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.
In this repository27 other files it gives its agents.
- beta-reader-passSkill
- build-distributionSkill
- chapter-reviewSkill
- continuity-checkSkill
- create-character-bibleSkill
- define-style-bibleSkill
- draft-chapterSkill
- generate-high-level-outlineSkill
- if-design-dialogueSkill
- if-design-mapSkill
- if-design-structureSkill
- if-draft-inkSkill
- if-init-projectSkill
- if-load-contextSkill
- if-plan-ink-sliceSkill
- if-playtest-reviewSkill
- if-sync-stateSkill
- ink-docSkill
- init-story-projectSkill
- load-story-contextSkill
- manuscript-reviewSkill
- plan-chapterSkill
- prepare-exportSkill
- rewrite-chapterSkill
- sync-story-bibleSkill
- update-character-stateSkill
- update-timelineSkill
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
- Distinctive: line 10
Use this skill to make the game progression playable.
- Distinctive: line 39
Use stable IDs and structured records.
- Very specific: line 54
Keep IDs, filenames, and YAML keys in English.
- Distinctive: line 60
Verify that critical path progress can be achieved through at least one understandable route.
- Distinctive: line 61
Add alternate routes for critical knowledge when the design calls for open exploration.
- Distinctive: line 63
Update the state model with the minimum variables needed for Ink implementation.
- Distinctive: line 77
Do not write Ink source here.
- Distinctive: line 78
Do not leave dependencies only in prose.
- Distinctive: line 79
Do not create a required clue or item with no obtainable source.
≈ “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.
Files
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.yaml04_design/story_beats.md04_design/critical_path.md04_design/state_model.md04_design/locations.yaml04_design/dialogue_matrix.md
Read when relevant:
03_characters/*04_design/progression.yaml07_continuity/*
Files To Write
Write or update:
04_design/progression.yaml04_design/critical_path.md04_design/state_model.md
Progression Model
Use stable IDs and structured records. Each obstacle should capture:
id;typesuch asknowledge,inventory,skill,relationship,location, orworld_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
- Extract all implied blockers from map, dialogue, and critical path files.
- Convert each blocker into explicit requirements and grants.
- Verify that critical path progress can be achieved through at least one understandable route.
- Add alternate routes for critical knowledge when the design calls for open exploration.
- Identify soft locks, circular dependencies, and unlocks that do not change play.
- 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.
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
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.

