[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F59T1KCQPQ1TBSHA6RF7V3":3,"skill-same:01M7F59T1KCQPQ1TBSHA6RF7V3":48},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7F59T1KCQPQ1TBSHA6RF7V3","soak-test",null,"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.","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\u002Fsoak-test\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: soak-test\ndescription: \"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.\"\nargument-hint: \"[duration: 30m | 1h | 2h | 4h] [focus: memory | stability | balance | all]\"\nuser-invocable: true\nallowed-tools: Read, Glob, Grep, Write\n---\n\n# Soak Test\n\nA soak test (also called an endurance test) is an extended play session run\nwith specific observation goals. Unlike a smoke check (broad critical path,\n~10 min) or a single-feature playtest (~30 min), a soak test runs for **30\nminutes to several hours** to surface:\n\n- **Memory leaks** — gradual heap growth that only appears after scene transitions\n- **Performance drift** — frame time degradation that worsens over time\n- **State accumulation bugs** — issues that only appear after N repetitions\n  of a mechanic (inventory full, score overflow, AI state corruption)\n- **Fun fatigue** — mechanics that feel good in a first session but grow\n  repetitive over extended play\n- **Content exhaustion** — the point where players run out of novel content\n\n**This skill generates the observation protocol and analysis harness — the\nhuman does the actual playing.**\n\n**Output:** `production\u002Fqa\u002Fsoak-test-[date]-[duration].md`\n\n**When to run:**\n- Polish phase — before `\u002Fgate-check release`\n- After fixing a memory or stability issue (regression soak)\n- When extended play has not been formally tracked\n\n---\n\n## 1. Parse Arguments\n\n**Duration** (default: `1h`):\n- `30m` — short soak; suitable for testing a single mechanic or scene\n- `1h` — standard soak; covers most common leak categories\n- `2h` — extended soak; recommended for first full Polish soak\n- `4h` — deep soak; required for games with long session design (RPGs, sims)\n\n**Focus** (default: `all`):\n- `memory` — focus on heap size, object count, leak patterns\n- `stability` — focus on crash\u002Ffreeze\u002Fhang detection\n- `balance` — focus on fun fatigue, content exhaustion, difficulty perception\n- `all` — all of the above\n\n---\n\n## 2. Load Context\n\nRead:\n- `.claude\u002Fdocs\u002Ftechnical-preferences.md` — engine (for engine-specific memory\n  monitoring guidance), performance budgets (memory ceiling, target FPS)\n- `design\u002Fgdd\u002Fgame-concept.md` — intended session length (for comparison against\n  soak duration), core loop description\n- Most recent file in `production\u002Fplaytests\u002F` — prior playtest findings\n  (to avoid re-documenting known issues)\n- Most recent file in `production\u002Fqa\u002Fqa-plan-*.md` — current sprint test coverage\n  (to understand what has been formally tested vs. what the soak covers)\n\nNote any performance budget targets from technical-preferences.md:\n- Memory ceiling: [N MB, or \"not set\"]\n- Target FPS: [N, or \"not set\"]\n- Frame budget: [N ms, or \"not set\"]\n\n---\n\n## 3. Define Observation Checkpoints\n\nBased on duration, generate timed checkpoints:\n\n**30m soak**: T+0, T+10, T+20, T+30\n**1h soak**: T+0, T+15, T+30, T+45, T+60\n**2h soak**: T+0, T+20, T+40, T+60, T+80, T+100, T+120\n**4h soak**: T+0, T+30, T+60, T+90, T+120, T+180, T+240\n\nAt each checkpoint, the observer records the observation items defined in\nPhase 4.\n\n---\n\n## 4. Generate the Soak Test Protocol\n\n### Memory \u002F Stability observation items (if focus = memory or all)\n\nEngine-specific monitoring guidance:\n\n**Godot 4:**\n- Open Debugger → Monitors tab; track `Memory → Static Memory` and\n  `Object Count → Objects` across checkpoints\n- Record: Static Memory (KB), Object Count, Orphan Nodes count\n- Alert threshold: Memory growth > 20% from T+0 after the first 15 minutes\n  (some growth on load is expected; sustained growth indicates a leak)\n- Note: `Performance.get_monitor(Performance.MEMORY_STATIC)` returns bytes\n  in Godot 4.6\n\n**Unity:**\n- Open Memory Profiler (Window → Analysis → Memory Profiler)\n- Record: Total Reserved Memory (MB), GC Allocated (MB), Object Count at each checkpoint\n- Alert threshold: GC Allocated growing monotonically across 3+ checkpoints\n\n**Unreal Engine:**\n- Use `stat memory` console command at each checkpoint\n- Record: Physical Memory Used (MB), Physical Memory Available\n- Alert threshold: Physical Memory Used growth > 50MB over the full soak\n\n### Stability observation items (if focus = stability or all)\n\nAt each checkpoint, note:\n- [ ] No crash, hang, or freeze occurred since last checkpoint\n- [ ] Frame rate still within target budget ([target FPS] fps)\n- [ ] Audio still playing correctly (no desync or silence)\n- [ ] All HUD elements still rendering correctly\n- [ ] Input responding as expected (no input loss or lag spike)\n\n### Balance \u002F fatigue observation items (if focus = balance or all)\n\nCollect subjective observations at each checkpoint:\n- [ ] Core mechanic still feels rewarding (Y\u002FN)\n- [ ] Perceived difficulty level: [too easy \u002F appropriate \u002F too hard]\n- [ ] Any \"I've seen this before\" moments since last checkpoint? (novel content exhaustion)\n- [ ] Any moment of frustration since last checkpoint? Note cause.\n- [ ] Any moment of peak engagement since last checkpoint? Note cause.\n\n---\n\n## 5. Generate the Protocol Document\n\n```markdown\n# Soak Test Protocol\n\n> **Date**: [date]\n> **Duration**: [duration]\n> **Focus**: [memory | stability | balance | all]\n> **Engine**: [engine]\n> **Generated by**: \u002Fsoak-test\n\n---\n\n## Pre-Session Setup\n\nBefore starting the soak:\n\n- [ ] Game is running from a **fresh launch** (not resumed from a prior session)\n- [ ] All background applications closed (minimise OS memory interference)\n- [ ] Performance monitoring tool open and recording:\n  - **Godot**: Debugger → Monitors tab → Memory section visible\n  - **Unity**: Memory Profiler window open\n  - **Unreal**: `stat memory` ready in console\n- [ ] Soak target confirmed: [session design intent from game concept]\n- [ ] Prior known issues to watch for: [from most recent playtest \u002F qa-plan]\n\n---\n\n## Baseline (T+0) — Record Before Playing\n\n| Metric | Baseline Value |\n|--------|---------------|\n| Memory \u002F Heap | [record before first frame of gameplay] |\n| Object Count | [record] |\n| FPS (first 30 seconds) | [record] |\n| [Engine-specific metric] | [record] |\n\n---\n\n## Checkpoint Log\n\n### T+[N] minutes\n\n**Memory \u002F Stability** *(if applicable)*:\n\n| Metric | Value | Δ from Baseline | Alert? |\n|--------|-------|-----------------|--------|\n| Memory \u002F Heap | | | |\n| Object Count | | | |\n| FPS | | | |\n| Crashes \u002F Hangs | | | |\n\n**Stability checks**:\n- [ ] No crash or hang since last checkpoint\n- [ ] Frame rate within budget ([N] fps target)\n- [ ] Audio correct\n- [ ] HUD rendering correctly\n- [ ] Input responding correctly\n\n**Balance \u002F Fatigue** *(if applicable)*:\n- Core mechanic still rewarding: Y \u002F N\n- Difficulty perception: too easy \u002F appropriate \u002F too hard\n- Notable moments: [note any peak engagement or frustration]\n- Content exhaustion signs: Y \u002F N — [describe]\n\n**Free observations**:\n*(Note anything unexpected observed since the last checkpoint)*\n\n---\n\n[Repeat Checkpoint Log section for each timed checkpoint]\n\n---\n\n## Post-Session Analysis\n\n### Memory Trend\n\n| Checkpoint | Memory | Δ\u002Fhr extrapolated |\n|------------|--------|-------------------|\n| T+0 | | |\n| [T+N] | | |\n\n**Leak detected?** Y \u002F N\n**Estimated time to OOM at current rate**: [N hours \u002F not applicable]\n\n### Stability Summary\n\nTotal crashes: [N]\nTotal hangs: [N]\nWorst FPS observed: [N] fps at [checkpoint]\nPerformance degradation: stable \u002F mild \u002F severe\n\n### Balance \u002F Fatigue Summary\n\nFun curve: [engaged throughout \u002F fatigue onset at T+N \u002F repetitive from start]\nContent exhaustion point: [never \u002F at T+N \u002F early]\nDifficulty arc: [appropriate \u002F too easy throughout \u002F difficulty spike at T+N]\n\n### Issues Found\n\n| ID | Severity | Checkpoint | Description |\n|----|----------|------------|-------------|\n| SOAK-001 | S[1-4] | T+[N] | [description] |\n\n---\n\n## Verdict: PASS \u002F PASS WITH CONCERNS \u002F FAIL\n\n**PASS**: No leaks detected, stability maintained, fun factor consistent\n**PASS WITH CONCERNS**: Minor drift or fatigue noted; addressable in Polish\n**FAIL**: Memory leak confirmed, stability breach, or severe fun fatigue\n\n---\n\n## Sign-Off\n\n- **Tester**: [name] — [date]\n- **QA Lead review**: [name] — [date]\n```\n\n---\n\n## 6. Write Output\n\nPresent the protocol summary in conversation, then ask:\n\n\"May I write this soak test protocol to\n`production\u002Fqa\u002Fsoak-test-[date]-[duration].md`?\"\n\nWrite only after approval.\n\nAfter writing:\n\n\"Protocol written. To run the soak:\n1. Open the file and follow the Pre-Session Setup checklist\n2. Record each checkpoint as you play\n3. Complete the Post-Session Analysis section when done\n4. File bugs from 'Issues Found' to `production\u002Fqa\u002Fbugs\u002F`\n5. Run `\u002Fbug-triage sprint` after the session to integrate any S1\u002FS2 issues\n\nIf the verdict is FAIL, run `\u002Fsmoke-check` again after fixing the issues.\"\n\n---\n\n## Collaborative Protocol\n\n- **This skill generates a protocol — humans run it** — never attempt to\n  run a soak test automatically. The observations require a human observer.\n- **Duration should match the game's session design** — a 5-minute game\n  doesn't need a 4h soak; a city-builder might. Use judgment and ask if unclear.\n- **First soak should be `all` focus** — narrow focus (memory-only) is for\n  regression soaks after a specific fix, not the first pass\n- **Ask before writing** — always confirm before creating the protocol file\n","# Soak Test\n\nA soak test (also called an endurance test) is an extended play session run\nwith specific observation goals. Unlike a smoke check (broad critical path,\n~10 min) or a single-feature playtest (~30 min), a soak test runs for **30\nminutes to several hours** to surface:\n\n- **Memory leaks** — gradual heap growth that only appears after scene transitions\n- **Performance drift** — frame time degradation that worsens over time\n- **State accumulation bugs** — issues that only appear after N repetitions\n  of a mechanic (inventory full, score overflow, AI state corruption)\n- **Fun fatigue** — mechanics that feel good in a first session but grow\n  repetitive over extended play\n- **Content exhaustion** — the point where players run out of novel content\n\n**This skill generates the observation protocol and analysis harness — the\nhuman does the actual playing.**\n\n**Output:** `production\u002Fqa\u002Fsoak-test-[date]-[duration].md`\n\n**When to run:**\n- Polish phase — before `\u002Fgate-check release`\n- After fixing a memory or stability issue (regression soak)\n- When extended play has not been formally tracked\n\n---\n\n## 1. Parse Arguments\n\n**Duration** (default: `1h`):\n- `30m` — short soak; suitable for testing a single mechanic or scene\n- `1h` — standard soak; covers most common leak categories\n- `2h` — extended soak; recommended for first full Polish soak\n- `4h` — deep soak; required for games with long session design (RPGs, sims)\n\n**Focus** (default: `all`):\n- `memory` — focus on heap size, object count, leak patterns\n- `stability` — focus on crash\u002Ffreeze\u002Fhang detection\n- `balance` — focus on fun fatigue, content exhaustion, difficulty perception\n- `all` — all of the above\n\n---\n\n## 2. Load Context\n\nRead:\n- `.claude\u002Fdocs\u002Ftechnical-preferences.md` — engine (for engine-specific memory\n  monitoring guidance), performance budgets (memory ceiling, target FPS)\n- `design\u002Fgdd\u002Fgame-concept.md` — intended session length (for comparison against\n  soak duration), core loop description\n- Most recent file in `production\u002Fplaytests\u002F` — prior playtest findings\n  (to avoid re-documenting known issues)\n- Most recent file in `production\u002Fqa\u002Fqa-plan-*.md` — current sprint test coverage\n  (to understand what has been formally tested vs. what the soak covers)\n\nNote any performance budget targets from technical-preferences.md:\n- Memory ceiling: [N MB, or \"not set\"]\n- Target FPS: [N, or \"not set\"]\n- Frame budget: [N ms, or \"not set\"]\n\n---\n\n## 3. Define Observation Checkpoints\n\nBased on duration, generate timed checkpoints:\n\n**30m soak**: T+0, T+10, T+20, T+30\n**1h soak**: T+0, T+15, T+30, T+45, T+60\n**2h soak**: T+0, T+20, T+40, T+60, T+80, T+100, T+120\n**4h soak**: T+0, T+30, T+60, T+90, T+120, T+180, T+240\n\nAt each checkpoint, the observer records the observation items defined in\nPhase 4.\n\n---\n\n## 4. Generate the Soak Test Protocol\n\n### Memory \u002F Stability observation items (if focus = memory or all)\n\nEngine-specific monitoring guidance:\n\n**Godot 4:**\n- Open Debugger → Monitors tab; track `Memory → Static Memory` and\n  `Object Count → Objects` across checkpoints\n- Record: Static Memory (KB), Object Count, Orphan Nodes count\n- Alert threshold: Memory growth > 20% from T+0 after the first 15 minutes\n  (some growth on load is expected; sustained growth indicates a leak)\n- Note: `Performance.get_monitor(Performance.MEMORY_STATIC)` returns bytes\n  in Godot 4.6\n\n**Unity:**\n- Open Memory Profiler (Window → Analysis → Memory Profiler)\n- Record: Total Reserved Memory (MB), GC Allocated (MB), Object Count at each checkpoint\n- Alert threshold: GC Allocated growing monotonically across 3+ checkpoints\n\n**Unreal Engine:**\n- Use `stat memory` console command at each checkpoint\n- Record: Physical Memory Used (MB), Physical Memory Available\n- Alert threshold: Physical Memory Used growth > 50MB over the full soak\n\n### Stability observation items (if focus = stability or all)\n\nAt each checkpoint, note:\n- [ ] No crash, hang, or freeze occurred since last checkpoint\n- [ ] Frame rate still within target budget ([target FPS] fps)\n- [ ] Audio still playing correctly (no desync or silence)\n- [ ] All HUD elements still rendering correctly\n- [ ] Input responding as expected (no input loss or lag spike)\n\n### Balance \u002F fatigue observation items (if focus = balance or all)\n\nCollect subjective observations at each checkpoint:\n- [ ] Core mechanic still feels rewarding (Y\u002FN)\n- [ ] Perceived difficulty level: [too easy \u002F appropriate \u002F too hard]\n- [ ] Any \"I've seen this before\" moments since last checkpoint? (novel content exhaustion)\n- [ ] Any moment of frustration since last checkpoint? Note cause.\n- [ ] Any moment of peak engagement since last checkpoint? Note cause.\n\n---\n\n## 5. Generate the Protocol Document\n\n```markdown\n# Soak Test Protocol\n\n> **Date**: [date]\n> **Duration**: [duration]\n> **Focus**: [memory | stability | balance | all]\n> **Engine**: [engine]\n> **Generated by**: \u002Fsoak-test\n\n---\n\n## Pre-Session Setup\n\nBefore starting the soak:\n\n- [ ] Game is running from a **fresh launch** (not resumed from a prior session)\n- [ ] All background applications closed (minimise OS memory interference)\n- [ ] Performance monitoring tool open and recording:\n  - **Godot**: Debugger → Monitors tab → Memory section visible\n  - **Unity**: Memory Profiler window open\n  - **Unreal**: `stat memory` ready in console\n- [ ] Soak target confirmed: [session design intent from game concept]\n- [ ] Prior known issues to watch for: [from most recent playtest \u002F qa-plan]\n\n---\n\n## Baseline (T+0) — Record Before Playing\n\n| Metric | Baseline Value |\n|--------|---------------|\n| Memory \u002F Heap | [record before first frame of gameplay] |\n| Object Count | [record] |\n| FPS (first 30 seconds) | [record] |\n| [Engine-specific metric] | [record] |\n\n---\n\n## Checkpoint Log\n\n### T+[N] minutes\n\n**Memory \u002F Stability** *(if applicable)*:\n\n| Metric | Value | Δ from Baseline | Alert? |\n|--------|-------|-----------------|--------|\n| Memory \u002F Heap | | | |\n| Object Count | | | |\n| FPS | | | |\n| Crashes \u002F Hangs | | | |\n\n**Stability checks**:\n- [ ] No crash or hang since last checkpoint\n- [ ] Frame rate within budget ([N] fps target)\n- [ ] Audio correct\n- [ ] HUD rendering correctly\n- [ ] Input responding correctly\n\n**Balance \u002F Fatigue** *(if applicable)*:\n- Core mechanic still rewarding: Y \u002F N\n- Difficulty perception: too easy \u002F appropriate \u002F too hard\n- Notable moments: [note any peak engagement or frustration]\n- Content exhaustion signs: Y \u002F N — [describe]\n\n**Free observations**:\n*(Note anything unexpected observed since the last checkpoint)*\n\n---\n\n[Repeat Checkpoint Log section for each timed checkpoint]\n\n---\n\n## Post-Session Analysis\n\n### Memory Trend\n\n| Checkpoint | Memory | Δ\u002Fhr extrapolated |\n|------------|--------|-------------------|\n| T+0 | | |\n| [T+N] | | |\n\n**Leak detected?** Y \u002F N\n**Estimated time to OOM at current rate**: [N hours \u002F not applicable]\n\n### Stability Summary\n\nTotal crashes: [N]\nTotal hangs: [N]\nWorst FPS observed: [N] fps at [checkpoint]\nPerformance degradation: stable \u002F mild \u002F severe\n\n### Balance \u002F Fatigue Summary\n\nFun curve: [engaged throughout \u002F fatigue onset at T+N \u002F repetitive from start]\nContent exhaustion point: [never \u002F at T+N \u002F early]\nDifficulty arc: [appropriate \u002F too easy throughout \u002F difficulty spike at T+N]\n\n### Issues Found\n\n| ID | Severity | Checkpoint | Description |\n|----|----------|------------|-------------|\n| SOAK-001 | S[1-4] | T+[N] | [description] |\n\n---\n\n## Verdict: PASS \u002F PASS WITH CONCERNS \u002F FAIL\n\n**PASS**: No leaks detected, stability maintained, fun factor consistent\n**PASS WITH CONCERNS**: Minor drift or fatigue noted; addressable in Polish\n**FAIL**: Memory leak confirmed, stability breach, or severe fun fatigue\n\n---\n\n## Sign-Off\n\n- **Tester**: [name] — [date]\n- **QA Lead review**: [name] — [date]\n```\n\n---\n\n## 6. Write Output\n\nPresent the protocol summary in conversation, then ask:\n\n\"May I write this soak test protocol to\n`production\u002Fqa\u002Fsoak-test-[date]-[duration].md`?\"\n\nWrite only after approval.\n\nAfter writing:\n\n\"Protocol written. To run the soak:\n1. Open the file and follow the Pre-Session Setup checklist\n2. Record each checkpoint as you play\n3. Complete the Post-Session Analysis section when done\n4. File bugs from 'Issues Found' to `production\u002Fqa\u002Fbugs\u002F`\n5. Run `\u002Fbug-triage sprint` after the session to integrate any S1\u002FS2 issues\n\nIf the verdict is FAIL, run `\u002Fsmoke-check` again after fixing the issues.\"\n\n---\n\n## Collaborative Protocol\n\n- **This skill generates a protocol — humans run it** — never attempt to\n  run a soak test automatically. The observations require a human observer.\n- **Duration should match the game's session design** — a 5-minute game\n  doesn't need a 4h soak; a city-builder might. Use judgment and ask if unclear.\n- **First soak should be `all` focus** — narrow focus (memory-only) is for\n  regression soaks after a specific fix, not the first pass\n- **Ask before writing** — always confirm before creating the protocol file\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25,"user-invocable":26},"Read, Glob, Grep, Write","[duration: 30m | 1h | 2h | 4h] [focus: memory | stability | balance | all]",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fsoak-test",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":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill soak-test",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill soak-test",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill soak-test","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\u002Fsoak-test\u002FSKILL.md",[],[49,56,61,68,75,82],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"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":57,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"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":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"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":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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",[],[]]