القائمة
Maintain deterministic performance, screenshot, fleet, geometry, asset, and release verification tools.
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/Kevin-Liu-01/Claude-of-Tanks --skill tools-skillيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
Build and verify Claude of Tanks without crossing simulation, rendering, fleet-generation, or shared-worktree ownership boundaries.
Work on first-party procedural tank specs, builders, materials, profiles, ordering, and asset provenance.
Work on battle integration, bots, input, garage dressing, progression, replays, and studio state.
استنادا إلى تصنيف SOC المهني
عرض SKILL.md
| name | tools-skill |
| description | Maintain deterministic performance, screenshot, fleet, geometry, asset, and release verification tools. |
Provide reproducible evidence for game performance, rendering, tank fidelity,
asset provenance, and public builds.
attribution-audit.mjs enforces the repository-wide Kevin B. Liu notice,
named authorship for every playable model, and exact records for tracked
external model files.
Performance probes drive the browser and record JSON; fleet/geometry tools audit authored tanks; screenshot/visual tools stage canonical views; strip/release tools enforce public asset boundaries.
Pin URL, flags, roster, timings, and output path. Make gates fail visibly and
avoid editing generated evidence manually. Combat-anatomy generation always
uses ALL_TANK_IDS; donor/retired spec rows are not part of the playable gate.
Read the tool's CLI/help and its current evidence doc, run a baseline, then
compare the same scenario after changes. Multiplayer release checks include the
two-player persistent-room soak, human 2v2 (npm run test:net:four), and full
human 7v7 capacity (npm run test:net:seven) browser paths. Visual combat
certification is the separate npm run test:net:seven:live gate: two real 7v7
matches render the host and an impaired remote client while all fourteen tanks
move, fire, deal damage, and report transport/prediction/frame/shadow health.
Tank work must run npm run tank:anatomy:update before asset/release checks;
the update refreshes the receipt map and only the three fleet technical views,
preserving unrelated garage/top/side/markings assets.
Many tmp-* tools and .qa-dev/ outputs are transient and must not be staged.
Own and stop every dev server/browser process you start.
