[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F629ZVM3REXA52J4SSZ65C":3,"skill-same:01M7F629ZVM3REXA52J4SSZ65C":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},"01M7F629ZVM3REXA52J4SSZ65C","test-flakiness",null,"Detect non-deterministic (flaky) tests by reading CI run logs or test result history. Aggregates pass rates per test, identifies intermittent failures, recommends quarantine or fix, and maintains a flaky test registry. Best run during Polish phase or after multiple CI runs.","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\u002Ftest-flakiness\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: test-flakiness\ndescription: \"Detect non-deterministic (flaky) tests by reading CI run logs or test result history. Aggregates pass rates per test, identifies intermittent failures, recommends quarantine or fix, and maintains a flaky test registry. Best run during Polish phase or after multiple CI runs.\"\nargument-hint: \"[ci-log-path | scan | registry]\"\nuser-invocable: true\nallowed-tools: Read, Glob, Grep, Write, Edit, Bash\n---\n\n# Test Flakiness Detection\n\nA flaky test is one that sometimes passes and sometimes fails without any code\nchange. Flaky tests are worse than no tests in some ways — they train the team\nto ignore red CI runs, masking genuine failures. This skill identifies them,\nexplains likely causes, and recommends whether to quarantine or fix each one.\n\n**Output:** Updated `tests\u002Fregression-suite.md` quarantine section + optional\n`production\u002Fqa\u002Fflakiness-report-[date].md`\n\n**When to run:**\n- Polish phase (tests have had many runs; statistical signal is reliable)\n- When developers start dismissing CI failures as \"probably flaky\"\n- After `\u002Fregression-suite` identifies quarantined tests that need diagnosis\n\n---\n\n## 1. Parse Arguments\n\n**Modes:**\n- `\u002Ftest-flakiness [ci-log-path]` — analyse a specific CI run log file\n- `\u002Ftest-flakiness scan` — scan all available CI logs in `.github\u002F` or\n  standard log output directories\n- `\u002Ftest-flakiness registry` — read existing regression-suite.md quarantine\n  section and provide remediation guidance for already-known flaky tests\n- No argument — auto-detect: run `scan` if CI logs are accessible, else\n  `registry`\n\n---\n\n## 2. Locate CI Log Data\n\n### Option A — GitHub Actions (preferred)\n\nCheck for test result artifacts:\n```bash\nls -t .github\u002F 2>\u002Fdev\u002Fnull\nls -t test-results\u002F 2>\u002Fdev\u002Fnull\n```\n\nFor Godot projects: GdUnit4 outputs XML results compatible with JUnit format.\nCheck `test-results\u002F` for `.xml` files.\n\nFor Unity projects: game-ci test runner outputs NUnit XML to `test-results\u002F`\nby default.\n\nFor Unreal projects: automation logs go to `Saved\u002FLogs\u002F`. Grep for\n`Result: Success` and `Result: Fail` patterns.\n\n### Option B — Local log files\n\nIf a path argument is provided, read that file directly.\n\n### Option C — No log data available\n\nIf no logs found:\n> \"No CI log data found. To detect flaky tests, this skill needs test result\n> history from multiple runs. Options:\n> 1. Run the test suite at least 3 times and collect the output logs\n> 2. Check CI pipeline output and save a log to `test-results\u002F`\n> 3. Run `\u002Ftest-flakiness registry` to review tests already flagged as flaky\n>    in `tests\u002Fregression-suite.md`\"\n\nStop and ask the user which option to pursue.\n\n---\n\n## 3. Parse Test Results\n\nFor each CI log or result file found, parse:\n\n**JUnit XML format** (GdUnit4 \u002F Unity):\n- Grep for `\u003Ctestcase name=` to get test names\n- Grep for `\u003Cfailure` or `\u003Cerror` to identify failures\n- Parse `classname` and `name` attributes for full test identifiers\n\n**Plain text logs**:\n- Grep for pass\u002Ffail patterns:\n  - Godot: `PASSED` \u002F `FAILED` adjacent to test names\n  - Unreal: `Result: Success` \u002F `Result: Fail`\n  - Unity: `Test passed` \u002F `Test failed`\n\nBuild a table: `test_id → [run1_result, run2_result, run3_result, ...]`\n\n---\n\n## 4. Identify Flaky Tests\n\nA test is **flaky** if it appears in the result history with both PASS and\nFAIL outcomes across runs with no code changes between them.\n\nFlakiness thresholds:\n- **High flakiness**: Fails in >25% of runs — quarantine immediately\n- **Moderate flakiness**: Fails in 5–25% of runs — investigate and fix soon\n- **Low\u002Fsuspected flakiness**: Fails in 1–5% of runs — monitor; may be\n  genuinely rare failure\n\nFor each flaky test, classify the likely cause:\n\n### Cause classification\n\n| Cause | Symptoms | Fix direction |\n|-------|----------|---------------|\n| **Timing \u002F async** | Fails after awaiting signals or timers; pass rate correlates with system load | Add explicit await\u002Fsynchronisation; avoid time-based delays |\n| **Order dependency** | Fails when run after specific other tests; passes in isolation | Add proper setup\u002Fteardown; ensure test isolation |\n| **Random seed** | Fails intermittently with no pattern; involves RNG | Pass explicit seed; don't use `randf()` in tests |\n| **Resource leak** | Fails more often later in a test run | Fix cleanup in teardown; check orphan nodes (Godot) or object disposal (Unity) |\n| **External state** | Fails when a file, scene, or global exists from a prior test | Isolate test from file system; use in-memory mocks |\n| **Floating point** | Fails on comparisons like `== 0.5` | Use epsilon comparison (`is_equal_approx`, `Assert.AreApproximately`) |\n| **Scene\u002Fprefab load race** | Fails when scenes are not yet ready | Await one frame after instantiation; use `await get_tree().process_frame` |\n\nUse Grep to check the test file for timing calls, randf, global state access,\nor equality comparisons on floats to narrow down the cause.\n\n---\n\n## 5. Recommend Action\n\nFor each flaky test:\n\n**Quarantine (High flakiness):**\n> \"Quarantine this test immediately. Disable it in CI by adding\n> `@pytest.mark.skip` \u002F `[Ignore]` \u002F `GdUnitSkip` annotation. Log it in\n> `tests\u002Fregression-suite.md` quarantine section. The test is now opt-in only.\n> Fix the root cause before removing quarantine.\"\n\n**Investigate and fix soon (Moderate):**\n> \"This test is intermittently unreliable. Root cause appears to be [cause].\n> Suggested fix: [specific fix based on cause classification]. Do not quarantine\n> yet — fix the test directly.\"\n\n**Monitor (Low\u002Fsuspected):**\n> \"This test shows suspected flakiness. Collect more run data before\n> quarantining. Note it as 'suspected' in the regression suite.\"\n\n---\n\n## 6. Generate Reports\n\n### In-conversation summary\n\n```\n## Flakiness Detection Results\n\n**Runs analysed**: [N]\n**Tests tracked**: [N]\n\n### Flaky Tests Found\n\n| Test | System | Fail Rate | Likely Cause | Recommendation |\n|------|--------|-----------|--------------|----------------|\n| [test_name] | [system] | [N]% | Timing | Quarantine + fix async |\n| [test_name] | [system] | [N]% | Float comparison | Fix: use epsilon compare |\n| [test_name] | [system] | [N]% | Order dependency | Investigate teardown |\n\n### Clean Tests (no flakiness detected)\n\n[N] tests ran across [N] runs with consistent results — no flakiness detected.\n\n### Data Limitations\n\n[Note if fewer than 5 runs were available — fewer runs = less statistical confidence]\n```\n\n---\n\n## 7. Update Regression Suite + Optional Report File\n\nAsk: \"May I update the quarantine section of `tests\u002Fregression-suite.md`\nwith the flaky tests found?\"\n\nIf yes: use `Edit` to append entries to the Quarantined Tests table.\nNever remove existing quarantine entries — only add new ones.\n\nAsk (separately): \"May I write a full flakiness report to\n`production\u002Fqa\u002Fflakiness-report-[date].md`?\"\n\nThe full report includes per-test analysis with cause details and\nengine-specific fix snippets.\n\nAfter writing:\n\n- For each quarantined test: \"Add the engine-specific skip annotation to\n  disable this test in CI. Re-enable after the root cause is fixed.\"\n- For fix-eligible tests: \"The fix for [test] is straightforward —\n  change the equality comparison on line [N] to use `is_equal_approx`.\"\n- Summary: \"Once all quarantine annotations are applied, CI should run green.\n  Schedule fix work for the [N] quarantined tests before the release gate.\"\n\n---\n\n## Collaborative Protocol\n\n- **Never delete test files** — quarantine means annotate + list, not remove\n- **Statistical confidence matters** — with \u003C 3 runs, flag findings as\n  \"suspected\" not \"confirmed\"; ask if more run data is available\n- **Fix is always the goal** — quarantine is temporary; surface the fix\n  direction even when recommending quarantine\n- **Ask before writing** — both the regression-suite update and the report\n  file require explicit approval. On write: Verdict: **COMPLETE** — flakiness report written. On decline: Verdict: **BLOCKED** — user declined write.\n- **Flakiness in CI is a team problem** — surface the list and recommended\n  actions clearly; do not just silently quarantine without the team knowing\n","# Test Flakiness Detection\n\nA flaky test is one that sometimes passes and sometimes fails without any code\nchange. Flaky tests are worse than no tests in some ways — they train the team\nto ignore red CI runs, masking genuine failures. This skill identifies them,\nexplains likely causes, and recommends whether to quarantine or fix each one.\n\n**Output:** Updated `tests\u002Fregression-suite.md` quarantine section + optional\n`production\u002Fqa\u002Fflakiness-report-[date].md`\n\n**When to run:**\n- Polish phase (tests have had many runs; statistical signal is reliable)\n- When developers start dismissing CI failures as \"probably flaky\"\n- After `\u002Fregression-suite` identifies quarantined tests that need diagnosis\n\n---\n\n## 1. Parse Arguments\n\n**Modes:**\n- `\u002Ftest-flakiness [ci-log-path]` — analyse a specific CI run log file\n- `\u002Ftest-flakiness scan` — scan all available CI logs in `.github\u002F` or\n  standard log output directories\n- `\u002Ftest-flakiness registry` — read existing regression-suite.md quarantine\n  section and provide remediation guidance for already-known flaky tests\n- No argument — auto-detect: run `scan` if CI logs are accessible, else\n  `registry`\n\n---\n\n## 2. Locate CI Log Data\n\n### Option A — GitHub Actions (preferred)\n\nCheck for test result artifacts:\n```bash\nls -t .github\u002F 2>\u002Fdev\u002Fnull\nls -t test-results\u002F 2>\u002Fdev\u002Fnull\n```\n\nFor Godot projects: GdUnit4 outputs XML results compatible with JUnit format.\nCheck `test-results\u002F` for `.xml` files.\n\nFor Unity projects: game-ci test runner outputs NUnit XML to `test-results\u002F`\nby default.\n\nFor Unreal projects: automation logs go to `Saved\u002FLogs\u002F`. Grep for\n`Result: Success` and `Result: Fail` patterns.\n\n### Option B — Local log files\n\nIf a path argument is provided, read that file directly.\n\n### Option C — No log data available\n\nIf no logs found:\n> \"No CI log data found. To detect flaky tests, this skill needs test result\n> history from multiple runs. Options:\n> 1. Run the test suite at least 3 times and collect the output logs\n> 2. Check CI pipeline output and save a log to `test-results\u002F`\n> 3. Run `\u002Ftest-flakiness registry` to review tests already flagged as flaky\n>    in `tests\u002Fregression-suite.md`\"\n\nStop and ask the user which option to pursue.\n\n---\n\n## 3. Parse Test Results\n\nFor each CI log or result file found, parse:\n\n**JUnit XML format** (GdUnit4 \u002F Unity):\n- Grep for `\u003Ctestcase name=` to get test names\n- Grep for `\u003Cfailure` or `\u003Cerror` to identify failures\n- Parse `classname` and `name` attributes for full test identifiers\n\n**Plain text logs**:\n- Grep for pass\u002Ffail patterns:\n  - Godot: `PASSED` \u002F `FAILED` adjacent to test names\n  - Unreal: `Result: Success` \u002F `Result: Fail`\n  - Unity: `Test passed` \u002F `Test failed`\n\nBuild a table: `test_id → [run1_result, run2_result, run3_result, ...]`\n\n---\n\n## 4. Identify Flaky Tests\n\nA test is **flaky** if it appears in the result history with both PASS and\nFAIL outcomes across runs with no code changes between them.\n\nFlakiness thresholds:\n- **High flakiness**: Fails in >25% of runs — quarantine immediately\n- **Moderate flakiness**: Fails in 5–25% of runs — investigate and fix soon\n- **Low\u002Fsuspected flakiness**: Fails in 1–5% of runs — monitor; may be\n  genuinely rare failure\n\nFor each flaky test, classify the likely cause:\n\n### Cause classification\n\n| Cause | Symptoms | Fix direction |\n|-------|----------|---------------|\n| **Timing \u002F async** | Fails after awaiting signals or timers; pass rate correlates with system load | Add explicit await\u002Fsynchronisation; avoid time-based delays |\n| **Order dependency** | Fails when run after specific other tests; passes in isolation | Add proper setup\u002Fteardown; ensure test isolation |\n| **Random seed** | Fails intermittently with no pattern; involves RNG | Pass explicit seed; don't use `randf()` in tests |\n| **Resource leak** | Fails more often later in a test run | Fix cleanup in teardown; check orphan nodes (Godot) or object disposal (Unity) |\n| **External state** | Fails when a file, scene, or global exists from a prior test | Isolate test from file system; use in-memory mocks |\n| **Floating point** | Fails on comparisons like `== 0.5` | Use epsilon comparison (`is_equal_approx`, `Assert.AreApproximately`) |\n| **Scene\u002Fprefab load race** | Fails when scenes are not yet ready | Await one frame after instantiation; use `await get_tree().process_frame` |\n\nUse Grep to check the test file for timing calls, randf, global state access,\nor equality comparisons on floats to narrow down the cause.\n\n---\n\n## 5. Recommend Action\n\nFor each flaky test:\n\n**Quarantine (High flakiness):**\n> \"Quarantine this test immediately. Disable it in CI by adding\n> `@pytest.mark.skip` \u002F `[Ignore]` \u002F `GdUnitSkip` annotation. Log it in\n> `tests\u002Fregression-suite.md` quarantine section. The test is now opt-in only.\n> Fix the root cause before removing quarantine.\"\n\n**Investigate and fix soon (Moderate):**\n> \"This test is intermittently unreliable. Root cause appears to be [cause].\n> Suggested fix: [specific fix based on cause classification]. Do not quarantine\n> yet — fix the test directly.\"\n\n**Monitor (Low\u002Fsuspected):**\n> \"This test shows suspected flakiness. Collect more run data before\n> quarantining. Note it as 'suspected' in the regression suite.\"\n\n---\n\n## 6. Generate Reports\n\n### In-conversation summary\n\n```\n## Flakiness Detection Results\n\n**Runs analysed**: [N]\n**Tests tracked**: [N]\n\n### Flaky Tests Found\n\n| Test | System | Fail Rate | Likely Cause | Recommendation |\n|------|--------|-----------|--------------|----------------|\n| [test_name] | [system] | [N]% | Timing | Quarantine + fix async |\n| [test_name] | [system] | [N]% | Float comparison | Fix: use epsilon compare |\n| [test_name] | [system] | [N]% | Order dependency | Investigate teardown |\n\n### Clean Tests (no flakiness detected)\n\n[N] tests ran across [N] runs with consistent results — no flakiness detected.\n\n### Data Limitations\n\n[Note if fewer than 5 runs were available — fewer runs = less statistical confidence]\n```\n\n---\n\n## 7. Update Regression Suite + Optional Report File\n\nAsk: \"May I update the quarantine section of `tests\u002Fregression-suite.md`\nwith the flaky tests found?\"\n\nIf yes: use `Edit` to append entries to the Quarantined Tests table.\nNever remove existing quarantine entries — only add new ones.\n\nAsk (separately): \"May I write a full flakiness report to\n`production\u002Fqa\u002Fflakiness-report-[date].md`?\"\n\nThe full report includes per-test analysis with cause details and\nengine-specific fix snippets.\n\nAfter writing:\n\n- For each quarantined test: \"Add the engine-specific skip annotation to\n  disable this test in CI. Re-enable after the root cause is fixed.\"\n- For fix-eligible tests: \"The fix for [test] is straightforward —\n  change the equality comparison on line [N] to use `is_equal_approx`.\"\n- Summary: \"Once all quarantine annotations are applied, CI should run green.\n  Schedule fix work for the [N] quarantined tests before the release gate.\"\n\n---\n\n## Collaborative Protocol\n\n- **Never delete test files** — quarantine means annotate + list, not remove\n- **Statistical confidence matters** — with \u003C 3 runs, flag findings as\n  \"suspected\" not \"confirmed\"; ask if more run data is available\n- **Fix is always the goal** — quarantine is temporary; surface the fix\n  direction even when recommending quarantine\n- **Ask before writing** — both the regression-suite update and the report\n  file require explicit approval. On write: Verdict: **COMPLETE** — flakiness report written. On decline: Verdict: **BLOCKED** — user declined write.\n- **Flakiness in CI is a team problem** — surface the list and recommended\n  actions clearly; do not just silently quarantine without the team knowing\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25,"user-invocable":26},"Read, Glob, Grep, Write, Edit, Bash","[ci-log-path | scan | registry]",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Ftest-flakiness",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 test-flakiness",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill test-flakiness",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill test-flakiness","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\u002Ftest-flakiness\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",[],[]]