[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F442KA7XBKAFT5Q6VRQAES":3,"skill-same:01M7F442KA7XBKAFT5Q6VRQAES":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7F442KA7XBKAFT5Q6VRQAES","review-all-gdds",null,"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.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Freview-all-gdds\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: review-all-gdds\ndescription: \"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.\"\nargument-hint: \"[focus: full | consistency | design-theory | since-last-review]\"\nuser-invocable: true\nallowed-tools: Read, Glob, Grep, Write, Bash, AskUserQuestion, Task\nmodel: opus\n---\n\n# Review All GDDs\n\nThis skill reads every system GDD simultaneously and performs two complementary\nreviews that cannot be done per-GDD in isolation:\n\n1. **Cross-GDD Consistency** — contradictions, stale references, and ownership\n   conflicts between documents\n2. **Game Design Holism** — issues that only emerge when you see all systems\n   together: dominant strategies, broken economies, cognitive overload, pillar\n   drift, competing progression loops\n\n**This is distinct from `\u002Fdesign-review`**, which reviews one GDD for internal\ncompleteness. This skill reviews the *relationships* between all GDDs.\n\n**When to run:**\n- After all MVP-tier GDDs are individually approved\n- After any GDD is significantly revised mid-production\n- Before `\u002Fcreate-architecture` begins (architecture built on inconsistent GDDs\n  inherits those inconsistencies)\n\n**Argument modes:**\n\n**Focus:** `$ARGUMENTS[0]` (blank = `full`)\n\n- **No argument \u002F `full`**: Both consistency and design theory passes\n- **`consistency`**: Cross-GDD consistency checks only (faster)\n- **`design-theory`**: Game design holism checks only\n- **`since-last-review`**: Only GDDs modified since the last review report (git-based)\n\n---\n\n## Phase 1: Load Everything\n\n### Phase 1a — L0: Summary Scan (fast, low tokens)\n\nBefore reading any full document, use Grep to extract `## Summary` sections\nfrom all GDD files:\n\n```\nGrep pattern=\"## Summary\" glob=\"design\u002Fgdd\u002F*.md\" output_mode=\"content\" -A 5\n```\n\nDisplay a manifest to the user:\n```\nFound [N] GDDs. Summaries:\n  • combat.md — [summary text]\n  • inventory.md — [summary text]\n  ...\n```\n\nFor `since-last-review` mode: run `git log --name-only` to identify GDDs\nmodified since the last review report file was written. Show the user which\nGDDs are in scope based on summaries before doing any full reads. Only\nproceed to L1 for those GDDs plus any GDDs listed in their \"Key deps\".\n\n### Phase 1b — Registry Pre-Load (fast baseline)\n\nBefore full-reading any GDD, check for the entity registry:\n\n```\nRead path=\"design\u002Fregistry\u002Fentities.yaml\"\n```\n\nIf the registry exists and has entries, use it as a **pre-built conflict\nbaseline**: known entities, items, formulas, and constants with their\nauthoritative values and source GDDs. In Phase 2, grep GDDs for registered\nnames first — this is faster than reading all GDDs in full before knowing\nwhat to look for.\n\nIf the registry is empty or absent: proceed without it. Note in the report:\n\"Entity registry is empty — consistency checks rely on full GDD reads only.\nRun `\u002Fconsistency-check` after this review to populate the registry.\"\n\n### Phase 1c — L1\u002FL2: Full Document Load\n\nFull-read the in-scope documents:\n\n1. `design\u002Fgdd\u002Fgame-concept.md` — game vision, core loop, MVP definition\n2. `design\u002Fgdd\u002Fgame-pillars.md` if it exists — design pillars and anti-pillars\n3. `design\u002Fgdd\u002Fsystems-index.md` — authoritative system list, layers, dependencies, status\n4. **Every in-scope system GDD in `design\u002Fgdd\u002F`** — read completely (skip\n   game-concept.md and systems-index.md — those are read above)\n\nReport: \"Loaded [N] system GDDs covering [M] systems. Pillars: [list]. Anti-pillars: [list].\"\n\nIf fewer than 2 system GDDs exist, stop:\n> \"Cross-GDD review requires at least 2 system GDDs. Write more GDDs first,\n> then re-run `\u002Freview-all-gdds`.\"\n\n---\n\n### Parallel Execution\n\nPhase 2 (Consistency) and Phase 3 (Design Theory) are independent — they read\nthe same GDD inputs but produce separate reports. Spawn both as parallel Task\nagents simultaneously rather than waiting for Phase 2 to complete before\nstarting Phase 3. Collect both results before writing the combined report.\n\n---\n\n## Phase 2: Cross-GDD Consistency\n\nWork through every pair and group of GDDs to find contradictions and gaps.\n\n### 2a: Dependency Bidirectionality\n\nFor every GDD's Dependencies section, check that every listed dependency is\nreciprocal:\n- If GDD-A lists \"depends on GDD-B\", check that GDD-B lists GDD-A as a dependent\n- If GDD-A lists \"depended on by GDD-C\", check that GDD-C lists GDD-A as a dependency\n- Flag any one-directional dependency as a consistency issue\n\n```\n⚠️  Dependency Asymmetry\n[system-a].md lists: Depends On → [system-b].md\n[system-b].md does NOT list [system-a].md as a dependent\n→ One of these documents has a stale dependency section\n```\n\n### 2b: Rule Contradictions\n\nFor each game rule, mechanic, or constraint defined in any GDD, check whether\nany other GDD defines a contradicting rule for the same situation:\n\nCategories to scan:\n- **Floor\u002Fceiling rules**: Does any GDD define a minimum value for an output? Does any other say a different system can bypass that floor? These contradict.\n- **Resource ownership**: If two GDDs both define how a shared resource accumulates or depletes, do they agree?\n- **State transitions**: If GDD-A describes what happens when a character dies,\n  does GDD-B's description of the same event agree?\n- **Timing**: If GDD-A says \"X happens on the same frame\", does GDD-B assume\n  it happens asynchronously?\n- **Stacking rules**: If GDD-A says status effects stack, does GDD-B assume\n  they don't?\n\n```\n🔴 Rule Contradiction\n[system-a].md: \"Minimum [output] after reduction is [floor_value]\"\n[system-b].md: \"[mechanic] bypasses [system-a]'s rules and can reduce [output] to 0\"\n→ These rules directly contradict. Which GDD is authoritative?\n```\n\n### 2c: Stale References\n\nFor every cross-document reference (GDD-A mentions a mechanic, value, or\nsystem name from GDD-B), verify the referenced element still exists in GDD-B\nwith the same name and behaviour:\n\n- If GDD-A says \"combo multiplier from the combat system feeds into score\", check\n  that the combat GDD actually defines a combo multiplier that outputs to score\n- If GDD-A references \"the progression curve defined in [system].md\", check that\n  [system].md actually has that curve, not a different progression model\n- If GDD-A was written before GDD-B and assumed a mechanic that GDD-B later\n  designed differently, flag GDD-A as containing a stale reference\n\n```\n⚠️  Stale Reference\ninventory.md (written first): \"Item weight uses the encumbrance formula\n  from movement.md\"\nmovement.md (written later): Defines no encumbrance formula — uses a flat\n  carry limit instead\n→ inventory.md references a formula that doesn't exist\n```\n\n### 2d: Data and Tuning Knob Ownership Conflicts\n\nTwo GDDs should not both claim to own the same data or tuning knob. Scan all\nTuning Knobs sections across all GDDs and flag duplicates:\n\n```\n⚠️  Ownership Conflict\n[system-a].md Tuning Knobs: \"[multiplier_name] — controls [output] scaling\"\n[system-b].md Tuning Knobs: \"[multiplier_name] — scales [output] with [factor]\"\n→ Two GDDs define multipliers on the same output. Which owns the final value?\n  This will produce either a double-application bug or a design conflict.\n```\n\n### 2e: Formula Compatibility\n\nFor GDDs whose formulas are connected (output of one feeds input of another),\ncheck that the output range of the upstream formula is within the expected\ninput range of the downstream formula:\n\n- If [system-a].md outputs values between [min]–[max], and [system-b].md is\n  designed to receive values between [min2]–[max2], is the mismatch intentional?\n- If an economy GDD expects resource acquisition in range X, and the\n  progression GDD generates it at range Y, the economy will be trivial or\n  inaccessible — is that intended?\n\nFlag incompatibilities as CONCERNS (design judgment needed, not necessarily wrong):\n\n```\n⚠️  Formula Range Mismatch\n[system-a].md: Max [output] = [value_a] (at max [condition])\n[system-b].md: Base [input] = [value_b], max [input] = [value_c]\n→ Late-[stage] [scenario] can resolve in a single [event].\n  Is this intentional? If not, either [system-a]'s ceiling or [system-b]'s ceiling needs adjustment.\n```\n\n### 2f: Acceptance Criteria Cross-Check\n\nScan Acceptance Criteria sections across all GDDs for contradictions:\n\n- GDD-A criteria: \"Player cannot die from a single hit\"\n- GDD-B criteria: \"Boss attack deals 150% of player max health\"\nThese acceptance criteria cannot both pass simultaneously.\n\n---\n\n## Phase 3: Game Design Holism\n\nReview all GDDs together through the lens of game design theory and player\npsychology. These are issues that individual GDD reviews cannot catch because\nthey require seeing all systems at once.\n\n### 3a: Progression Loop Competition\n\nA game should have one dominant progression loop that players feel is \"the\npoint\" of the game, with supporting loops that feed into it. When multiple\nsystems compete equally as the primary progression driver, players don't know\nwhat the game is about.\n\nScan all GDDs for systems that:\n- Award the player's primary resource (XP, levels, prestige, unlocks)\n- Define themselves as the \"core\" or \"main\" loop\n- Have comparable depth and time investment to other systems doing the same\n\n```\n⚠️  Competing Progression Loops\ncombat.md: Awards XP, unlocks abilities, is described as \"the core loop\"\ncrafting.md: Awards XP, unlocks recipes, is described as \"the primary activity\"\nexploration.md: Awards XP, unlocks map areas, described as \"the main driver\"\n→ Three systems all claim to be the primary progression loop and all award\n  the same primary currency. Players will optimise one and ignore the others.\n  Consider: one primary loop with the others as support systems.\n```\n\n### 3b: Player Attention Budget\n\nCount how many systems require active player attention simultaneously during\na typical session. Each actively-managed system costs attention:\n\n- Active = player must make decisions about this system regularly during play\n- Passive = system runs automatically, player sees results but doesn't manage it\n\nMore than 3-4 simultaneously active systems creates cognitive overload for most\nplayers. Present the count and flag if it exceeds 4 concurrent active systems:\n\n```\n⚠️  Cognitive Load Risk\nSimultaneously active systems during [core loop moment]:\n  1. [system-a].md — [decision type] (active)\n  2. [system-b].md — [resource management] (active)\n  3. [system-c].md — [tracking] (active)\n  4. [system-d].md — [item\u002Faction use] (active)\n  5. [system-e].md — [cooldown\u002Ftimer management] (active)\n  6. [system-f].md — [coordination decisions] (active)\n→ 6 simultaneously active systems during the core loop.\n  Research suggests 3-4 is the comfortable limit for most players.\n  Consider: which of these can be made passive or simplified?\n```\n\n### 3c: Dominant Strategy Detection\n\nA dominant strategy makes other strategies irrelevant — players discover it,\nuse it exclusively, and find the rest of the game boring. Look for:\n\n- **Resource monopolies**: One strategy generates a resource significantly\n  faster than all others\n- **Risk-free power**: A strategy that is both high-reward and low-risk\n  (if high-risk strategies exist, they need proportionally higher reward)\n- **No trade-offs**: An option that is superior in all dimensions to all others\n- **Obvious optimal path**: If any progression choice is \"clearly correct\",\n  the others aren't real choices\n\n```\n⚠️  Potential Dominant Strategy\ncombat.md: Ranged attacks deal 80% of melee damage with no risk\ncombat.md: Melee attacks deal 100% damage but require close range\n→ Unless melee has a significant compensating advantage (AOE, stagger,\n  resource regeneration), ranged is dominant — higher safety, only 20% less\n  damage. Consider what melee offers that ranged cannot.\n```\n\n### 3d: Economic Loop Analysis\n\nIdentify all resources across all GDDs (gold, XP, crafting materials, stamina,\nhealth, mana, etc.). For each resource, map its **sources** (how players gain\nit) and **sinks** (how players spend it).\n\nFlag dangerous economic conditions:\n\n| Condition | Sign | Risk |\n|-----------|------|------|\n| **Infinite source, no sink** | Resource accumulates indefinitely | Late game becomes trivially easy |\n| **Sink, no source** | Resource drains to zero | System becomes unavailable |\n| **Source >> Sink** | Surplus accumulates | Resource becomes meaningless |\n| **Sink >> Source** | Constant scarcity | Frustration and gatekeeping |\n| **Positive feedback loop** | More resource → easier to earn more | Runaway leader, snowball |\n| **No catch-up** | Falling behind accelerates deficit | Unrecoverable states |\n\n```\n🔴 Economic Imbalance: Unbounded Positive Feedback\ngold economy:\n  Sources: monster drops (scales with player power), merchant selling (unlimited)\n  Sinks: equipment purchase (one-time), ability upgrades (finite count)\n→ After equipment and abilities are purchased, gold has no sink.\n  Infinite surplus. Gold becomes meaningless mid-game.\n  Add ongoing gold sinks (upkeep, consumables, cosmetics, gambling).\n```\n\n### 3e: Difficulty Curve Consistency\n\nWhen multiple systems scale with player progression, they must scale in\ncompatible directions and at compatible rates. Mismatched scaling curves\ncreate unintended difficulty spikes or trivialisations.\n\nFor each system that scales over time, extract:\n- What scales (enemy health, player damage, resource cost, area size)\n- How it scales (linear, exponential, stepped)\n- When it scales (level, time, area)\n\nCompare all scaling curves. Flag mismatches:\n\n```\n⚠️  Difficulty Curve Mismatch\ncombat.md: Enemy health scales exponentially with area (×2 per area)\nprogression.md: Player damage scales linearly with level (+10% per level)\n→ By area 5, enemies have 32× base health; player deals ~1.5× base damage.\n  The gap widens indefinitely. Late areas will become inaccessibly difficult\n  unless the curves are reconciled.\n```\n\n### 3f: Pillar Alignment\n\nEvery system should clearly serve at least one design pillar. A system that\nserves no pillar is \"scope creep by design\" — it's in the game but not in\nservice of what the game is trying to be.\n\nFor each GDD system, check its Player Fantasy section against the design pillars.\nFlag any system whose stated fantasy doesn't map to any pillar:\n\n```\n⚠️  Pillar Drift\nfishing-system.md: Player Fantasy — \"peaceful, meditative activity\"\nPillars: \"Brutal Combat\", \"Tense Survival\", \"Emergent Stories\"\n→ The fishing system serves none of the three pillars. Either add a pillar\n  that covers it, redesign it to serve an existing pillar, or cut it.\n```\n\nAlso check anti-pillars — flag any system that does what an anti-pillar\nexplicitly says the game will NOT do:\n\n```\n🔴 Anti-Pillar Violation\nAnti-Pillar: \"We will NOT have linear story progression — player defines their path\"\nmain-quest.md: Defines a 12-chapter linear story with mandatory sequence\n→ This system directly violates the defined anti-pillar.\n```\n\n### 3g: Player Fantasy Coherence\n\nThe player fantasies across all systems should be compatible — they should\nreinforce a consistent identity for what the player IS in this game. Conflicting\nplayer fantasies create identity confusion.\n\n```\n⚠️  Player Fantasy Conflict\ncombat.md: \"You are a ruthless, precise warrior — every kill is earned\"\ndialogue.md: \"You are a charismatic diplomat — violence is always avoidable\"\nexploration.md: \"You are a reckless adventurer — diving in without a plan\"\n→ Three systems present incompatible identities. Players will feel the game\n  doesn't know what it wants them to be. Consider: do these fantasies serve\n  the same core identity from different angles, or do they genuinely conflict?\n```\n\n---\n\n## Phase 4: Cross-System Scenario Walkthrough\n\nWalk through the game from the player's perspective to find problems that only\nappear at the interaction boundary between multiple systems — things static\nanalysis of individual GDDs cannot surface.\n\n### 4a: Identify Key Multi-System Moments\n\nScan all GDDs and identify the 3–5 most important player-facing moments where\nmultiple systems activate simultaneously. Look specifically for:\n\n- **Combat + Economy overlap**: killing enemies that drop resources, spending\n  resources during combat, death\u002Frespawn interacting with economy state\n- **Progression + Difficulty overlap**: level-up triggering mid-fight, ability\n  unlocks changing combat viability, difficulty scaling at progression milestones\n- **Narrative + Gameplay overlap**: dialogue choices locking\u002Funlocking mechanics,\n  story beats interrupting resource loops, quest completion triggering system\n  state changes\n- **3+ system chains**: any player action that triggers System A, which feeds\n  into System B, which triggers System C (these are highest-risk interaction paths)\n\nList each identified scenario with a one-line description before proceeding.\n\n### 4b: Walk Through Each Scenario\n\nFor each scenario, step through the sequence explicitly:\n\n1. **Trigger** — what player action or game event starts this?\n2. **Activation order** — which systems activate, in what sequence?\n3. **Data flow** — what does each system output, and is that output a valid\n   input for the next system in the chain?\n4. **Player experience** — what does the player see, hear, or feel at each step?\n5. **Failure modes** — are there any of the following?\n   - **Race conditions**: two systems trying to modify the same state simultaneously\n   - **Feedback loops**: System A amplifies System B which re-amplifies System A\n     with no cap or dampener\n   - **Broken state transitions**: a system assumes a state that a previous\n     system may have changed (e.g., \"player is alive\" assumption after a combat\n     step that could have caused death)\n   - **Contradictory messaging**: player receives conflicting feedback from two\n     systems reacting to the same event (e.g., \"success\" sound + \"failure\" UI)\n   - **Compounding difficulty spikes**: two systems both scaling up at the same\n     progression point, multiplying the intended difficulty increase\n   - **Reward conflicts**: two systems both reacting to the same trigger with\n     rewards that together exceed the intended value (double-dipping)\n   - **Undefined behavior**: the GDDs don't specify what happens in this combined\n     state (neither system's rules cover it)\n\n```\nExample walkthrough:\nScenario: Player kills elite enemy at level-up threshold during active quest\n\nTrigger: Player lands killing blow on elite enemy\n→ combat.md: awards kill XP (100 pts)\n→ progression.md: XP total crosses level threshold → triggers level-up\n  Output: new level, stat increases, ability unlock popup\n→ quest.md: kill-count criterion met → triggers quest completion event\n  Output: quest reward XP (500 pts), completion fanfare\n→ progression.md (again): quest XP added → triggers SECOND level-up in same frame\n  ⚠️  Data flow issue: quest.md awards XP without checking if a level-up\n  is already in progress. progression.md has no guard against concurrent\n  level-up events. Undefined behavior: does the player level up once or twice?\n  Does the ability popup fire twice? Does the second level use the updated or\n  pre-update stat baseline?\n```\n\n### 4c: Flag Scenario Issues\n\nFor each problem found during the walkthrough, categorize severity:\n\n- **BLOCKER**: undefined behavior, broken state transition, or contradictory\n  player messaging — the experience is broken or incoherent in this scenario\n- **WARNING**: compounding spikes, feedback loops without caps, reward conflicts —\n  the experience works but produces unintended outcomes\n- **INFO**: minor ordering ambiguity or messaging overlap — worth noting but\n  unlikely to cause player-visible problems\n\nAdd all findings to the output report under **\"Cross-System Scenario Issues\"**.\nEach finding must cite: the scenario name, the specific systems involved, the\nstep where the issue occurs, and the nature of the failure mode.\n\n---\n\n## Phase 5: Output the Review Report\n\n```\n## Cross-GDD Review Report\nDate: [date]\nGDDs Reviewed: [N]\nSystems Covered: [list]\n\n---\n\n### Consistency Issues\n\n#### Blocking (must resolve before architecture begins)\n🔴 [Issue title]\n[What GDDs are involved, what the contradiction is, what needs to change]\n\n#### Warnings (should resolve, but won't block)\n⚠️  [Issue title]\n[What GDDs are involved, what the concern is]\n\n---\n\n### Game Design Issues\n\n#### Blocking\n🔴 [Issue title]\n[What the problem is, which GDDs are involved, design recommendation]\n\n#### Warnings\n⚠️  [Issue title]\n[What the concern is, which GDDs are affected, recommendation]\n\n---\n\n### Cross-System Scenario Issues\n\nScenarios walked: [N]\n[List scenario names]\n\n#### Blockers\n🔴 [Scenario name] — [Systems involved]\n[Step where failure occurs, nature of the failure mode, what must be resolved]\n\n#### Warnings\n⚠️  [Scenario name] — [Systems involved]\n[What the unintended outcome is, recommendation]\n\n#### Info\nℹ️  [Scenario name] — [Systems involved]\n[Minor ordering ambiguity or note]\n\n---\n\n### GDDs Flagged for Revision\n\n| GDD | Reason | Type | Priority |\n|-----|--------|------|----------|\n| [system-a].md | Rule contradiction with [system-b].md | Consistency | Blocking |\n| [system-c].md | Stale reference to nonexistent mechanic | Consistency | Blocking |\n| [system-d].md | No pillar alignment | Design Theory | Warning |\n\n---\n\n### Verdict: [PASS \u002F CONCERNS \u002F FAIL]\n\nPASS: No blocking issues. Warnings present but don't prevent architecture.\nCONCERNS: Warnings present that should be resolved but are not blocking.\nFAIL: One or more blocking issues must be resolved before architecture begins.\n\n### If FAIL — required actions before re-running:\n[Specific list of what must change in which GDD]\n```\n\n---\n\n## Phase 6: Write Report and Flag GDDs\n\nUse `AskUserQuestion` for write permission:\n- Prompt: \"May I write this review to `design\u002Fgdd\u002Fgdd-cross-review-[date].md`?\"\n- Options: `[A] Yes — write the report` \u002F `[B] No — skip`\n\nIf any GDDs are flagged for revision, use a second `AskUserQuestion`:\n- Prompt: \"Should I update the systems index to mark these GDDs as needing revision? ([list of flagged GDDs])\"\n- Options: `[A] Yes — update systems index` \u002F `[B] No — leave as-is`\n- If yes: update each flagged GDD's Status field in systems-index.md to \"Needs Revision\".\n  (Do NOT append parentheticals to the status value — other skills match \"Needs Revision\"\n  as an exact string and parentheticals break that match.)\n\n### Session State Update\n\nAfter writing the report (and updating systems index if approved), silently\nappend to `production\u002Fsession-state\u002Factive.md`:\n\n    ## Session Extract — \u002Freview-all-gdds [date]\n    - Verdict: [PASS \u002F CONCERNS \u002F FAIL]\n    - GDDs reviewed: [N]\n    - Flagged for revision: [comma-separated list, or \"None\"]\n    - Blocking issues: [N — brief one-line descriptions, or \"None\"]\n    - Recommended next: [the Phase 7 handoff action, condensed to one line]\n    - Report: design\u002Fgdd\u002Fgdd-cross-review-[date].md\n\nIf `active.md` does not exist, create it with this block as the initial content.\nConfirm in conversation: \"Session state updated.\"\n\n---\n\n## Phase 7: Handoff\n\nAfter all file writes are complete, use `AskUserQuestion` for a closing widget.\n\nBefore building options, check project state:\n- Are there any Warning-level items that are simple edits (flagged with \"30-second edit\", \"brief addition\", or similar)? → offer inline quick-fix option\n- Are any GDDs in the \"Flagged for Revision\" table? → offer \u002Fdesign-review option for each\n- Read systems-index.md for the next system with Status: Not Started → offer \u002Fdesign-system option\n- Is the verdict PASS or CONCERNS? → offer \u002Fgate-check or \u002Fcreate-architecture\n\nBuild the option list dynamically — only include options that apply:\n\n**Option pool:**\n- `[_] Apply quick fix: [W-XX description] in [gdd-name].md — [effort estimate]` (one option per simple-edit warning; only for Warning-level, not Blocking)\n- `[_] Run \u002Fdesign-review [flagged-gdd-path] — address flagged warnings` (one per flagged GDD, if any)\n- `[_] Run \u002Fdesign-system [next-system] — next in design order` (always include, name the actual system)\n- `[_] Run \u002Fcreate-architecture — begin architecture (verdict is PASS\u002FCONCERNS)` (include if verdict is not FAIL)\n- `[_] Run \u002Fgate-check — validate Systems Design phase gate` (include if verdict is PASS)\n- `[_] Stop here`\n\nAssign letters A, B, C… only to included options. Mark the most pipeline-advancing option as `(recommended)`.\n\nNever end the skill with plain text. Always close with this widget.\n\n---\n\n## Error Recovery Protocol\n\nIf any spawned agent returns BLOCKED, errors, or fails to complete:\n\n1. **Surface immediately**: Report \"[AgentName]: BLOCKED — [reason]\" before continuing\n2. **Assess dependencies**: If the blocked agent's output is required by a later phase, do not proceed past that phase without user input\n3. **Offer options** via AskUserQuestion with three choices:\n   - Skip this agent and note the gap in the final report\n   - Retry with narrower scope (fewer GDDs, single-system focus)\n   - Stop here and resolve the blocker first\n4. **Always produce a partial report** — output whatever was completed so work is not lost\n\n---\n\n## Collaborative Protocol\n\n1. **Read silently** — load all GDDs before presenting anything\n2. **Show everything** — present the full consistency and design theory analysis\n   before asking for any action\n3. **Distinguish blocking from advisory** — not every issue needs to block\n   architecture; be clear about which do\n4. **Don't make design decisions** — flag contradictions and options, but never\n   unilaterally decide which GDD is \"right\"\n5. **Ask before writing** — confirm before writing the report or updating the\n   systems index\n6. **Be specific** — every issue must cite the exact GDD, section, and text\n   involved; no vague warnings\n","# Review All GDDs\n\nThis skill reads every system GDD simultaneously and performs two complementary\nreviews that cannot be done per-GDD in isolation:\n\n1. **Cross-GDD Consistency** — contradictions, stale references, and ownership\n   conflicts between documents\n2. **Game Design Holism** — issues that only emerge when you see all systems\n   together: dominant strategies, broken economies, cognitive overload, pillar\n   drift, competing progression loops\n\n**This is distinct from `\u002Fdesign-review`**, which reviews one GDD for internal\ncompleteness. This skill reviews the *relationships* between all GDDs.\n\n**When to run:**\n- After all MVP-tier GDDs are individually approved\n- After any GDD is significantly revised mid-production\n- Before `\u002Fcreate-architecture` begins (architecture built on inconsistent GDDs\n  inherits those inconsistencies)\n\n**Argument modes:**\n\n**Focus:** `$ARGUMENTS[0]` (blank = `full`)\n\n- **No argument \u002F `full`**: Both consistency and design theory passes\n- **`consistency`**: Cross-GDD consistency checks only (faster)\n- **`design-theory`**: Game design holism checks only\n- **`since-last-review`**: Only GDDs modified since the last review report (git-based)\n\n---\n\n## Phase 1: Load Everything\n\n### Phase 1a — L0: Summary Scan (fast, low tokens)\n\nBefore reading any full document, use Grep to extract `## Summary` sections\nfrom all GDD files:\n\n```\nGrep pattern=\"## Summary\" glob=\"design\u002Fgdd\u002F*.md\" output_mode=\"content\" -A 5\n```\n\nDisplay a manifest to the user:\n```\nFound [N] GDDs. Summaries:\n  • combat.md — [summary text]\n  • inventory.md — [summary text]\n  ...\n```\n\nFor `since-last-review` mode: run `git log --name-only` to identify GDDs\nmodified since the last review report file was written. Show the user which\nGDDs are in scope based on summaries before doing any full reads. Only\nproceed to L1 for those GDDs plus any GDDs listed in their \"Key deps\".\n\n### Phase 1b — Registry Pre-Load (fast baseline)\n\nBefore full-reading any GDD, check for the entity registry:\n\n```\nRead path=\"design\u002Fregistry\u002Fentities.yaml\"\n```\n\nIf the registry exists and has entries, use it as a **pre-built conflict\nbaseline**: known entities, items, formulas, and constants with their\nauthoritative values and source GDDs. In Phase 2, grep GDDs for registered\nnames first — this is faster than reading all GDDs in full before knowing\nwhat to look for.\n\nIf the registry is empty or absent: proceed without it. Note in the report:\n\"Entity registry is empty — consistency checks rely on full GDD reads only.\nRun `\u002Fconsistency-check` after this review to populate the registry.\"\n\n### Phase 1c — L1\u002FL2: Full Document Load\n\nFull-read the in-scope documents:\n\n1. `design\u002Fgdd\u002Fgame-concept.md` — game vision, core loop, MVP definition\n2. `design\u002Fgdd\u002Fgame-pillars.md` if it exists — design pillars and anti-pillars\n3. `design\u002Fgdd\u002Fsystems-index.md` — authoritative system list, layers, dependencies, status\n4. **Every in-scope system GDD in `design\u002Fgdd\u002F`** — read completely (skip\n   game-concept.md and systems-index.md — those are read above)\n\nReport: \"Loaded [N] system GDDs covering [M] systems. Pillars: [list]. Anti-pillars: [list].\"\n\nIf fewer than 2 system GDDs exist, stop:\n> \"Cross-GDD review requires at least 2 system GDDs. Write more GDDs first,\n> then re-run `\u002Freview-all-gdds`.\"\n\n---\n\n### Parallel Execution\n\nPhase 2 (Consistency) and Phase 3 (Design Theory) are independent — they read\nthe same GDD inputs but produce separate reports. Spawn both as parallel Task\nagents simultaneously rather than waiting for Phase 2 to complete before\nstarting Phase 3. Collect both results before writing the combined report.\n\n---\n\n## Phase 2: Cross-GDD Consistency\n\nWork through every pair and group of GDDs to find contradictions and gaps.\n\n### 2a: Dependency Bidirectionality\n\nFor every GDD's Dependencies section, check that every listed dependency is\nreciprocal:\n- If GDD-A lists \"depends on GDD-B\", check that GDD-B lists GDD-A as a dependent\n- If GDD-A lists \"depended on by GDD-C\", check that GDD-C lists GDD-A as a dependency\n- Flag any one-directional dependency as a consistency issue\n\n```\n⚠️  Dependency Asymmetry\n[system-a].md lists: Depends On → [system-b].md\n[system-b].md does NOT list [system-a].md as a dependent\n→ One of these documents has a stale dependency section\n```\n\n### 2b: Rule Contradictions\n\nFor each game rule, mechanic, or constraint defined in any GDD, check whether\nany other GDD defines a contradicting rule for the same situation:\n\nCategories to scan:\n- **Floor\u002Fceiling rules**: Does any GDD define a minimum value for an output? Does any other say a different system can bypass that floor? These contradict.\n- **Resource ownership**: If two GDDs both define how a shared resource accumulates or depletes, do they agree?\n- **State transitions**: If GDD-A describes what happens when a character dies,\n  does GDD-B's description of the same event agree?\n- **Timing**: If GDD-A says \"X happens on the same frame\", does GDD-B assume\n  it happens asynchronously?\n- **Stacking rules**: If GDD-A says status effects stack, does GDD-B assume\n  they don't?\n\n```\n🔴 Rule Contradiction\n[system-a].md: \"Minimum [output] after reduction is [floor_value]\"\n[system-b].md: \"[mechanic] bypasses [system-a]'s rules and can reduce [output] to 0\"\n→ These rules directly contradict. Which GDD is authoritative?\n```\n\n### 2c: Stale References\n\nFor every cross-document reference (GDD-A mentions a mechanic, value, or\nsystem name from GDD-B), verify the referenced element still exists in GDD-B\nwith the same name and behaviour:\n\n- If GDD-A says \"combo multiplier from the combat system feeds into score\", check\n  that the combat GDD actually defines a combo multiplier that outputs to score\n- If GDD-A references \"the progression curve defined in [system].md\", check that\n  [system].md actually has that curve, not a different progression model\n- If GDD-A was written before GDD-B and assumed a mechanic that GDD-B later\n  designed differently, flag GDD-A as containing a stale reference\n\n```\n⚠️  Stale Reference\ninventory.md (written first): \"Item weight uses the encumbrance formula\n  from movement.md\"\nmovement.md (written later): Defines no encumbrance formula — uses a flat\n  carry limit instead\n→ inventory.md references a formula that doesn't exist\n```\n\n### 2d: Data and Tuning Knob Ownership Conflicts\n\nTwo GDDs should not both claim to own the same data or tuning knob. Scan all\nTuning Knobs sections across all GDDs and flag duplicates:\n\n```\n⚠️  Ownership Conflict\n[system-a].md Tuning Knobs: \"[multiplier_name] — controls [output] scaling\"\n[system-b].md Tuning Knobs: \"[multiplier_name] — scales [output] with [factor]\"\n→ Two GDDs define multipliers on the same output. Which owns the final value?\n  This will produce either a double-application bug or a design conflict.\n```\n\n### 2e: Formula Compatibility\n\nFor GDDs whose formulas are connected (output of one feeds input of another),\ncheck that the output range of the upstream formula is within the expected\ninput range of the downstream formula:\n\n- If [system-a].md outputs values between [min]–[max], and [system-b].md is\n  designed to receive values between [min2]–[max2], is the mismatch intentional?\n- If an economy GDD expects resource acquisition in range X, and the\n  progression GDD generates it at range Y, the economy will be trivial or\n  inaccessible — is that intended?\n\nFlag incompatibilities as CONCERNS (design judgment needed, not necessarily wrong):\n\n```\n⚠️  Formula Range Mismatch\n[system-a].md: Max [output] = [value_a] (at max [condition])\n[system-b].md: Base [input] = [value_b], max [input] = [value_c]\n→ Late-[stage] [scenario] can resolve in a single [event].\n  Is this intentional? If not, either [system-a]'s ceiling or [system-b]'s ceiling needs adjustment.\n```\n\n### 2f: Acceptance Criteria Cross-Check\n\nScan Acceptance Criteria sections across all GDDs for contradictions:\n\n- GDD-A criteria: \"Player cannot die from a single hit\"\n- GDD-B criteria: \"Boss attack deals 150% of player max health\"\nThese acceptance criteria cannot both pass simultaneously.\n\n---\n\n## Phase 3: Game Design Holism\n\nReview all GDDs together through the lens of game design theory and player\npsychology. These are issues that individual GDD reviews cannot catch because\nthey require seeing all systems at once.\n\n### 3a: Progression Loop Competition\n\nA game should have one dominant progression loop that players feel is \"the\npoint\" of the game, with supporting loops that feed into it. When multiple\nsystems compete equally as the primary progression driver, players don't know\nwhat the game is about.\n\nScan all GDDs for systems that:\n- Award the player's primary resource (XP, levels, prestige, unlocks)\n- Define themselves as the \"core\" or \"main\" loop\n- Have comparable depth and time investment to other systems doing the same\n\n```\n⚠️  Competing Progression Loops\ncombat.md: Awards XP, unlocks abilities, is described as \"the core loop\"\ncrafting.md: Awards XP, unlocks recipes, is described as \"the primary activity\"\nexploration.md: Awards XP, unlocks map areas, described as \"the main driver\"\n→ Three systems all claim to be the primary progression loop and all award\n  the same primary currency. Players will optimise one and ignore the others.\n  Consider: one primary loop with the others as support systems.\n```\n\n### 3b: Player Attention Budget\n\nCount how many systems require active player attention simultaneously during\na typical session. Each actively-managed system costs attention:\n\n- Active = player must make decisions about this system regularly during play\n- Passive = system runs automatically, player sees results but doesn't manage it\n\nMore than 3-4 simultaneously active systems creates cognitive overload for most\nplayers. Present the count and flag if it exceeds 4 concurrent active systems:\n\n```\n⚠️  Cognitive Load Risk\nSimultaneously active systems during [core loop moment]:\n  1. [system-a].md — [decision type] (active)\n  2. [system-b].md — [resource management] (active)\n  3. [system-c].md — [tracking] (active)\n  4. [system-d].md — [item\u002Faction use] (active)\n  5. [system-e].md — [cooldown\u002Ftimer management] (active)\n  6. [system-f].md — [coordination decisions] (active)\n→ 6 simultaneously active systems during the core loop.\n  Research suggests 3-4 is the comfortable limit for most players.\n  Consider: which of these can be made passive or simplified?\n```\n\n### 3c: Dominant Strategy Detection\n\nA dominant strategy makes other strategies irrelevant — players discover it,\nuse it exclusively, and find the rest of the game boring. Look for:\n\n- **Resource monopolies**: One strategy generates a resource significantly\n  faster than all others\n- **Risk-free power**: A strategy that is both high-reward and low-risk\n  (if high-risk strategies exist, they need proportionally higher reward)\n- **No trade-offs**: An option that is superior in all dimensions to all others\n- **Obvious optimal path**: If any progression choice is \"clearly correct\",\n  the others aren't real choices\n\n```\n⚠️  Potential Dominant Strategy\ncombat.md: Ranged attacks deal 80% of melee damage with no risk\ncombat.md: Melee attacks deal 100% damage but require close range\n→ Unless melee has a significant compensating advantage (AOE, stagger,\n  resource regeneration), ranged is dominant — higher safety, only 20% less\n  damage. Consider what melee offers that ranged cannot.\n```\n\n### 3d: Economic Loop Analysis\n\nIdentify all resources across all GDDs (gold, XP, crafting materials, stamina,\nhealth, mana, etc.). For each resource, map its **sources** (how players gain\nit) and **sinks** (how players spend it).\n\nFlag dangerous economic conditions:\n\n| Condition | Sign | Risk |\n|-----------|------|------|\n| **Infinite source, no sink** | Resource accumulates indefinitely | Late game becomes trivially easy |\n| **Sink, no source** | Resource drains to zero | System becomes unavailable |\n| **Source >> Sink** | Surplus accumulates | Resource becomes meaningless |\n| **Sink >> Source** | Constant scarcity | Frustration and gatekeeping |\n| **Positive feedback loop** | More resource → easier to earn more | Runaway leader, snowball |\n| **No catch-up** | Falling behind accelerates deficit | Unrecoverable states |\n\n```\n🔴 Economic Imbalance: Unbounded Positive Feedback\ngold economy:\n  Sources: monster drops (scales with player power), merchant selling (unlimited)\n  Sinks: equipment purchase (one-time), ability upgrades (finite count)\n→ After equipment and abilities are purchased, gold has no sink.\n  Infinite surplus. Gold becomes meaningless mid-game.\n  Add ongoing gold sinks (upkeep, consumables, cosmetics, gambling).\n```\n\n### 3e: Difficulty Curve Consistency\n\nWhen multiple systems scale with player progression, they must scale in\ncompatible directions and at compatible rates. Mismatched scaling curves\ncreate unintended difficulty spikes or trivialisations.\n\nFor each system that scales over time, extract:\n- What scales (enemy health, player damage, resource cost, area size)\n- How it scales (linear, exponential, stepped)\n- When it scales (level, time, area)\n\nCompare all scaling curves. Flag mismatches:\n\n```\n⚠️  Difficulty Curve Mismatch\ncombat.md: Enemy health scales exponentially with area (×2 per area)\nprogression.md: Player damage scales linearly with level (+10% per level)\n→ By area 5, enemies have 32× base health; player deals ~1.5× base damage.\n  The gap widens indefinitely. Late areas will become inaccessibly difficult\n  unless the curves are reconciled.\n```\n\n### 3f: Pillar Alignment\n\nEvery system should clearly serve at least one design pillar. A system that\nserves no pillar is \"scope creep by design\" — it's in the game but not in\nservice of what the game is trying to be.\n\nFor each GDD system, check its Player Fantasy section against the design pillars.\nFlag any system whose stated fantasy doesn't map to any pillar:\n\n```\n⚠️  Pillar Drift\nfishing-system.md: Player Fantasy — \"peaceful, meditative activity\"\nPillars: \"Brutal Combat\", \"Tense Survival\", \"Emergent Stories\"\n→ The fishing system serves none of the three pillars. Either add a pillar\n  that covers it, redesign it to serve an existing pillar, or cut it.\n```\n\nAlso check anti-pillars — flag any system that does what an anti-pillar\nexplicitly says the game will NOT do:\n\n```\n🔴 Anti-Pillar Violation\nAnti-Pillar: \"We will NOT have linear story progression — player defines their path\"\nmain-quest.md: Defines a 12-chapter linear story with mandatory sequence\n→ This system directly violates the defined anti-pillar.\n```\n\n### 3g: Player Fantasy Coherence\n\nThe player fantasies across all systems should be compatible — they should\nreinforce a consistent identity for what the player IS in this game. Conflicting\nplayer fantasies create identity confusion.\n\n```\n⚠️  Player Fantasy Conflict\ncombat.md: \"You are a ruthless, precise warrior — every kill is earned\"\ndialogue.md: \"You are a charismatic diplomat — violence is always avoidable\"\nexploration.md: \"You are a reckless adventurer — diving in without a plan\"\n→ Three systems present incompatible identities. Players will feel the game\n  doesn't know what it wants them to be. Consider: do these fantasies serve\n  the same core identity from different angles, or do they genuinely conflict?\n```\n\n---\n\n## Phase 4: Cross-System Scenario Walkthrough\n\nWalk through the game from the player's perspective to find problems that only\nappear at the interaction boundary between multiple systems — things static\nanalysis of individual GDDs cannot surface.\n\n### 4a: Identify Key Multi-System Moments\n\nScan all GDDs and identify the 3–5 most important player-facing moments where\nmultiple systems activate simultaneously. Look specifically for:\n\n- **Combat + Economy overlap**: killing enemies that drop resources, spending\n  resources during combat, death\u002Frespawn interacting with economy state\n- **Progression + Difficulty overlap**: level-up triggering mid-fight, ability\n  unlocks changing combat viability, difficulty scaling at progression milestones\n- **Narrative + Gameplay overlap**: dialogue choices locking\u002Funlocking mechanics,\n  story beats interrupting resource loops, quest completion triggering system\n  state changes\n- **3+ system chains**: any player action that triggers System A, which feeds\n  into System B, which triggers System C (these are highest-risk interaction paths)\n\nList each identified scenario with a one-line description before proceeding.\n\n### 4b: Walk Through Each Scenario\n\nFor each scenario, step through the sequence explicitly:\n\n1. **Trigger** — what player action or game event starts this?\n2. **Activation order** — which systems activate, in what sequence?\n3. **Data flow** — what does each system output, and is that output a valid\n   input for the next system in the chain?\n4. **Player experience** — what does the player see, hear, or feel at each step?\n5. **Failure modes** — are there any of the following?\n   - **Race conditions**: two systems trying to modify the same state simultaneously\n   - **Feedback loops**: System A amplifies System B which re-amplifies System A\n     with no cap or dampener\n   - **Broken state transitions**: a system assumes a state that a previous\n     system may have changed (e.g., \"player is alive\" assumption after a combat\n     step that could have caused death)\n   - **Contradictory messaging**: player receives conflicting feedback from two\n     systems reacting to the same event (e.g., \"success\" sound + \"failure\" UI)\n   - **Compounding difficulty spikes**: two systems both scaling up at the same\n     progression point, multiplying the intended difficulty increase\n   - **Reward conflicts**: two systems both reacting to the same trigger with\n     rewards that together exceed the intended value (double-dipping)\n   - **Undefined behavior**: the GDDs don't specify what happens in this combined\n     state (neither system's rules cover it)\n\n```\nExample walkthrough:\nScenario: Player kills elite enemy at level-up threshold during active quest\n\nTrigger: Player lands killing blow on elite enemy\n→ combat.md: awards kill XP (100 pts)\n→ progression.md: XP total crosses level threshold → triggers level-up\n  Output: new level, stat increases, ability unlock popup\n→ quest.md: kill-count criterion met → triggers quest completion event\n  Output: quest reward XP (500 pts), completion fanfare\n→ progression.md (again): quest XP added → triggers SECOND level-up in same frame\n  ⚠️  Data flow issue: quest.md awards XP without checking if a level-up\n  is already in progress. progression.md has no guard against concurrent\n  level-up events. Undefined behavior: does the player level up once or twice?\n  Does the ability popup fire twice? Does the second level use the updated or\n  pre-update stat baseline?\n```\n\n### 4c: Flag Scenario Issues\n\nFor each problem found during the walkthrough, categorize severity:\n\n- **BLOCKER**: undefined behavior, broken state transition, or contradictory\n  player messaging — the experience is broken or incoherent in this scenario\n- **WARNING**: compounding spikes, feedback loops without caps, reward conflicts —\n  the experience works but produces unintended outcomes\n- **INFO**: minor ordering ambiguity or messaging overlap — worth noting but\n  unlikely to cause player-visible problems\n\nAdd all findings to the output report under **\"Cross-System Scenario Issues\"**.\nEach finding must cite: the scenario name, the specific systems involved, the\nstep where the issue occurs, and the nature of the failure mode.\n\n---\n\n## Phase 5: Output the Review Report\n\n```\n## Cross-GDD Review Report\nDate: [date]\nGDDs Reviewed: [N]\nSystems Covered: [list]\n\n---\n\n### Consistency Issues\n\n#### Blocking (must resolve before architecture begins)\n🔴 [Issue title]\n[What GDDs are involved, what the contradiction is, what needs to change]\n\n#### Warnings (should resolve, but won't block)\n⚠️  [Issue title]\n[What GDDs are involved, what the concern is]\n\n---\n\n### Game Design Issues\n\n#### Blocking\n🔴 [Issue title]\n[What the problem is, which GDDs are involved, design recommendation]\n\n#### Warnings\n⚠️  [Issue title]\n[What the concern is, which GDDs are affected, recommendation]\n\n---\n\n### Cross-System Scenario Issues\n\nScenarios walked: [N]\n[List scenario names]\n\n#### Blockers\n🔴 [Scenario name] — [Systems involved]\n[Step where failure occurs, nature of the failure mode, what must be resolved]\n\n#### Warnings\n⚠️  [Scenario name] — [Systems involved]\n[What the unintended outcome is, recommendation]\n\n#### Info\nℹ️  [Scenario name] — [Systems involved]\n[Minor ordering ambiguity or note]\n\n---\n\n### GDDs Flagged for Revision\n\n| GDD | Reason | Type | Priority |\n|-----|--------|------|----------|\n| [system-a].md | Rule contradiction with [system-b].md | Consistency | Blocking |\n| [system-c].md | Stale reference to nonexistent mechanic | Consistency | Blocking |\n| [system-d].md | No pillar alignment | Design Theory | Warning |\n\n---\n\n### Verdict: [PASS \u002F CONCERNS \u002F FAIL]\n\nPASS: No blocking issues. Warnings present but don't prevent architecture.\nCONCERNS: Warnings present that should be resolved but are not blocking.\nFAIL: One or more blocking issues must be resolved before architecture begins.\n\n### If FAIL — required actions before re-running:\n[Specific list of what must change in which GDD]\n```\n\n---\n\n## Phase 6: Write Report and Flag GDDs\n\nUse `AskUserQuestion` for write permission:\n- Prompt: \"May I write this review to `design\u002Fgdd\u002Fgdd-cross-review-[date].md`?\"\n- Options: `[A] Yes — write the report` \u002F `[B] No — skip`\n\nIf any GDDs are flagged for revision, use a second `AskUserQuestion`:\n- Prompt: \"Should I update the systems index to mark these GDDs as needing revision? ([list of flagged GDDs])\"\n- Options: `[A] Yes — update systems index` \u002F `[B] No — leave as-is`\n- If yes: update each flagged GDD's Status field in systems-index.md to \"Needs Revision\".\n  (Do NOT append parentheticals to the status value — other skills match \"Needs Revision\"\n  as an exact string and parentheticals break that match.)\n\n### Session State Update\n\nAfter writing the report (and updating systems index if approved), silently\nappend to `production\u002Fsession-state\u002Factive.md`:\n\n    ## Session Extract — \u002Freview-all-gdds [date]\n    - Verdict: [PASS \u002F CONCERNS \u002F FAIL]\n    - GDDs reviewed: [N]\n    - Flagged for revision: [comma-separated list, or \"None\"]\n    - Blocking issues: [N — brief one-line descriptions, or \"None\"]\n    - Recommended next: [the Phase 7 handoff action, condensed to one line]\n    - Report: design\u002Fgdd\u002Fgdd-cross-review-[date].md\n\nIf `active.md` does not exist, create it with this block as the initial content.\nConfirm in conversation: \"Session state updated.\"\n\n---\n\n## Phase 7: Handoff\n\nAfter all file writes are complete, use `AskUserQuestion` for a closing widget.\n\nBefore building options, check project state:\n- Are there any Warning-level items that are simple edits (flagged with \"30-second edit\", \"brief addition\", or similar)? → offer inline quick-fix option\n- Are any GDDs in the \"Flagged for Revision\" table? → offer \u002Fdesign-review option for each\n- Read systems-index.md for the next system with Status: Not Started → offer \u002Fdesign-system option\n- Is the verdict PASS or CONCERNS? → offer \u002Fgate-check or \u002Fcreate-architecture\n\nBuild the option list dynamically — only include options that apply:\n\n**Option pool:**\n- `[_] Apply quick fix: [W-XX description] in [gdd-name].md — [effort estimate]` (one option per simple-edit warning; only for Warning-level, not Blocking)\n- `[_] Run \u002Fdesign-review [flagged-gdd-path] — address flagged warnings` (one per flagged GDD, if any)\n- `[_] Run \u002Fdesign-system [next-system] — next in design order` (always include, name the actual system)\n- `[_] Run \u002Fcreate-architecture — begin architecture (verdict is PASS\u002FCONCERNS)` (include if verdict is not FAIL)\n- `[_] Run \u002Fgate-check — validate Systems Design phase gate` (include if verdict is PASS)\n- `[_] Stop here`\n\nAssign letters A, B, C… only to included options. Mark the most pipeline-advancing option as `(recommended)`.\n\nNever end the skill with plain text. Always close with this widget.\n\n---\n\n## Error Recovery Protocol\n\nIf any spawned agent returns BLOCKED, errors, or fails to complete:\n\n1. **Surface immediately**: Report \"[AgentName]: BLOCKED — [reason]\" before continuing\n2. **Assess dependencies**: If the blocked agent's output is required by a later phase, do not proceed past that phase without user input\n3. **Offer options** via AskUserQuestion with three choices:\n   - Skip this agent and note the gap in the final report\n   - Retry with narrower scope (fewer GDDs, single-system focus)\n   - Stop here and resolve the blocker first\n4. **Always produce a partial report** — output whatever was completed so work is not lost\n\n---\n\n## Collaborative Protocol\n\n1. **Read silently** — load all GDDs before presenting anything\n2. **Show everything** — present the full consistency and design theory analysis\n   before asking for any action\n3. **Distinguish blocking from advisory** — not every issue needs to block\n   architecture; be clear about which do\n4. **Don't make design decisions** — flag contradictions and options, but never\n   unilaterally decide which GDD is \"right\"\n5. **Ask before writing** — confirm before writing the report or updating the\n   systems index\n6. **Be specific** — every issue must cite the exact GDD, section, and text\n   involved; no vague warnings\n",{"name":5,"model":24,"description":7,"allowed-tools":25,"argument-hint":26,"user-invocable":27},"opus","Read, Glob, Grep, Write, Bash, AskUserQuestion, Task","[focus: full | consistency | design-theory | since-last-review]",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Freview-all-gdds",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill review-all-gdds",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill review-all-gdds",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill review-all-gdds","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Freview-all-gdds\u002FSKILL.md",[],[50,57,62,69,76,83],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":58,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]