[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CP7ZX037EAHXM6HGQ68VQX":3,"skill-same:01M6CP7ZX037EAHXM6HGQ68VQX":60},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":45,"updatedAt":46,"install":47,"resources":59},"01M6CP7ZX037EAHXM6HGQ68VQX","dsh-translate-docs",null,"Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.","gccszs\u002FWorldSoul","gccszs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85680574?v=4","01M6CP73CSF9QGSTGE0NMMX8WV","cris_tofu","01M6CP73H2C65X28TS1NATXRZT",2,"MIT","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002F.agents\u002Fskills\u002Fdsh-translate-docs\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"docs","translate","translate docs","dsh translate docs","workflow","run","verification","harness","generated","deepseek harness","document","prose","translation","deepseek","2026-11-10 10:12:30",false,"---\nname: dsh-translate-docs\ndescription: Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.\ndisable-model-invocation: true\nuser-invocable: true\n---\n\n# Translating DeepSeek-Harness docs\n\n## Invocation boundary\n\nRun this extended workflow only when the user explicitly invokes `dsh-translate-docs` by name. Never select or load it for ordinary documentation work, from another skill, or from an inferred translation need; routine translation follows the one-shot, one-pass rule in [docs\u002FAGENTS.md](..\u002F..\u002F..\u002Fdocs\u002FAGENTS.md).\n\n## What this skill is\n\n**This skill is guidance, not a translation memory.** It is the workflow map for keeping `foo.md ↔ foo.zh.md` pairs consistent and natural in both languages. Both languages carry equal authority — a change is authored in either one, and that side is the source for that update. You are the translator: the rules below say what must hold, not how to phrase any particular sentence — phrasing judgment is yours, terminology is not.\n\n## Triage by change type — this decides everything else\n\n- **Update** (pair exists, one side edited): follow [the update path](#the-update-path-briefing-driven). It is briefing-driven and deliberately cheap: no guidance-corpus reading, no git archaeology, smallest counterpart edit. Never re-translate a whole document to apply an update — a minimal update preserves the reviewed phrasing of everything that didn't change; a re-translation throws that review away.\n- **New pair** (no counterpart yet): follow [the whole-document path](#the-whole-document-path-new-pairs).\n- **Deleted or renamed doc**: delete or rename the counterpart and the `.i18n.yaml` alongside it — the gate reports an incomplete pair otherwise.\n\nFrozen Agent Notes under `.agents\u002Fnotes\u002Farchived\u002F` are not translation work. Their complete triplets are sealed by the archive verifier; never update, re-record, or repair either side after archival.\n\n## The update path (briefing-driven)\n\nThe briefing-driven path matches guidance-corpus quality at a fraction of the cost; the [briefed-updates Agent Note](..\u002F..\u002Fnotes\u002Fimplemented\u002Fprocess\u002F2026-07-26-briefed-minimal-translation-updates.md) owns the benchmark evidence.\n\n1. **Generate the briefing**: `pnpm run gen-translation-brief \u003Cany file of the pair>` (no arguments briefs every out-of-sync pair). The briefing maps the change at the narrowest safely aligned granularity — changed Markdown units (paragraph, table row, list item, heading), then whole heading sections, then whole document — and contains the authored side's diff since the last confirmed-consistent state, each changed unit's last-confirmed source, current source, and current counterpart text (with line numbers), the terminology rows the change touches, first-occurrence movement notes, and a digest of the binding update rules.\n2. **Mechanical-only diff? `--apply` it.** When every change lies inside code fences that the pair shares byte-identically, the briefing says so; `pnpm run gen-translation-brief --apply \u003Cpair>` splices the edited fences into the counterpart and structure-validates the result before writing — no subagent, no hand-editing.\n3. **Prose diff? Delegate to a subagent, passing the briefing** (or the command to generate it). The briefing is the translator's whole working set — the subagent does not re-read the guidance corpus (the rules digest, terminology rows, and each changed unit's three-way context are inline) and does not re-derive the diff. It escalates to the whole-document path's sources of truth only when the briefing leaves a specific decision genuinely unanswerable — an unlisted term with no precedent in the surrounding text, or a whole-document briefing (`BOTH sides changed`, or neither units nor sections align), which always means reconciling by hand under [translation-rules.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Ftranslation-rules.md).\n4. **Smallest edit that covers the diff.** Preserve the reviewed phrasing of everything the diff does not touch, then verify the changed hunks clause by clause against the source: nothing added, nothing dropped, terminology per the inline rows, code spans verbatim.\n5. **Record and verify, scoped**: `pnpm run verify-translation-pairing --write \u003Cpair>` then `pnpm run verify-translation-pairing \u003Cpair>`. `--write` names exactly the pairs you confirmed — it refuses to run bare so a bulk re-record is always an explicit `--all`. The corpus-wide check still runs in `doc-sync`\u002FCI; do not run it per-update.\n\n## The whole-document path (new pairs)\n\nWhen translations need to be written from scratch, the orchestrating agent does not translate: spawn a subagent to do the translation work. The translator reads the sources of truth below first, then translates the whole file into the other language — section by section for long documents, keeping each section's structure locked to the source as you go rather than fixing structure at the end.\n\n### Sources of truth (read, don't re-summarize)\n\n- **[docs\u002Fi18n\u002FREADME.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002FREADME.md)** — the pairing contract: the three-file pair (`foo.md`, `foo.zh.md`, `foo.i18n.yaml`), the consistency record's both-side blob hashes, the language-switcher lines, scope, and exclusions.\n- **[docs\u002Fi18n\u002Ftranslation-rules.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Ftranslation-rules.md)** — how to translate: faithfulness, structure preservation, terminology discipline, typography (MUST\u002FSHOULD levels).\n- **[docs\u002Fi18n\u002Fterminology.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Fterminology.md)** — the terminology table, binding in both directions. Load it BEFORE translating, not when a term feels uncertain; the terms you don't notice are the ones that drift.\n- **[docs\u002Fi18n\u002Ftranslation-prompt.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Ftranslation-prompt.md)** — the automated pipeline's calibrated machine-consumed template. Agents using this skill do not render it; the terminology table is the only repository file the automated renderer injects, while this skill and `translation-rules.md` remain binding for agent-authored translations.\n- **[dsh-prose-standard](..\u002Fdsh-prose-standard\u002FSKILL.md)** — required prose coverage and editorial judgment. Apply it to both sides without adding or dropping source propositions.\n\n### Translate\n\n- **Pass 1 — write, don't transpose.** Read a semantic unit, then restate it as a native technical author in the nearest [style sample's](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Fstyle-samples.md) register. Preserve the required frame without forcing sentence-by-sentence correspondence.\n- **Pass 2 — verify against the source, clause by clause.** Fidelity is checked here, not written in: confirm nothing was added or dropped, every term follows the table, and each code span survived verbatim. Fix by rewriting the sentence natively, not by patching words into it.\n- **Read the completed counterpart alone.** After the source comparison, read the translated file without the source beside it and rewrite phrasing whose awkwardness only becomes visible in isolation.\n- Write only the final text to the file, never drafts or notes.\n- Every term in [terminology.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Fterminology.md) renders exactly as specified. For a Chinese target, use the Chinese and first-occurrence columns; an unlisted term needs a citable Chinese OSS\u002Fvendor precedent or stays English under 「待定术语」. For an English target, use the English column and an established English technical term; preserve an ambiguous source term with a short gloss and list it as pending. Never invent a rendering inline.\n- Code blocks are byte-identical across the pair, comments included. Repository-relative document links keep the same semantic target and exact query\u002Ffragment suffix: targets in the active bilingual corpus use `.md` on the English side and `.zh.md` on the Chinese side, a missing in-scope counterpart is an error, targets outside the corpus keep their authored path, and the switcher remains the cross-locale exception.\n- The pairing gate checks heading depths, fenced blocks, table row and column counts, list kinds, ordered-list starts, list item counts, link locale, and semantic targets. In Pass 2, manually verify list and table order, noncanonical list numbering, inline code, emphasis, meaning, terminology, and tone.\n\n## Find the work\n\n- `pnpm run verify-translation-pairing --list` prints every in-scope document as missing \u002F out-of-sync \u002F ok. Missing and out-of-sync rows are contract violations; the normal check rejects them.\n- `pnpm run gen-translation-brief` with no arguments prints the briefing for every out-of-sync pair.\n- In a PR that edits paired docs, the work list is the diff itself: every changed side of a pair needs its counterpart updated and the pair re-recorded in the same PR, and the gate goes red if you forget.\n\n## Finish the pair\n\n1. Switcher: `[English](foo.md) | 中文` immediately after the Chinese file's H1, `English | [中文](foo.zh.md)` after the English file's H1 — add both if this is a new pair, except that a generator-owned English source stays byte-identical to generator output and omits its switcher while the Chinese counterpart still links back.\n2. Record consistency: `pnpm run verify-translation-pairing --write \u003Cpair>` recomputes and records both sides' full blob hashes in `foo.i18n.yaml`. The yaml diff in your PR is the reviewable statement \"I confirmed these two say the same thing\" — only run it after you actually have.\n3. No manifest entry is needed for an ordinary document: every in-scope source requires a pair. Change [scripts\u002Ftranslation-pairing.manifest.json](..\u002F..\u002F..\u002Fscripts\u002Ftranslation-pairing.manifest.json) only when the owning policy documents a genuine generated, instructional, or bilingual-by-construction exclusion.\n4. Before the PR: the touched pairs are green under the scoped check; `pnpm run doc-sync` (which includes the corpus-wide pairing check plus `verify-md-wrap`\u002F`verify-md-links`) runs once at PR level per [dsh-pre-push-checks](..\u002Fdsh-pre-push-checks\u002FSKILL.md), not inside each translation task.\n5. Keep the PR reviewable: state which pairs are new versus minimally updated and list 「待定术语」 prominently.\n\n## How to respond to translation review\n\nFollow the [code-review reporting guidance](..\u002Fdsh-code-review\u002FSKILL.md#reporting-findings): evaluate each comment on its merits, and for terminology comments, remember the terminology table is the contract — apply a reviewer's rendering decision to [terminology.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Fterminology.md), not only to one file.\n","# Translating DeepSeek-Harness docs\n\n## Invocation boundary\n\nRun this extended workflow only when the user explicitly invokes `dsh-translate-docs` by name. Never select or load it for ordinary documentation work, from another skill, or from an inferred translation need; routine translation follows the one-shot, one-pass rule in [docs\u002FAGENTS.md](..\u002F..\u002F..\u002Fdocs\u002FAGENTS.md).\n\n## What this skill is\n\n**This skill is guidance, not a translation memory.** It is the workflow map for keeping `foo.md ↔ foo.zh.md` pairs consistent and natural in both languages. Both languages carry equal authority — a change is authored in either one, and that side is the source for that update. You are the translator: the rules below say what must hold, not how to phrase any particular sentence — phrasing judgment is yours, terminology is not.\n\n## Triage by change type — this decides everything else\n\n- **Update** (pair exists, one side edited): follow [the update path](#the-update-path-briefing-driven). It is briefing-driven and deliberately cheap: no guidance-corpus reading, no git archaeology, smallest counterpart edit. Never re-translate a whole document to apply an update — a minimal update preserves the reviewed phrasing of everything that didn't change; a re-translation throws that review away.\n- **New pair** (no counterpart yet): follow [the whole-document path](#the-whole-document-path-new-pairs).\n- **Deleted or renamed doc**: delete or rename the counterpart and the `.i18n.yaml` alongside it — the gate reports an incomplete pair otherwise.\n\nFrozen Agent Notes under `.agents\u002Fnotes\u002Farchived\u002F` are not translation work. Their complete triplets are sealed by the archive verifier; never update, re-record, or repair either side after archival.\n\n## The update path (briefing-driven)\n\nThe briefing-driven path matches guidance-corpus quality at a fraction of the cost; the [briefed-updates Agent Note](..\u002F..\u002Fnotes\u002Fimplemented\u002Fprocess\u002F2026-07-26-briefed-minimal-translation-updates.md) owns the benchmark evidence.\n\n1. **Generate the briefing**: `pnpm run gen-translation-brief \u003Cany file of the pair>` (no arguments briefs every out-of-sync pair). The briefing maps the change at the narrowest safely aligned granularity — changed Markdown units (paragraph, table row, list item, heading), then whole heading sections, then whole document — and contains the authored side's diff since the last confirmed-consistent state, each changed unit's last-confirmed source, current source, and current counterpart text (with line numbers), the terminology rows the change touches, first-occurrence movement notes, and a digest of the binding update rules.\n2. **Mechanical-only diff? `--apply` it.** When every change lies inside code fences that the pair shares byte-identically, the briefing says so; `pnpm run gen-translation-brief --apply \u003Cpair>` splices the edited fences into the counterpart and structure-validates the result before writing — no subagent, no hand-editing.\n3. **Prose diff? Delegate to a subagent, passing the briefing** (or the command to generate it). The briefing is the translator's whole working set — the subagent does not re-read the guidance corpus (the rules digest, terminology rows, and each changed unit's three-way context are inline) and does not re-derive the diff. It escalates to the whole-document path's sources of truth only when the briefing leaves a specific decision genuinely unanswerable — an unlisted term with no precedent in the surrounding text, or a whole-document briefing (`BOTH sides changed`, or neither units nor sections align), which always means reconciling by hand under [translation-rules.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Ftranslation-rules.md).\n4. **Smallest edit that covers the diff.** Preserve the reviewed phrasing of everything the diff does not touch, then verify the changed hunks clause by clause against the source: nothing added, nothing dropped, terminology per the inline rows, code spans verbatim.\n5. **Record and verify, scoped**: `pnpm run verify-translation-pairing --write \u003Cpair>` then `pnpm run verify-translation-pairing \u003Cpair>`. `--write` names exactly the pairs you confirmed — it refuses to run bare so a bulk re-record is always an explicit `--all`. The corpus-wide check still runs in `doc-sync`\u002FCI; do not run it per-update.\n\n## The whole-document path (new pairs)\n\nWhen translations need to be written from scratch, the orchestrating agent does not translate: spawn a subagent to do the translation work. The translator reads the sources of truth below first, then translates the whole file into the other language — section by section for long documents, keeping each section's structure locked to the source as you go rather than fixing structure at the end.\n\n### Sources of truth (read, don't re-summarize)\n\n- **[docs\u002Fi18n\u002FREADME.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002FREADME.md)** — the pairing contract: the three-file pair (`foo.md`, `foo.zh.md`, `foo.i18n.yaml`), the consistency record's both-side blob hashes, the language-switcher lines, scope, and exclusions.\n- **[docs\u002Fi18n\u002Ftranslation-rules.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Ftranslation-rules.md)** — how to translate: faithfulness, structure preservation, terminology discipline, typography (MUST\u002FSHOULD levels).\n- **[docs\u002Fi18n\u002Fterminology.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Fterminology.md)** — the terminology table, binding in both directions. Load it BEFORE translating, not when a term feels uncertain; the terms you don't notice are the ones that drift.\n- **[docs\u002Fi18n\u002Ftranslation-prompt.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Ftranslation-prompt.md)** — the automated pipeline's calibrated machine-consumed template. Agents using this skill do not render it; the terminology table is the only repository file the automated renderer injects, while this skill and `translation-rules.md` remain binding for agent-authored translations.\n- **[dsh-prose-standard](..\u002Fdsh-prose-standard\u002FSKILL.md)** — required prose coverage and editorial judgment. Apply it to both sides without adding or dropping source propositions.\n\n### Translate\n\n- **Pass 1 — write, don't transpose.** Read a semantic unit, then restate it as a native technical author in the nearest [style sample's](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Fstyle-samples.md) register. Preserve the required frame without forcing sentence-by-sentence correspondence.\n- **Pass 2 — verify against the source, clause by clause.** Fidelity is checked here, not written in: confirm nothing was added or dropped, every term follows the table, and each code span survived verbatim. Fix by rewriting the sentence natively, not by patching words into it.\n- **Read the completed counterpart alone.** After the source comparison, read the translated file without the source beside it and rewrite phrasing whose awkwardness only becomes visible in isolation.\n- Write only the final text to the file, never drafts or notes.\n- Every term in [terminology.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Fterminology.md) renders exactly as specified. For a Chinese target, use the Chinese and first-occurrence columns; an unlisted term needs a citable Chinese OSS\u002Fvendor precedent or stays English under 「待定术语」. For an English target, use the English column and an established English technical term; preserve an ambiguous source term with a short gloss and list it as pending. Never invent a rendering inline.\n- Code blocks are byte-identical across the pair, comments included. Repository-relative document links keep the same semantic target and exact query\u002Ffragment suffix: targets in the active bilingual corpus use `.md` on the English side and `.zh.md` on the Chinese side, a missing in-scope counterpart is an error, targets outside the corpus keep their authored path, and the switcher remains the cross-locale exception.\n- The pairing gate checks heading depths, fenced blocks, table row and column counts, list kinds, ordered-list starts, list item counts, link locale, and semantic targets. In Pass 2, manually verify list and table order, noncanonical list numbering, inline code, emphasis, meaning, terminology, and tone.\n\n## Find the work\n\n- `pnpm run verify-translation-pairing --list` prints every in-scope document as missing \u002F out-of-sync \u002F ok. Missing and out-of-sync rows are contract violations; the normal check rejects them.\n- `pnpm run gen-translation-brief` with no arguments prints the briefing for every out-of-sync pair.\n- In a PR that edits paired docs, the work list is the diff itself: every changed side of a pair needs its counterpart updated and the pair re-recorded in the same PR, and the gate goes red if you forget.\n\n## Finish the pair\n\n1. Switcher: `[English](foo.md) | 中文` immediately after the Chinese file's H1, `English | [中文](foo.zh.md)` after the English file's H1 — add both if this is a new pair, except that a generator-owned English source stays byte-identical to generator output and omits its switcher while the Chinese counterpart still links back.\n2. Record consistency: `pnpm run verify-translation-pairing --write \u003Cpair>` recomputes and records both sides' full blob hashes in `foo.i18n.yaml`. The yaml diff in your PR is the reviewable statement \"I confirmed these two say the same thing\" — only run it after you actually have.\n3. No manifest entry is needed for an ordinary document: every in-scope source requires a pair. Change [scripts\u002Ftranslation-pairing.manifest.json](..\u002F..\u002F..\u002Fscripts\u002Ftranslation-pairing.manifest.json) only when the owning policy documents a genuine generated, instructional, or bilingual-by-construction exclusion.\n4. Before the PR: the touched pairs are green under the scoped check; `pnpm run doc-sync` (which includes the corpus-wide pairing check plus `verify-md-wrap`\u002F`verify-md-links`) runs once at PR level per [dsh-pre-push-checks](..\u002Fdsh-pre-push-checks\u002FSKILL.md), not inside each translation task.\n5. Keep the PR reviewable: state which pairs are new versus minimally updated and list 「待定术语」 prominently.\n\n## How to respond to translation review\n\nFollow the [code-review reporting guidance](..\u002Fdsh-code-review\u002FSKILL.md#reporting-findings): evaluate each comment on its merits, and for terminology comments, remember the terminology table is the contract — apply a reviewer's rendering decision to [terminology.md](..\u002F..\u002F..\u002Fdocs\u002Fi18n\u002Fterminology.md), not only to one file.\n",{"name":5,"description":7,"user-invocable":38,"disable-model-invocation":38},true,"main","d682beee161da2963de0a1bc91d17efc54ea8689","worldsoul-harness\u002F.agents\u002Fskills\u002Fdsh-translate-docs",0,"https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul","https:\u002F\u002Fgithub.com\u002Fgccszs","Code is cheap! Show me your prompt.","2026-09-27 15:07:46",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":38},[49,52,55],{"tool":50,"command":51},"npx","npx skills add gccszs\u002FWorldSoul --skill dsh-translate-docs",{"tool":53,"command":54},"bunx","bunx skills add gccszs\u002FWorldSoul --skill dsh-translate-docs",{"tool":56,"command":57},"pnpm","pnpm dlx skills add gccszs\u002FWorldSoul --skill dsh-translate-docs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002F.agents\u002Fskills\u002Fdsh-translate-docs\u002FSKILL.md",[],[61,74,92,100,116,139],{"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":33},"01M6CP8JPZRGT3SEHGSV9AHG4H","user-only-skill","Prove model-disabled skills stay outside the model catalog.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.dsh\u002Fskills\u002Fuser-only-skill\u002FSKILL.md",[],[68,69,70,71,72,73],"user","only","user only skill","model catalog","model","catalog",{"skillNo":75,"name":76,"nameZh":6,"description":77,"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":85,"publishedAt":33},"01M6CP8H9P868EE1HX81BRXY0Y","snapshot-skill","Exercise project skill discovery and loading in snapshot tests.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.dsh\u002Fskills\u002Fsnapshot-skill\u002FSKILL.md",[80],{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[86,87,88,89,90,91],"snapshot skill","snapshot","discovery","exercise","project skill","skill discovery",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":33},"01M6CP8FWAC3866R4B6R8GZ04V","model-only-skill","Prove user-disabled skills remain available to the model.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.dsh\u002Fskills\u002Fmodel-only-skill\u002FSKILL.md",[],[72,69,99,68],"model only skill",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":33},"01M6CP8DE65MXX0KW3TMP2655R","editing-cordis-compositions","Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted but contributed nothing.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fpackages\u002Fpreset\u002Fagent-presets\u002Fpresets\u002Fcordis\u002Fskills\u002Fediting-cordis-compositions\u002FSKILL.md",[],[107,108,26,109,110,111,112,113,114,115],"editing cordis compositions","editing","Composition","session","use","but","writing","plugin","preset",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":33},"01M6CP8A0ACVBGHRR5M9X77KBG","cordis-plugin-development","Create, modify, debug, or extend dynamic Cordis Plugins, including Host Services and Events, Client Slot and theme UI, Package-private Client-to-Host calls, dynamic Tools, version updates, approval failures, and runtime diagnostics. Use this Skill to route a user request to the correct platform and Inspect Provider, then define, run, repair, or roll back the Plugin.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fpackages\u002Fpreset\u002Fagent-presets\u002Fpresets\u002Fcordis\u002Fskills\u002Fcordis-plugin-development\u002FSKILL.md",[],[123,124,114,125,126,127,128,24,129,130,131,132,133,68,134,111,135,136,137,138],"cordis plugin development","development","Tools","debug","diagnostics","create","package","plugins","ui","services","correct","approval","version","provider","back","route",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":33},"01M6CP88NJH71DR1W6MRQ6ZMN6","preview-tour","Inspect the bundled Preview workspace and its deterministic Session examples.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fpackages\u002Fexperimental\u002Fwebworker-runtime\u002Ftests\u002Ffixtures\u002Fvfs-example\u002Fworkspace\u002F.agents\u002Fskills\u002Fpreview-tour\u002FSKILL.md",[],[146,147,110,148,149],"preview tour","workspace","deterministic","examples"]