[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EZDCJS3PZS4X6HNB2KB0XS":3,"skill-same:01M7EZDCJS3PZS4X6HNB2KB0XS":68},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EZDCJS3PZS4X6HNB2KB0XS","dsh-upgrade-audit",null,"Audit external compatibility between two DSH (DeepSeek Harness) versions and detect reverts, producing an upgrade-report directory; compares git tags with a source checkout, or published npm packages without one. Use whenever the user asks to check\u002Fcompare\u002Faudit two DSH versions or whether upgrading is safe — e.g. \"more changes or reverts in dsh-vX -> dsh-vY\", \"compare the breaking changes\" — even with only two version numbers and no source location. Read-only outside the report directory; npm mode installs in isolation with --ignore-scripts.","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\u002Fdsh-upgrade-audit\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: dsh-upgrade-audit\ndescription: Audit external compatibility between two DSH (DeepSeek Harness) versions and detect reverts, producing an upgrade-report directory; compares git tags with a source checkout, or published npm packages without one. Use whenever the user asks to check\u002Fcompare\u002Faudit two DSH versions or whether upgrading is safe — e.g. \"more changes or reverts in dsh-vX -> dsh-vY\", \"compare the breaking changes\" — even with only two version numbers and no source location. Read-only outside the report directory; npm mode installs in isolation with --ignore-scripts.\n---\n\nEnglish | [简体中文](SKILL.zh-CN.md)\n\n# dsh-upgrade-audit\n\nAudit every change observable by consumers **outside the repository** between two DSH versions, and produce the set of reports the user expects. The fixed form of this problem: *relative to from, does to contain more changes or reverts?* — \"more changes\" means externally visible breakage (removed exports, renamed wire error codes, data formats refused on read); \"revert\" means behavior present in `from` deliberately withdrawn by a revert within the interval. Both need evidence: commit messages and subagent summaries are claims — only conclusions drawn after reading both trees (source files or published packages) count as evidence.\n\nExternal compatibility = everything observable by consumers outside the repository: the npm package public API (exports, types, signatures, dependency surface), the `dsh` CLI (commands, flags, profiles, config keys), the wire protocol (SDK JSON-RPC, remote gateway\u002FBFF, ACP, hooks), session data on disk (JSONL logs, SQLite stores and their version guards), the model-visible surface (tool names\u002Fschemas, system-prompt output), and the Python SDK's expectations. Internal refactors are background, not findings — aggregate and count them.\n\nNote: report language follows the user's language (see \"Output contract\" below); the existing sample report under `examples\u002F` is in English by historical convention.\n\n## Phase 0 — Parse input and choose a mode\n\nInput: two version identifiers (accepts `0.1.2-alpha.2`, `dsh-v0.1.2-alpha.2`, dist-tags `alpha`\u002F`latest`\u002F`next`). Choose the analysis mode by specificity, high to low:\n\n1. **Context path** — the user named a deepseek-harness checkout directory in the message. Verify: root `package.json` + `packages\u002F` + `AGENTS.md` all present.\n2. **`DSH_SOURCE_PATH` environment variable** — verify the same way. (Optional `DSH_NPM_REGISTRY` overrides the npm registry.)\n3. **CWD heuristic** — the current directory is itself a deepseek-harness checkout (marked the same way).\n4. **npm mode** — none of the above (the default path for third-party repos): download the published packages of the two versions for analysis.\n\nSource mode audits git tags; npm mode audits published artifacts. The audit core (recon surface, classification, verification, reporting) is shared; only the materialization and some evidence sources differ. Know npm mode's boundaries before choosing it: **the npm version set ≠ the git tag set** (e.g. `0.1.2-alpha.1` is tagged but was never published — the materialization script exits with the published list, so present the gap to the user instead of silently substituting a version pair); the CLI closure does not include every publishable package (the SQLite persistence backend is not a CLI dependency; the script installs it as a supplement package).\n\n## Output contract\n\nEverything lands in one directory: `tmp\u002F\u003CfromNorm>-to-\u003CtoNorm>\u002F` (normalization: strip `dsh-v`, strip dots in the prerelease segment — `dsh-v0.1.2-alpha.1` → `0.1.2alpha1`). Source mode creates it inside the checkout (gitignored); npm mode creates it inside the current project. If the target directory already exists it is most likely a previously hand-made report — stop and ask first; do not overwrite.\n\n| Artifact | Source mode | npm mode |\n|---|---|---|\n| `commits.txt`, `reverts.txt` | from git; reverts folded into CHANGELOG | from GitHub compare enrichment (none if private repo) |\n| `files.txt`, `diffstat.txt`, full `.diff` | git tree diff | `manifest-diff.txt` (per-package manifest diff) + `a\u002F`, `b\u002F` published package trees |\n| `CHANGELOG.md` | categorized by type, **must have a Reverts section** | generated when enrichment exists; otherwise omitted with an explicit note |\n| `UPGRADE-ADAPTATION.md` | audit report (same skeleton in both modes) | same; header records mode and version provenance |\n\nReport language follows the user's language ([examples\u002F](examples\u002F0.1.2alpha1-to-0.1.2alpha2\u002FUPGRADE-ADAPTATION.md) existing report is in English, a historical convention — not mandatory).\n\n## Phase 1 — Materialize the two trees\n\n**Source mode** — verify purity first; a merge base that is not `from` itself means base drift: stop and report, never diff against a moving baseline:\n\n```sh\ngit merge-base \u003Cfrom> \u003Cto>   # must equal \u003Cfrom>'s commit\nnode \u003Cskill-dir>\u002Fscripts\u002Fgen-artifacts.mjs \u003Cfrom> \u003Cto> tmp\u002F\u003Cpair>\n```\n\n**npm mode**:\n\n```sh\nnode \u003Cskill-dir>\u002Fscripts\u002Fmaterialize-npm.mjs \u003Cfrom> \u003Cto> tmp\u002F\u003Cpair>\n```\n\nThe script resolves both versions against the registry (missing → exit 1 with the published list — present the gap to the user), installs the `@deepseek-ai\u002Fdsh` dependency closure plus the SQLite supplement package into `a\u002F` and `b\u002F` with `--ignore-scripts`, produces `manifest-diff.txt` from per-package manifest diffs for every `@deepseek-ai\u002F*` package, and enriches from the public GitHub repository (`commits.txt`, `reverts.txt`) — so revert detection works even without a source checkout.\n\nSize the recon from the stats output: ≤40 non-merge commits → run the recon-surface checklist inline; 40–250 → merge 3–4 facades; more → all six facades. For density comparison, open the *previous* pair's `commits.txt` — the immediately preceding pair in **chronological order**, never just the newest directory in `tmp\u002F`.\n\n## Phase 2 — Establish shared facts first\n\nRun once and feed to every subagent, so they do not each re-derive them:\n\n- **Format guards** — source mode reads `SESSION_FORMAT_VERSION` on both tags (`packages\u002Fcore\u002Fsession\u002Fsrc\u002Ftypes.ts`) and the SQLite `SCHEMA_VERSION` (`packages\u002Fsession\u002Fsession-persistence-sqlite\u002Fsrc\u002Fschema.ts`); npm mode greps the same-named constants from the published `lib\u002F*.js` of `dsh-session` and the supplement package. A guard that jumps with no migration path = hard data breakage; put it at the front of the report.\n- **Revert list** — source mode: `git log --grep='[Rr]evert' \u003Cfrom>..\u003Cto>`; npm mode: the enriched `reverts.txt` (absent → revert *intent* is undetectable; say so explicitly and do only the from→to delta audit).\n- **Python SDK** — source mode: diff `python\u002F`; npm mode: outside the npm artifact scope, one sentence suffices.\n\n## Phase 3 — Parallel facade scans\n\nDispatch one read-only recon agent per facade in a parallel batch, each carrying the Phase 2 shared facts and the output contract from [references\u002Faudit-playbook.md](references\u002Faudit-playbook.md): sections **REMOVED** (first — candidate breakage\u002Freverts), **CHANGED** (before → after), **ADDED**, **RENAMED**; every entry carries package\u002Fpath, symbol or field, and an impact-surface class (SDK consumers \u002F CLI users \u002F config authors \u002F session data \u002F model-visible \u002F protocol peers \u002F web UI \u002F npm installers); end with a one-line verdict. The per-facade target path lists (per mode) are in the playbook.\n\n## Phase 4 — Verify before publishing\n\nRecon output is leads, not findings. Personally re-verify every REMOVED, revert, and wire claim: source mode with `git show \u003Ctag>:\u003Cpath>` \u002F `git ls-tree` against both tags; npm mode by reading both published trees (`a\u002Fnode_modules\u002F...` vs `b\u002Fnode_modules\u002F...`). This step has a real lesson: a recon agent once reported a package that already existed in alpha.1 as \"added in alpha.2\". Whatever cannot be verified is either marked `[INFERENCE]` or deleted.\n\n## Phase 5 — Write UPGRADE-ADAPTATION.md\n\nPer the [references\u002Faudit-playbook.md](references\u002Faudit-playbook.md) skeleton: header (range, stats, mode & provenance, source-mode purity note), **Verdict** (answer the comparative question directly), §1 reverts, breaking sections sorted by consumer impact (removals first, each annotating who breaks, with an **Adapt:** line), **Confirmed unchanged** (the parts where compatibility holds matter as much as the breaks), the boundary signature table `[API surface | from | to | changed?]`, and a numbered migration checklist. Full worked example at [examples\u002F0.1.2alpha1-to-0.1.2alpha2\u002F](examples\u002F0.1.2alpha1-to-0.1.2alpha2\u002FUPGRADE-ADAPTATION.md) (a real source-mode audit). Chat replies follow the user's language.\n\n## Guards\n\n- Read-only: source mode touches nothing outside `tmp\u002F\u003Cpair>\u002F`; npm mode writes only its own `tmp\u002F\u003Cpair>\u002F` and installs with `--ignore-scripts` into that directory — never install the dsh package into the host project's `node_modules`.\n- Prefer tree-level facts (published files, two-tag reads); do not trust narratives inferred from logs.\n- Aggregate internal irrelevant churn (tests, notes, i18n, styles) into a single count; do not itemize it.\n- npm mode records its limitations honestly: no enrichment → no git history; the CLI tarball ships only `lib\u002F` (config composition audited via each bundle package's `cordis.patch.yml` + manifest); Python SDK out of scope.\n- Do not fully fan out a 20-commit range; do not inline a 500-commit range. Misjudging the scale is the main reason audits go stale or shallow.\n\n## Relationship to plugin-upgrade\n\nThis skill produces **evidence of host-version compatibility** (report + boundary signature table); [plugin-upgrade](https:\u002F\u002Fgithub.com\u002Foh-my-dsh\u002Fdsh-plugin-upgrade-skill\u002Fblob\u002Fmain\u002Fskills\u002Fplugin-upgrade\u002F) consumes that evidence (version-change cards) to execute a single plugin's migration. Audit findings can feed a card's \"field notes\" directly; when adding cards to `plugin-upgrade`, cite this skill's report directory rather than restating from memory.\n","English | [简体中文](SKILL.zh-CN.md)\n\n# dsh-upgrade-audit\n\nAudit every change observable by consumers **outside the repository** between two DSH versions, and produce the set of reports the user expects. The fixed form of this problem: *relative to from, does to contain more changes or reverts?* — \"more changes\" means externally visible breakage (removed exports, renamed wire error codes, data formats refused on read); \"revert\" means behavior present in `from` deliberately withdrawn by a revert within the interval. Both need evidence: commit messages and subagent summaries are claims — only conclusions drawn after reading both trees (source files or published packages) count as evidence.\n\nExternal compatibility = everything observable by consumers outside the repository: the npm package public API (exports, types, signatures, dependency surface), the `dsh` CLI (commands, flags, profiles, config keys), the wire protocol (SDK JSON-RPC, remote gateway\u002FBFF, ACP, hooks), session data on disk (JSONL logs, SQLite stores and their version guards), the model-visible surface (tool names\u002Fschemas, system-prompt output), and the Python SDK's expectations. Internal refactors are background, not findings — aggregate and count them.\n\nNote: report language follows the user's language (see \"Output contract\" below); the existing sample report under `examples\u002F` is in English by historical convention.\n\n## Phase 0 — Parse input and choose a mode\n\nInput: two version identifiers (accepts `0.1.2-alpha.2`, `dsh-v0.1.2-alpha.2`, dist-tags `alpha`\u002F`latest`\u002F`next`). Choose the analysis mode by specificity, high to low:\n\n1. **Context path** — the user named a deepseek-harness checkout directory in the message. Verify: root `package.json` + `packages\u002F` + `AGENTS.md` all present.\n2. **`DSH_SOURCE_PATH` environment variable** — verify the same way. (Optional `DSH_NPM_REGISTRY` overrides the npm registry.)\n3. **CWD heuristic** — the current directory is itself a deepseek-harness checkout (marked the same way).\n4. **npm mode** — none of the above (the default path for third-party repos): download the published packages of the two versions for analysis.\n\nSource mode audits git tags; npm mode audits published artifacts. The audit core (recon surface, classification, verification, reporting) is shared; only the materialization and some evidence sources differ. Know npm mode's boundaries before choosing it: **the npm version set ≠ the git tag set** (e.g. `0.1.2-alpha.1` is tagged but was never published — the materialization script exits with the published list, so present the gap to the user instead of silently substituting a version pair); the CLI closure does not include every publishable package (the SQLite persistence backend is not a CLI dependency; the script installs it as a supplement package).\n\n## Output contract\n\nEverything lands in one directory: `tmp\u002F\u003CfromNorm>-to-\u003CtoNorm>\u002F` (normalization: strip `dsh-v`, strip dots in the prerelease segment — `dsh-v0.1.2-alpha.1` → `0.1.2alpha1`). Source mode creates it inside the checkout (gitignored); npm mode creates it inside the current project. If the target directory already exists it is most likely a previously hand-made report — stop and ask first; do not overwrite.\n\n| Artifact | Source mode | npm mode |\n|---|---|---|\n| `commits.txt`, `reverts.txt` | from git; reverts folded into CHANGELOG | from GitHub compare enrichment (none if private repo) |\n| `files.txt`, `diffstat.txt`, full `.diff` | git tree diff | `manifest-diff.txt` (per-package manifest diff) + `a\u002F`, `b\u002F` published package trees |\n| `CHANGELOG.md` | categorized by type, **must have a Reverts section** | generated when enrichment exists; otherwise omitted with an explicit note |\n| `UPGRADE-ADAPTATION.md` | audit report (same skeleton in both modes) | same; header records mode and version provenance |\n\nReport language follows the user's language ([examples\u002F](examples\u002F0.1.2alpha1-to-0.1.2alpha2\u002FUPGRADE-ADAPTATION.md) existing report is in English, a historical convention — not mandatory).\n\n## Phase 1 — Materialize the two trees\n\n**Source mode** — verify purity first; a merge base that is not `from` itself means base drift: stop and report, never diff against a moving baseline:\n\n```sh\ngit merge-base \u003Cfrom> \u003Cto>   # must equal \u003Cfrom>'s commit\nnode \u003Cskill-dir>\u002Fscripts\u002Fgen-artifacts.mjs \u003Cfrom> \u003Cto> tmp\u002F\u003Cpair>\n```\n\n**npm mode**:\n\n```sh\nnode \u003Cskill-dir>\u002Fscripts\u002Fmaterialize-npm.mjs \u003Cfrom> \u003Cto> tmp\u002F\u003Cpair>\n```\n\nThe script resolves both versions against the registry (missing → exit 1 with the published list — present the gap to the user), installs the `@deepseek-ai\u002Fdsh` dependency closure plus the SQLite supplement package into `a\u002F` and `b\u002F` with `--ignore-scripts`, produces `manifest-diff.txt` from per-package manifest diffs for every `@deepseek-ai\u002F*` package, and enriches from the public GitHub repository (`commits.txt`, `reverts.txt`) — so revert detection works even without a source checkout.\n\nSize the recon from the stats output: ≤40 non-merge commits → run the recon-surface checklist inline; 40–250 → merge 3–4 facades; more → all six facades. For density comparison, open the *previous* pair's `commits.txt` — the immediately preceding pair in **chronological order**, never just the newest directory in `tmp\u002F`.\n\n## Phase 2 — Establish shared facts first\n\nRun once and feed to every subagent, so they do not each re-derive them:\n\n- **Format guards** — source mode reads `SESSION_FORMAT_VERSION` on both tags (`packages\u002Fcore\u002Fsession\u002Fsrc\u002Ftypes.ts`) and the SQLite `SCHEMA_VERSION` (`packages\u002Fsession\u002Fsession-persistence-sqlite\u002Fsrc\u002Fschema.ts`); npm mode greps the same-named constants from the published `lib\u002F*.js` of `dsh-session` and the supplement package. A guard that jumps with no migration path = hard data breakage; put it at the front of the report.\n- **Revert list** — source mode: `git log --grep='[Rr]evert' \u003Cfrom>..\u003Cto>`; npm mode: the enriched `reverts.txt` (absent → revert *intent* is undetectable; say so explicitly and do only the from→to delta audit).\n- **Python SDK** — source mode: diff `python\u002F`; npm mode: outside the npm artifact scope, one sentence suffices.\n\n## Phase 3 — Parallel facade scans\n\nDispatch one read-only recon agent per facade in a parallel batch, each carrying the Phase 2 shared facts and the output contract from [references\u002Faudit-playbook.md](references\u002Faudit-playbook.md): sections **REMOVED** (first — candidate breakage\u002Freverts), **CHANGED** (before → after), **ADDED**, **RENAMED**; every entry carries package\u002Fpath, symbol or field, and an impact-surface class (SDK consumers \u002F CLI users \u002F config authors \u002F session data \u002F model-visible \u002F protocol peers \u002F web UI \u002F npm installers); end with a one-line verdict. The per-facade target path lists (per mode) are in the playbook.\n\n## Phase 4 — Verify before publishing\n\nRecon output is leads, not findings. Personally re-verify every REMOVED, revert, and wire claim: source mode with `git show \u003Ctag>:\u003Cpath>` \u002F `git ls-tree` against both tags; npm mode by reading both published trees (`a\u002Fnode_modules\u002F...` vs `b\u002Fnode_modules\u002F...`). This step has a real lesson: a recon agent once reported a package that already existed in alpha.1 as \"added in alpha.2\". Whatever cannot be verified is either marked `[INFERENCE]` or deleted.\n\n## Phase 5 — Write UPGRADE-ADAPTATION.md\n\nPer the [references\u002Faudit-playbook.md](references\u002Faudit-playbook.md) skeleton: header (range, stats, mode & provenance, source-mode purity note), **Verdict** (answer the comparative question directly), §1 reverts, breaking sections sorted by consumer impact (removals first, each annotating who breaks, with an **Adapt:** line), **Confirmed unchanged** (the parts where compatibility holds matter as much as the breaks), the boundary signature table `[API surface | from | to | changed?]`, and a numbered migration checklist. Full worked example at [examples\u002F0.1.2alpha1-to-0.1.2alpha2\u002F](examples\u002F0.1.2alpha1-to-0.1.2alpha2\u002FUPGRADE-ADAPTATION.md) (a real source-mode audit). Chat replies follow the user's language.\n\n## Guards\n\n- Read-only: source mode touches nothing outside `tmp\u002F\u003Cpair>\u002F`; npm mode writes only its own `tmp\u002F\u003Cpair>\u002F` and installs with `--ignore-scripts` into that directory — never install the dsh package into the host project's `node_modules`.\n- Prefer tree-level facts (published files, two-tag reads); do not trust narratives inferred from logs.\n- Aggregate internal irrelevant churn (tests, notes, i18n, styles) into a single count; do not itemize it.\n- npm mode records its limitations honestly: no enrichment → no git history; the CLI tarball ships only `lib\u002F` (config composition audited via each bundle package's `cordis.patch.yml` + manifest); Python SDK out of scope.\n- Do not fully fan out a 20-commit range; do not inline a 500-commit range. Misjudging the scale is the main reason audits go stale or shallow.\n\n## Relationship to plugin-upgrade\n\nThis skill produces **evidence of host-version compatibility** (report + boundary signature table); [plugin-upgrade](https:\u002F\u002Fgithub.com\u002Foh-my-dsh\u002Fdsh-plugin-upgrade-skill\u002Fblob\u002Fmain\u002Fskills\u002Fplugin-upgrade\u002F) consumes that evidence (version-change cards) to execute a single plugin's migration. Audit findings can feed a card's \"field notes\" directly; when adding cards to `plugin-upgrade`, cite this skill's report directory rather than restating from memory.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fdsh-upgrade-audit",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":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill dsh-upgrade-audit",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill dsh-upgrade-audit",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill dsh-upgrade-audit","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\u002Fdsh-upgrade-audit\u002FSKILL.md",true,[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"evals\u002Fevals.json","REFERENCE","参考文档",2827,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fdsh-upgrade-audit\u002Fevals\u002Fevals.json",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"examples\u002F0.1.2alpha1-to-0.1.2alpha2\u002FREADME.md",991,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fdsh-upgrade-audit\u002Fexamples\u002F0.1.2alpha1-to-0.1.2alpha2\u002FREADME.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"examples\u002F0.1.2alpha1-to-0.1.2alpha2\u002FUPGRADE-ADAPTATION.md",18122,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fdsh-upgrade-audit\u002Fexamples\u002F0.1.2alpha1-to-0.1.2alpha2\u002FUPGRADE-ADAPTATION.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Faudit-playbook.md",8761,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fdsh-upgrade-audit\u002Freferences\u002Faudit-playbook.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"SKILL.zh-CN.md",8159,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fdsh-upgrade-audit\u002FSKILL.zh-CN.md",[69,76,81,88,95,102],{"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},"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":77,"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":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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",[],[]]