agentleFS
bladecoderbladecoder/narrative-skills/skills/if/if-plan-ink-slice/SKILL.md

if-plan-ink-slice

Skill0 starsChanged 7 months agoMITView on GitHub

Plan a single implementable Ink slice, such as one location, character dialogue, obstacle, system, or progression beat, before writing or revising Ink source files.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill to prepare one bounded unit of Ink implementation.

    line 10
  2. Distinctive:

    Read according to slice type:

    line 32
  3. Distinctive:

    Write or update one plan file under:

    line 44
  4. Very specific:

    Use English filenames and stable snake_case slice IDs.

    line 50
  5. Very specific:

    Write project content in story.language.

    line 68
  6. Distinctive:

    Read only the Ink and design files needed for this slice.

    line 73
  7. Distinctive:

    Do not write Ink source here.

    line 81
  8. Distinctive:

    Do not plan multiple unrelated slices in one file.

    line 82
  9. Distinctive:

    Do not introduce new state without adding it to the plan and state model.

    line 83

≈ “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 Plan Ink Slice

Overview

Use this skill to prepare one bounded unit of Ink implementation. The slice plan should be specific enough that if-draft-ink can write code without re-solving map, dialogue, or progression design.

Slice Types

Supported slice types:

  • location;
  • dialogue;
  • obstacle;
  • navigation system;
  • inventory, knowledge, or skill system;
  • phase transition;
  • ending or major branch.

Files To Read

Always read:

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

Read according to slice type:

  • 04_design/map.md
  • 04_design/locations.yaml
  • 04_design/dialogue_matrix.md
  • 04_design/story_beats.md
  • 04_design/critical_path.md
  • relevant 05_ink/*
  • ink-doc references only when Ink syntax decisions are needed.

Files To Write

Write or update one plan file under:

04_design/slices/<slice_id>.plan.md

Use English filenames and stable snake_case slice IDs.

Plan Requirements

Each slice plan must define:

  • slice ID and type;
  • source design records involved;
  • Ink files expected to change;
  • entry and exit knots or stitches;
  • state variables read and written;
  • choices shown to the player;
  • repeat behavior on revisit;
  • required includes or tunnels;
  • acceptance criteria.

Language Rules

Write project content in story.language. Keep filenames, IDs, and Ink identifiers in English unless the project already uses another stable convention.

Procedure

  1. Locate the target design item and confirm its role.
  2. Read only the Ink and design files needed for this slice.
  3. Define the player-facing interaction and state transitions.
  4. Decide how the slice reconnects to navigation or dialogue loops.
  5. Record implementation constraints and acceptance checks.
  6. Recommend if-draft-ink.

Restrictions

  • Do not write Ink source here.
  • Do not plan multiple unrelated slices in one file.
  • Do not introduce new state without adding it to the plan and state model.

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.