agentleFS
ShiningPlagueShiningPlague/shiningplague-studio/skills/project-stage-detect/SKILL.md

project-stage-detect

Skill0 starsChanged 4 months agoMITView on GitHub

Use when checking what development phase the project is in, what artifacts exist vs are missing, or when the designer asks 'where are we?' Reads production/stage.txt, scans artifact globs from workflow-catalog.yaml, and reports phase + gaps. ShiningPlague-adopted: per-phase project artifact checks, workstream phase map, gap summary with priority gap surfacing.

15 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use soak-test, team-live-ops and 2 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.
  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

  • +2 more from lilangMax

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 0

    Distinctive

    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:

    Read production/stage.txt.

    line 35
  2. Very specific:

    Read .claude/docs/workflow-catalog.yaml.

    line 47
  3. Very specific:

    Read production/workstreams/*.md for per-workstream phase positions.

    line 74

“Common” is measured: kept by at least 6 in 10 of the 14 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

Project Stage Detect

🌱 ShiningPlague-adopted. Originally Donchitos (barebones stub); battle-tested on a shipped Godot project. Upstream was a pointer-only file; the studio version is the full implementation — per-phase artifact checks, workstream phase map, gap summary.

Auto-detect current development phase and report gap analysis.

If an artifact named here is absent: say so plainly in one line, skip that step, and continue. Never invent the file to satisfy a checklist, and never fail a close because an optional artifact was never created.

Procedure

Existence is not evidence. The installer seeds the whole document stack, so every artifact this skill globs already exists on a virgin project. A file still carrying the scaffold-seed: unwritten marker near the top is a blank seed and counts as absent everywhere below. The mechanical version of this whole procedure is python tools/workflow_state_check.py, which already applies the rule — prefer running it over re-deriving it by hand. Contract: .claude/docs/doc-stack.md § Seeded is not written.

1. Read Authoritative Phase

Read production/stage.txt. Map to workflow-catalog phase key:

  • "not-started" → the seeded default, not a phase. No gate has been cleared — report the project as pre-concept and infer readiness from artifacts below.
  • "Concept" → concept
  • "Systems Design" → systems-design
  • "Technical Setup" → technical-setup
  • "Pre-Production" → pre-production
  • "Production" → production
  • "Polish" → polish
  • "Release" → release

2. Read Workflow Catalog

Read .claude/docs/workflow-catalog.yaml. For each phase up to and including current, check each step's artifact.glob — and where the step declares one, its artifact.pattern too. A match only counts if the file is non-empty and no longer carries the scaffold-seed marker.

3. Check Per-Phase Artifacts

Concept phase:

  • Game concept doc: docs/gdd/game-concept.md or {{GDD_PATH}}
  • Game pillars: docs/gdd/game-pillars.md
  • Art bible: check for art-bible artifact

Systems Design phase:

  • Systems index: docs/gdd/systems-index.md
  • Per-system GDDs: docs/gdd/*.md
  • Cross-GDD review: review-all-gdds artifact

Technical Setup phase:

  • ADRs: docs/adr/[0-9]*.md
  • Master architecture: docs/architecture/architecture.md
  • Control manifest: docs/architecture/control-manifest.md
  • Engine reference: docs/engine-reference/

Production phase:

  • Source files: src/
  • Sprint status: production/sprint-status.yaml

Report each as EXISTS / MISSING / partial from the live scan — never from cached claims.

4. Check Workstream States

Read production/workstreams/*.md for per-workstream phase positions. Report which workstreams are ahead/behind the declared project phase.

5. Output Report

## Project Phase: [phase]

### Phase Artifacts
✓ [artifact] — exists
✗ [artifact] — MISSING (required for [phase])
~ [artifact] — partial (exists but incomplete)

### Workstream Phase Map
- Combat: Production
- Narrative: Concept
- Game Design: Production (gaps in Concept/Systems Design)

### Gaps Summary
[N] missing required artifacts across [phases]
Priority gap: [highest-impact missing item]

### Recommendation
[what to do next to close the most important gap]

Project Paths

  • Stage: production/stage.txt
  • Catalog: .claude/docs/workflow-catalog.yaml
  • Workstreams: production/workstreams/*.md
  • Registry: data/_schemas/system_registry.json

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.