[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EP4EVJ20NQ3EJ9YA0AXYFE":3,"skill-same:01M7EP4EVJ20NQ3EJ9YA0AXYFE":67},{"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},"01M7EP4EVJ20NQ3EJ9YA0AXYFE","repo-development",null,"Guide Observal repository-wide setup, lint\u002Ftest selection, contributor policy, release\u002Fcompliance scripts, and PR readiness workflow.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002Fsub-skills\u002Frepo-development\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: repo-development\ndescription: \"Guide Observal repository-wide setup, lint\u002Ftest selection,\n  contributor policy, release\u002Fcompliance scripts, and PR readiness workflow.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Observal Repo Development Router\n\nUse this sub-skill when a task is about repository-wide contributor operations rather than one product layer: local setup, Make targets, choosing lint and test commands, pre-commit\u002FSPDX\u002Flicense policy, AI contribution policy, changelog and documentation updates, conventional commits, release\u002Fcompliance scripts, safe use of development scripts, or the final PR review checklist.\n\nDo **not** use this sub-skill as the primary guide for detailed implementation inside one layer. Route detailed Typer command work to `cli`, FastAPI\u002Fdata\u002Fmigration work to `server`, harness registry\u002Fadapters\u002Fhooks\u002Fparsers\u002Fsession delivery to `harness-telemetry`, and Vite\u002FReact\u002FTanStack Router frontend work to `web`. Use this sub-skill to coordinate cross-cutting checks and contributor obligations around those changes.\n\n## Route the request\n\n- First-time setup, local development loop, rebuild target choice, branch\u002Fcommit\u002FPR workflow, changelog\u002Fdocs obligations: read `references\u002Fdevelopment-workflow.md`.\n- Choosing focused tests, avoiding unnecessary Docker\u002FE2E runs, pytest patterns, ruff\u002Fpre-commit\u002FSPDX expectations: read `references\u002Ftesting-and-quality.md`.\n- Make target inventory, repository scripts, release preparation, license\u002FSBOM\u002FVEX\u002Fcompliance tooling, live-data seeders, and script safety levels: read `references\u002Frepo-scripts.md`.\n- Install\u002Fimport, CLI\u002FAPI, config, optional dependency, telemetry\u002Fharness, Playwright, release, migration, pre-commit, or workflow failures: read `references\u002Ftroubleshooting.md`.\n\n## Non-negotiable contributor rules\n\n1. Start from the smallest owning sub-skill for code changes, then return here for repository-wide checks.\n2. Keep tests hermetic by default. Docker is for the local stack, Playwright\u002FE2E, live integration scripts, and manual service validation; it is not required for normal Python unit tests.\n3. Any CLI command add\u002Fremove\u002Frename\u002Fflag change must update bundled CLI skill files and regenerate the auto-generated Observal command reference.\n4. Any user-facing behavior change needs a changelog entry under `[Unreleased]`; frontend UI changes also need screenshots in the PR body.\n5. New source files need SPDX copyright and Apache-2.0 license headers. Let hooks update committer copyright lines rather than hand-editing bulk headers unless doing a dedicated license repair.\n6. Follow Conventional Commits (`feat`, `fix`, `docs`, `refactor`, `test`, `build`, `ci`, `chore` with optional scope). Keep subject lines short, imperative, and without trailing periods.\n7. AI-assisted PRs are allowed only with accountable human direction, full human diff review, local execution of appropriate checks, and explicit AI tool\u002Fversion disclosure. Unattended autonomous submissions are not acceptable.\n8. Never commit private harness\u002Feditor directories or generated local worktrees such as `.claude\u002F`, `.kiro\u002F`, `.cursor\u002F`, `.gemini\u002F`, `.opencode\u002F`, `.copilot\u002F`, `.vscode\u002F`, `.worktrees\u002F`, or their companion instruction files.\n\n## Fast repo inspection\n\nFrom the repository root, run this bundled read-only helper before choosing a broad workflow:\n\n```bash\npython skills\u002Fdisco\u002Fobserval\u002Fsub-skills\u002Frepo-development\u002Fscripts\u002Finspect_observal_repo.py --repo-root . --pretty\n```\n\nExpected signal: JSON containing repository markers, package versions, Make targets, test layout counts, selected evidence-file summaries, and script summaries. The helper should not write files, call the network, invoke Docker, or expose absolute local checkout paths.\n\n## Default work loop\n\n1. Identify the owning implementation layer and the user-visible behavior being changed.\n2. Use the implementation owner for code design, then use this sub-skill to choose focused tests, docs\u002Fchangelog updates, and policy checks.\n3. Run the narrowest safe checks first, then broaden to `make test`, `make lint`, and `make check` when the diff is PR-ready or touches cross-cutting policy\u002Fbuild files.\n4. If a script can mutate files, call a preview\u002Fdry-run mode first when available and inspect the diff before committing.\n5. Before handoff, state what was tested, what was intentionally not tested, whether Docker\u002FE2E was needed, and any remaining policy or reviewer questions.\n","# Observal Repo Development Router\n\nUse this sub-skill when a task is about repository-wide contributor operations rather than one product layer: local setup, Make targets, choosing lint and test commands, pre-commit\u002FSPDX\u002Flicense policy, AI contribution policy, changelog and documentation updates, conventional commits, release\u002Fcompliance scripts, safe use of development scripts, or the final PR review checklist.\n\nDo **not** use this sub-skill as the primary guide for detailed implementation inside one layer. Route detailed Typer command work to `cli`, FastAPI\u002Fdata\u002Fmigration work to `server`, harness registry\u002Fadapters\u002Fhooks\u002Fparsers\u002Fsession delivery to `harness-telemetry`, and Vite\u002FReact\u002FTanStack Router frontend work to `web`. Use this sub-skill to coordinate cross-cutting checks and contributor obligations around those changes.\n\n## Route the request\n\n- First-time setup, local development loop, rebuild target choice, branch\u002Fcommit\u002FPR workflow, changelog\u002Fdocs obligations: read `references\u002Fdevelopment-workflow.md`.\n- Choosing focused tests, avoiding unnecessary Docker\u002FE2E runs, pytest patterns, ruff\u002Fpre-commit\u002FSPDX expectations: read `references\u002Ftesting-and-quality.md`.\n- Make target inventory, repository scripts, release preparation, license\u002FSBOM\u002FVEX\u002Fcompliance tooling, live-data seeders, and script safety levels: read `references\u002Frepo-scripts.md`.\n- Install\u002Fimport, CLI\u002FAPI, config, optional dependency, telemetry\u002Fharness, Playwright, release, migration, pre-commit, or workflow failures: read `references\u002Ftroubleshooting.md`.\n\n## Non-negotiable contributor rules\n\n1. Start from the smallest owning sub-skill for code changes, then return here for repository-wide checks.\n2. Keep tests hermetic by default. Docker is for the local stack, Playwright\u002FE2E, live integration scripts, and manual service validation; it is not required for normal Python unit tests.\n3. Any CLI command add\u002Fremove\u002Frename\u002Fflag change must update bundled CLI skill files and regenerate the auto-generated Observal command reference.\n4. Any user-facing behavior change needs a changelog entry under `[Unreleased]`; frontend UI changes also need screenshots in the PR body.\n5. New source files need SPDX copyright and Apache-2.0 license headers. Let hooks update committer copyright lines rather than hand-editing bulk headers unless doing a dedicated license repair.\n6. Follow Conventional Commits (`feat`, `fix`, `docs`, `refactor`, `test`, `build`, `ci`, `chore` with optional scope). Keep subject lines short, imperative, and without trailing periods.\n7. AI-assisted PRs are allowed only with accountable human direction, full human diff review, local execution of appropriate checks, and explicit AI tool\u002Fversion disclosure. Unattended autonomous submissions are not acceptable.\n8. Never commit private harness\u002Feditor directories or generated local worktrees such as `.claude\u002F`, `.kiro\u002F`, `.cursor\u002F`, `.gemini\u002F`, `.opencode\u002F`, `.copilot\u002F`, `.vscode\u002F`, `.worktrees\u002F`, or their companion instruction files.\n\n## Fast repo inspection\n\nFrom the repository root, run this bundled read-only helper before choosing a broad workflow:\n\n```bash\npython skills\u002Fdisco\u002Fobserval\u002Fsub-skills\u002Frepo-development\u002Fscripts\u002Finspect_observal_repo.py --repo-root . --pretty\n```\n\nExpected signal: JSON containing repository markers, package versions, Make targets, test layout counts, selected evidence-file summaries, and script summaries. The helper should not write files, call the network, invoke Docker, or expose absolute local checkout paths.\n\n## Default work loop\n\n1. Identify the owning implementation layer and the user-visible behavior being changed.\n2. Use the implementation owner for code design, then use this sub-skill to choose focused tests, docs\u002Fchangelog updates, and policy checks.\n3. Run the narrowest safe checks first, then broaden to `make test`, `make lint`, and `make check` when the diff is PR-ready or touches cross-cutting policy\u002Fbuild files.\n4. If a script can mutate files, call a preview\u002Fdry-run mode first when available and inspect the diff before committing.\n5. Before handoff, state what was tested, what was intentionally not tested, whether Docker\u002FE2E was needed, and any remaining policy or reviewer questions.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fobserval\u002Fsub-skills\u002Frepo-development",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 repo-development",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill repo-development",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill repo-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002Fsub-skills\u002Frepo-development\u002FSKILL.md",[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fdevelopment-workflow.md","REFERENCE","参考文档",10716,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002Fsub-skills\u002Frepo-development\u002Freferences\u002Fdevelopment-workflow.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Frepo-scripts.md",11093,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002Fsub-skills\u002Frepo-development\u002Freferences\u002Frepo-scripts.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Ftesting-and-quality.md",10406,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002Fsub-skills\u002Frepo-development\u002Freferences\u002Ftesting-and-quality.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Ftroubleshooting.md",12830,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002Fsub-skills\u002Frepo-development\u002Freferences\u002Ftroubleshooting.md",[68,77,82,89,96,103],{"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":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":76},"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.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":78,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":76},"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":76},"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":76},"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":76},"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":76},"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",[],[]]