agentleFS
bladecoderbladecoder/narrative-skills/skills/if/if-design-progression/SKILL.md

if-design-progression

Skill0 starsChanged 7 months agoMITView on GitHub

Model obstacles, locks, keys, knowledge, inventory, protagonist skills, and unlock conditions for an Ink interactive fiction project.

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 to make the game progression playable.

    line 10
  2. Distinctive:

    Use stable IDs and structured records.

    line 39
  3. Very specific:

    Keep IDs, filenames, and YAML keys in English.

    line 54
  4. Distinctive:

    Verify that critical path progress can be achieved through at least one understandable route.

    line 60
  5. Distinctive:

    Add alternate routes for critical knowledge when the design calls for open exploration.

    line 61
  6. Distinctive:

    Update the state model with the minimum variables needed for Ink implementation.

    line 63
  7. Distinctive:

    Do not write Ink source here.

    line 77
  8. Distinctive:

    Do not leave dependencies only in prose.

    line 78
  9. Distinctive:

    Do not create a required clue or item with no obtainable source.

    line 79

≈ “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 Design Progression

Overview

Use this skill to make the game progression playable. It turns map and dialogue ideas into explicit obstacles, requirements, grants, and completion paths so the player can explore freely without impossible locks or accidental linearity.

Files To Read

Always read:

  • story.yaml
  • 04_design/story_beats.md
  • 04_design/critical_path.md
  • 04_design/state_model.md
  • 04_design/locations.yaml
  • 04_design/dialogue_matrix.md

Read when relevant:

  • 03_characters/*
  • 04_design/progression.yaml
  • 07_continuity/*

Files To Write

Write or update:

  • 04_design/progression.yaml
  • 04_design/critical_path.md
  • 04_design/state_model.md

Progression Model

Use stable IDs and structured records. Each obstacle should capture:

  • id;
  • type such as knowledge, inventory, skill, relationship, location, or world_state;
  • description;
  • requires;
  • grants;
  • location_scope;
  • character_scope;
  • critical_path;
  • fallback_route;
  • status.

Language Rules

Keep IDs, filenames, and YAML keys in English. Write human-readable values in story.language.

Procedure

  1. Extract all implied blockers from map, dialogue, and critical path files.
  2. Convert each blocker into explicit requirements and grants.
  3. Verify that critical path progress can be achieved through at least one understandable route.
  4. Add alternate routes for critical knowledge when the design calls for open exploration.
  5. Identify soft locks, circular dependencies, and unlocks that do not change play.
  6. Update the state model with the minimum variables needed for Ink implementation.

Output

Provide:

  • progression summary;
  • critical path requirements;
  • optional unlocks;
  • detected dependency risks;
  • recommended next step, usually if-plan-ink-slice.

Restrictions

  • Do not write Ink source here.
  • Do not leave dependencies only in prose.
  • Do not create a required clue or item with no obtainable source.

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.