plan-audit
Skill0 starsChanged 9 months agoMITView on GitHub
Game-specific plan quality auditing. Use when auditing game project plans, checking game plan completeness, evaluating game MLP scope, reviewing GDD quality, assessing economy design, difficulty curves, playtest readiness, or running plan-audit on a game project. Covers core loop validation, scope complexity scoring, design document quality, economy red flags, difficulty assessment.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- anthony-chaudhary/faktheir own version, first seen Nov 3, 2026
- xiaolai/vmarktheir own version, first seen Oct 8, 2026
- weg-9000/Orange-pmtheir own version, first seen Jul 11, 2026
- Avalon-27reg/claude-skill-plan-audittheir own version, first seen Jun 14, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- xiaolai/vmark★ 908same name
- anthony-chaudhary/fak★ 47same name
- Avalon-27reg/claude-skill-plan-audit★ 0same name
- weg-9000/Orange-pm★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- antipatternsSkill
- architecture-auditSkill
- ascii-wireframingSkill
- content-planningSkill
- design-frameworksSkill
- difficulty-designSkill
- economy-designSkill
- implementationSkill
- mechanics-paletteSkill
- playtestingSkill
- scenario-walkthroughSkill
- scopingSkill
- simulation-guideSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 88
All five "Yes" → READY TO BUILD.
- Distinctive: line 108
Start at Tier 0 (observation + notes).
“Common” is measured: kept by at least 6 in 10 of the 3 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.
Files
Game Plan Audit
Audit game plans for completeness, scope realism, and design quality. Catches game-specific gaps that generic plan audits miss.
Quick Reference
Game Plan Completeness Scorecard
| # | Check | Severity | Cross-Reference |
| 1 | Core loop defined in one sentence | Critical | (see scoping → Core Loop Identification) |
| 2 | Target aesthetics identified (1-2 from MDA) | Critical | (see design-frameworks → MDA Framework) |
| 3 | MLP has ≤3 features beyond core loop | Warning | (see scoping → The 3-Feature Rule) |
| 4 | Tracer bullet defined | Warning | (see scoping) |
| 5 | Economy complexity decided | Warning | (see economy-design) |
| 6 | Difficulty approach selected | Info | (see difficulty-design → Difficulty Curve Patterns) |
| 7 | Scenario walkthrough written | Info | (see scenario-walkthrough → The 5-Beat Structure) |
| 8 | Playtest plan exists (who, when, what) | Warning | (see playtesting → Playtest Planning Checklist) |
| 9 | Over-scope score ≤2 | Warning | (see antipatterns → Is My Plan Over-Scoped?) |
| 10 | Content scope estimated with production ratios | Info | (see content-planning) |
Scoring: 10/10 = ready to build. 7-9 = minor gaps, address before starting. 4-6 = return to scoping. <4 = needs fundamental design work.
Core Loop Validation Tests
Four tests every core loop must pass:
| Test | Method | Pass Criteria |
| Sentence Test | Describe in one sentence: "Player [verbs] to [goal], earning [reward] that enables [reinvestment]" | Active verbs, clear goal, explicit reinvestment |
| Verb Chain Test | List the verbs in sequence | 2-5 verbs that feed into each other. >5 = too complex. <2 = not a loop |
| Reinvestment Test | Output of one cycle meaningfully changes the next | Strong: Diablo (Kill→Loot→Equip→Kill stronger). Weak: Flappy Bird (score up, nothing changes) |
| 30-Second Test | Time one micro-loop cycle | Under 60 seconds. If 5+ minutes, loop is too slow for rapid iteration |
Core Loop Red Flags:
| Red Flag | Symptom |
| No Reinvestment | Cycle output doesn't change next cycle |
| External Motivation Only | Story/obligation drives play, not mechanics |
| Complexity Explosion | 6+ verbs in the loop |
| Hidden Loop | Actual fun ≠ stated loop (players enjoy the metagame, not what you designed) |
| No Failure State | Can't lose or make bad decisions |
| Mandatory Grinding | Progression requires repetition without meaningful choice |
GDD Quality Audit
Design Document Anti-Patterns
| Anti-Pattern | Symptom | Fix |
| The Novel | 100+ pages of prose | Max 5 pages for MLP. Decision tables, not paragraphs |
| The Wishlist | Describes v5.0, no MLP definition | Define MLP first, park the rest |
| The Fog | Adjectives without verbs ("engaging combat") | Every feature needs concrete player verbs |
| The Fossil | Written once, never updated | Living doc, date-stamp sections |
| The Silo | Only designers can read it | Cross-discipline sections with implementation notes |
| The Clone | "Like X but..." without understanding WHY X works | Identify specific mechanics/dynamics, not the brand |
Actionability Test
Score each item 1-5. Total ≥28 = actionable. 20-27 = needs work. <20 = rewrite.
| # | Test | What to Check |
| 1 | Verb Test | Does every feature description contain player verbs? |
| 2 | Prototype Test | Could you build a prototype from this description alone? |
| 3 | Decision Test | Does it contain clear decisions (not "we'll figure it out later")? |
| 4 | Feedback Test | Are player feedback loops described (action → response)? |
| 5 | Scope Test | Is there a clear MLP boundary? |
| 6 | Cut Test | Are deferred ideas explicitly listed? |
| 7 | Pillar Test | Would the design pillars cause you to reject some plausible features? |
Decision Table: Is This Plan Ready to Build?
| # | Question | If No → |
| 1 | Can you state the core loop in one sentence? | STOP — Define the core loop first |
| 2 | Does the core loop pass the Reinvestment Test? | STOP — Loop isn't a loop, it's linear |
| 3 | Is scope complexity score ≤15 for solo dev? | STOP — Cut scope until feasible |
| 4 | Does the GDD pass the Actionability Test (≥20)? | STOP — Rewrite vague sections |
| 5 | Is a playtest planned within the first 2 weeks? | STOP — Schedule a test before building |
All five "Yes" → READY TO BUILD. Start with the tracer bullet.
Checklists
Plan Audit Checklist
- Completeness Scorecard ≥7/10
- Core loop passes all 4 validation tests
- No core loop red flags present
- GDD has none of the 6 anti-patterns
- Actionability Test score ≥20
- Scope Complexity score appropriate for team size
- No genre-specific scope traps triggered
- Economy design has sources, sinks, and player decisions (if applicable)
- Difficulty approach matches target audience
- Playtest plan is concrete (who, when, what)
- Data collection strategy exists
What to Measure (Data Collection Checklist)
Start at Tier 0 (observation + notes). Only add instrumentation when you need answers observation can't provide.
| Category | Key Metrics |
| Session | Duration, frequency, sessions-to-churn |
| Progression | Completion rate per section, drop-off points |
| Difficulty | Death/failure locations, retry counts per section |
| Economy | Earning rate, spending patterns, stockpiling behavior |
| Feature usage | Discovery rate, usage frequency, adoption timing |
Analytics tiers: Tier 0 = manual observation (free, immediate). Tier 1 = local CSV logging (free, 1-2 hours setup). Tier 2 = free SDK (GameAnalytics, Unity Analytics). Tier 3 = custom backend (rarely needed for indie games).
Evidence chain: Observation → Diagnosis → Hypothesis → Design Change → Verification. Without this chain, you're guessing.
Deep Dives
(see plan-audit/detailed-audits.md for MLP Scope Audit, Economy/Balance Audit, Difficulty Curve Assessment, Playtest Readiness Audit, Data Strategy Audit)(see plan-audit/questionnaires.md for validated playtest frameworks and templates)
See Also
- scoping — MLP process and cutting heuristics that this audit validates
(see scoping → MLP Scoping Process) - antipatterns — Anti-pattern detection complements this comprehensive audit
(see antipatterns) - design-frameworks — MDA framework for aesthetic validation
(see design-frameworks → MDA Framework) - economy-design — Detailed economy design guidance
(see economy-design) - difficulty-design — Difficulty curves and accessibility
(see difficulty-design) - playtesting — Playtest methodology and iteration
(see playtesting → Playtest Planning Checklist) - architecture-audit — Code architecture audit (companion to plan audit)
(see architecture-audit)
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.