **Vibelabs Bento Grid Hero & Site Revert** (branch: `feat/homepage-redesign-2026`, 7 messages)
- **Human-Centric Vibelabs One-Pager** (branch: `main`, 10 messages)

### 2026-01-05
- **Per-app volume mixer macOS app research** (branch: `main`, 7 messages)

Step 4: Add Current State section

After historical entries, add a Current State section based on:

  • Git status (git log --oneline -10)
  • README content
  • Visible project structure

Mark inferred information clearly:

## Current State

> **Last Updated:** [DATE]
> **Status:** *Inferred from codebase - please verify*

### What's Working (inferred from code)
- [x] Item visible in codebase

Bootstrap Rules

  1. ONLY use factual sources: session summaries, git log, existing docs
  2. NEVER invent context: If you don't know WHY something was done, say "Context unknown"
  3. NEVER hallucinate details: Session summary says "Fixed auth bug" → write exactly that, don't elaborate
  4. Mark uncertainty: Use "inferred", "from session log", "context unknown" labels
  5. Invite corrections: Add note asking user to fill in missing context

Context Triggers

Automatically consider reading the changelog when:

  • About to modify ANY code you haven't touched recently in this session
  • Wondering "what was the approach here?" or "why is this done this way?"
  • User asks about previous work ("what did we do with X?", "where were we?")
  • Starting a new session or after context compaction
  • Before making changes that might conflict with recent decisions
  • Unsure if something was already implemented or fixed

Automatically consider writing when:

  • ANY code changes were made (features, fixes, refactoring)
  • Decisions were reached about how to do something
  • User expressed preferences, changed direction, or clarified vision
  • ★ Insight blocks were generated
  • Something non-obvious was discovered (gotchas, patterns, behaviors)
  • Leaving work incomplete (document what's pending)
  • A conversation led to strategic clarity (even without code changes)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.