agentleFS
lightly-ailightly-ai/lightly-studio/.agents/skills/changelog/SKILL.md

changelog

Skill911 starsChanged 3 days agoApache-2.0View on GitHub

Read before adding or editing an entry in CHANGELOG.md or lightly_studio_serve/CHANGELOG.md. Says what an entry contains, how long it is, and which prefixes to use.

165 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 13 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 10 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 10 projects that use this

  • CoralGameSkill

    team-audio

    Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.

    Also in 13 projects that use this

  • +6 more from lilangMax
  • +2 more from CoralGame

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 154 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use one or two short sentences.

    line 14
  2. Distinctive:

    Do not describe how the code works: no internal functions, precedence rules, retries, or database tables.

    line 15
  3. Very specific:

    Start a change to the Python SDK with Python SDK:.

    line 17
  4. Very specific:

    Start a change that breaks existing code or data with BREAKING:.

    line 18
  5. Very specific:

    Do not add ticket ids (LIG-1234) or PR numbers.

    line 20
  6. Very specific:

    Put the entry under the correct heading of ## [Unreleased]: Added, Changed, Deprecated, Removed, Fixed, or Security.

    line 21

“Common” is measured: kept by at least 6 in 10 of the 154 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 Entries

The changelog becomes the release notes. Write each entry for a person who uses LightlyStudio, not for a person who reviews the code.

Rules

  • Say what the user can now do, or what changed for them. One change per entry.
  • Use one or two short sentences.
  • Do not describe how the code works: no internal functions, precedence rules, retries, or database tables. Name a public API only when users call or implement it.
  • Start a change to the Python SDK with Python SDK:.
  • Start a change that breaks existing code or data with BREAKING:. Add the one step that users must do.
  • Do not add ticket ids (LIG-1234) or PR numbers.
  • Put the entry under the correct heading of ## [Unreleased]: Added, Changed, Deprecated, Removed, Fixed, or Security.

Example

Bad:

Python SDK: New annotation crops and video frames are embedded in the embedding space of their parent collection, also in a later process with no registered embedder. A registered embedder for crops or frames still takes priority. If no embedder is available for the parent's space, embedding is skipped with a warning and a later run retries.

Good:

Python SDK: Crops and frames get embedded with a remote embedder automatically when a compatible remote embedder was used previously.

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.