agentleFS
WhorideChickenWhorideChicken/first-playable/skills/feature/SKILL.md

feature

Skill3 starsChanged 32 days agoMITView on GitHub

Spec-first feature development for Unity — writes a Feature Spec referencing game rule IDs, gets approval, then implements pure logic, tests, and Unity integration in that order. Use when the user says /first-playable:feature <name>.

71 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use bug, bugfix and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • paulocsbSkill

    bug

    Investigation playbook for fixing a bug. Walks through 5 phases: reproduce → isolate → root cause → propose fix → validate. Forces concrete reasoning with code reads, log inspection, and git blame instead of pattern-matching guesses. Use for any non-trivial defect.

    Also in 8 projects that use this

  • team-attentionSkill

    bugfix

    Root cause based one-shot bug fix. debugger diagnosis → requirements.md generation → /execute. /bugfix "error description" Full investigation pipeline: debugger + gap-analyzer + standard verify. QA suggestion after successful fix.

    Also in 7 projects that use this

  • Google CloudSkill

    fix

    Plan a remediation strategy after a test failure.

    Also in 10 projects that use this

  • marylinSkill

    recover

    Recover work from a crashed or interrupted session. Use when Claude crashed mid-task, after an unexpected exit, when you see 'stale sessions detected', or when you lost context and need to figure out what was happening.

    Also in 3 projects that use this

  • aegiswizardSkill

    context

    Also in 4 projects that use this

  • AWSSkill

    map

    Map verified service capabilities against customer-provided control framework and threat model. Produces mapping-results.json, controls-catalog.md, and framework-mapping.md. Supports pluggable frameworks: CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001, etc. Split into 4 focused sub-skills for better accuracy; this skill orchestrates them.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 65 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Only implement what the approved spec includes.

    line 26
  2. Very specific:

    Every scene-wiring Editor script must ship with a Verify() that re-reads what it just assigned and logs the result.

    line 72
  3. Very specific:

    Read references/unity-testing.md in this plugin before implementing — it covers the humble-object split (pure logic in Game.Core, thin …

    line 78
  4. Distinctive:

    Follow the asmdef boundaries set up by bootstrap.

    line 82

“Common” is measured: kept by at least 6 in 10 of the 65 edited versions of this file we could read. “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

Feature Spec & Implementation

You are running Phase 5 of the FirstPlayable workflow. Never implement a feature without an approved spec. The spec — not the conversation — defines what "done" means.

Order of work

read design docs (Docs/Game, Docs/Design)
→ survey related code and packages already in the project
→ write the Feature Spec (Draft)
→ user approves the spec
→ implement pure C# logic (no UnityEngine dependencies where possible)
→ EditMode tests for the pure logic
→ Unity integration (MonoBehaviours, scenes, prefabs via MCP/Editor API)
→ PlayMode tests
→ hand off to /first-playable:verify

Only implement what the approved spec includes. If mid-implementation you discover the spec is wrong, stop, update the spec, and get re-approval — do not quietly diverge.

Feature Spec

Location: Docs/Features/<FEATURE_NAME>.md (template: templates/features/FEATURE_SPEC.md).

# Feature: Player Movement

## Status
Draft | Approved | Implementing | Verified

## Purpose
## Player's perspective
## Referenced rules
- MOVE-001          # every behavior must trace to a GAME_RULES.md ID

## In scope
## Out of scope
## Behavior rules
## Initial tuning values
| Item | Value | Status |
|---|---:|---|
| Move speed | 5 | TEMPORARY |

## Done conditions
## EditMode tests
## PlayMode tests
## Manual play checks     # things only a human can judge (feel, readability)
## Open questions

Scene wiring order (recompilation drops inspector references)

Assigning inspector references and then editing scripts loses those assignments: the domain reload can null out serialized fields, and the scene looks wired while the game does nothing. Always:

edit scripts  →  confirm compile finished  →  wire the scene  →  save
              →  read the references back and log them

Every scene-wiring Editor script must ship with a Verify() that re-reads what it just assigned and logs the result. Cheap to write, and it catches both this failure and typo'd lookups immediately.

Implementation rules

  • Read references/unity-testing.md in this plugin before implementing — it covers the humble-object split (pure logic in Game.Core, thin MonoBehaviour adapters), EditMode/PlayMode test patterns, common PlayMode pitfalls, and what NOT to test.
  • Follow the asmdef boundaries set up by bootstrap; check them before adding code.
  • Tuning values marked TEMPORARY go in serialized fields or configs — never scattered magic numbers.
  • Include the referenced rule ID in test names or descriptions (e.g. Move001_KnockbackSuppressesInput).
  • Scene/Prefab changes go through Unity MCP or Editor API only.

Default feature order (from DEVELOPMENT_ORDER.md)

input → movement → camera → core action → interaction targets → win/lose → restart

One feature per invocation. Finish and verify before starting the next.

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.