agentleFS
bladecoderbladecoder/narrative-skills/skills/if/if-playtest-review/SKILL.md

if-playtest-review

Skill0 starsChanged 7 months agoMITView on GitHub

Review an Ink interactive fiction project or slice for playability, route coverage, dead ends, impossible locks, repeated-choice behavior, pacing, and state consistency.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill after Ink source exists.

    line 10
  2. Very specific:

    If an Ink compiler such as inklecate is available, run it only as a verification step.

    line 60
  3. Very specific:

    Write review notes in story.language.

    line 64
  4. Distinctive:

    Write concrete fixes, naming files and knots when possible.

    line 72
  5. Distinctive:

    Do not rewrite Ink source here unless explicitly asked.

    line 77
  6. Distinctive:

    Do not treat every optional missed line as a blocking playability defect.

    line 78
  7. Distinctive:

    Do not ignore soft locks caused by dialogue order.

    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 Playtest Review

Overview

Use this skill after Ink source exists. It evaluates whether the player can navigate, converse, unlock progress, revisit content, and complete the intended path without contradictions or impossible state dependencies.

Files To Read

Always read:

  • story.yaml
  • 04_design/state_model.md
  • 04_design/progression.yaml
  • 05_ink/main.ink

Read when relevant:

  • target slice plan under 04_design/slices/
  • relevant 05_ink/locations/*
  • relevant 05_ink/dialogues/*
  • relevant 05_ink/systems/*
  • 04_design/map.md
  • 04_design/locations.yaml
  • 04_design/dialogue_matrix.md
  • 04_design/critical_path.md
  • existing 06_playtest/*

Files To Write

Write or update:

  • 06_playtest/route_matrix.md
  • 06_playtest/playability.review.md

Optionally add slice-specific review notes under 06_playtest/ if the project already uses that convention.

Review Dimensions

Check:

  • start-to-completion route;
  • location reachability;
  • character availability;
  • critical clue availability;
  • inventory, knowledge, skill, and relationship gates;
  • circular dependencies;
  • repeated choices and revisits;
  • accidental one-way exits;
  • unavailable endings or premature endings;
  • state names used in Ink but absent from the model;
  • state names in the model but unused in Ink.

Optional Compile Check

If an Ink compiler such as inklecate is available, run it only as a verification step. If it is unavailable, state that syntax was reviewed statically.

Language Rules

Write review notes in story.language. Keep filenames and structured keys in English.

Procedure

  1. Identify the scope: whole project or specific slice.
  2. Build a route matrix covering critical path and likely optional orders.
  3. Compare required states in progression design against states granted in Ink.
  4. Classify findings as blocking, major, minor, or polish.
  5. Write concrete fixes, naming files and knots when possible.
  6. Recommend if-draft-ink, if-design-progression, or if-sync-state depending on the result.

Restrictions

  • Do not rewrite Ink source here unless explicitly asked.
  • Do not treat every optional missed line as a blocking playability defect.
  • Do not ignore soft locks caused by dialogue order.

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.