Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →donchitos/review-all-gdds
Holistic cross-GDD consistency and game design review. Reads all system GDDs simultaneously and checks for contradictions between them, stale references, ownership conflicts, formula incompatibilities, and game design theory violations (dominant strategies, economic imbalance, cognitive overload, pillar drift). Run after all MVP GDDs are written, before architecture begins.
Passed 11 of 17 test cases with the skill, and 7 of 17 without it.
and 8 more in the full report
7 fixed8 passed either way7 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/15/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
After writing the cross-GDD review report to disk, what file must be updated to track session state, and what exact header section should be appended?
| Checked | Without skill | With skill |
|---|---|---|
| The session state is recorded by appending an entry to production/session-state/active.md. | Missed | Passed |
| The appended entry begins with the header line ## Session Extract — /review-all-gdds [date]. | Missed | Passed |
The instructions your model reads when the skill loads.
!bash "${CLAUDE_SKILL_DIR}/../../hooks/yaml-helper.sh" resolve_config --keys automation,workflow,system_overrides
This skill reads every system GDD simultaneously and performs two complementary reviews that cannot be done per-GDD in isolation:
This is distinct from /design-review, which reviews one GDD for internal
completeness. This skill reviews the relationships between all GDDs.
When to run:
/create-architecture begins (architecture built on inconsistent GDDs
inherits those inconsistencies)Every AskUserQuestion call follows .claude/docs/automation-modes.md
(collaborative asks always · guided major-only · autonomous logs and proceeds;
automation_always_ask categories always prompt).
Argument modes:
Focus: $ARGUMENTS (blank = full)
full: Both consistency and design theory passesconsistency: Cross-GDD consistency checks only (faster)design-theory: Game design holism checks onlysince-last-review: Only GDDs modified since the last review report (git-based)workflow per GDD (per .claude/docs/workflow-modes.md): each GDD validates
against its effective tier — the project value, overridden per system by the
system_overrides row for that system when the block lists one. At full, validate all 8
test cases passed, vs 7 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.