agentleFS
Sign inStart free
bladecoderbladecoder/narrative-skills/skills/if/if-sync-state/SKILL.md

if-sync-state

Skill0 starsChanged 7 months agoMITView on GitHub

Synchronize accepted Ink interactive fiction changes back into design, progression, continuity, playtest records, and workflow metadata.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    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:

    Use this skill after Ink implementation or review changes have stabilized.

    line 10
  2. Distinctive:

    Keep uncertain facts marked provisional.

    line 48
  3. Distinctive:

    Do not promote draft-only text into canon unless it is accepted or stable.

    line 49
  4. Very specific:

    Use English keys and filenames.

    line 54
  5. Distinctive:

    Update structured design files additively where possible.

    line 60
  6. Distinctive:

    Update continuity records only when evidence is stable.

    line 61
  7. Distinctive:

    Do not rewrite playable Ink here.

    line 76
  8. Distinctive:

    Do not erase useful design history without clear replacement.

    line 77
  9. Distinctive:

    Do not mark unresolved playtest findings as solved unless the files prove it.

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

IF Sync State

Overview

Use this skill after Ink implementation or review changes have stabilized. It updates design and continuity records so later IF work does not rely on stale plans or chat memory.

Files To Read

Always read:

  • story.yaml
  • changed or target 05_ink/* files;
  • relevant 04_design/* files.

Read when relevant:

  • 06_playtest/route_matrix.md
  • 06_playtest/playability.review.md
  • 07_continuity/*
  • 03_characters/*

Files To Write

Update as justified:

  • story.yaml
  • 04_design/map.md
  • 04_design/locations.yaml
  • 04_design/dialogue_matrix.md
  • 04_design/progression.yaml
  • 04_design/state_model.md
  • 04_design/critical_path.md
  • 06_playtest/route_matrix.md
  • 07_continuity/canon_facts.yaml
  • 07_continuity/entities.yaml
  • 07_continuity/locations.yaml
  • 07_continuity/unresolved_threads.yaml

Sync Rules

  • Preserve confirmed design facts unless Ink clearly supersedes them.
  • Record implementation reality when it differs from old plans.
  • Keep uncertain facts marked provisional.
  • Do not promote draft-only text into canon unless it is accepted or stable.
  • Keep workflow.next_skill actionable.

Language Rules

Use English keys and filenames. Write human-readable values in story.language.

Procedure

  1. Identify the accepted Ink or review changes in scope.
  2. Extract new or changed facts about locations, characters, obstacles, state, and progression.
  3. Update structured design files additively where possible.
  4. Update continuity records only when evidence is stable.
  5. Refresh workflow metadata and recommend the next IF skill.

Output

Provide:

  • files synchronized;
  • new or changed progression/state facts;
  • continuity updates;
  • remaining discrepancies;
  • recommended next step.

Restrictions

  • Do not rewrite playable Ink here.
  • Do not erase useful design history without clear replacement.
  • Do not mark unresolved playtest findings as solved unless the files prove it.

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.

Check your setup, free