[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AS694QJ1ACZTR3YCEZ7J6H":3,"skill-same:01M7AS694QJ1ACZTR3YCEZ7J6H":45},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7AS694QJ1ACZTR3YCEZ7J6H","editing-cordis-compositions",null,"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.","Qiuzixiao\u002Fdeepseek-harness-desktop","Qiuzixiao","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F120417469?v=4","01M7AS3GVP6K6CY963D6YR3613","Jar maker","01M7AS3GWP71XA2MZRRBM42Y41",0,"MIT","https:\u002F\u002Fgithub.com\u002FQiuzixiao\u002Fdeepseek-harness-desktop\u002Fblob\u002Fmaster\u002Fdsh-plugin-desktop\u002Fresources\u002Fagent-presets\u002Fcordis\u002Fskills\u002Fediting-cordis-compositions\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: editing-cordis-compositions\ndescription: 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.\n---\n\n# Editing Cordis compositions\n\nEvery capability in this harness is a plugin row in a `cordis.yml`. There is no separate configuration language: changing what an agent can do means changing which rows are composed for it.\n\n## Off-limits\n\n**Never edit, delete, or overwrite a preset that ships with the deployment** — the `agent-presets` directory beside the deployment's own config, which supplies `standard`, `code`, `minimal`, and `cordis`. Never escalate the sandbox to reach it, even when a change there looks quicker. An upgrade overwrites that install, and corrupting `cordis` disables preset authoring itself. Reading a shipped composition is the intended way to start; writing to one is not, and neither is editing the host composition to work around a preset limitation.\n\nTo change what a shipped preset does, copy it and edit the copy. Locally authored presets under the user root are yours to create, edit, and delete.\n\n## Decide the plane first\n\nTwo planes, and the choice is not about how \"agent-related\" something feels — it is about whether the thing must be shared.\n\n**Host composition.** The registries themselves (`tools`, `systemPrompt`, `agents`, `agent-loop`, `sessions`), anything crossing sessions (persistence, session query, storage, settings, credentials, telemetry), the sandbox and approval stack, the model route, and the subagent registry with its spawn\u002Ffork backends. One instance for the process.\n\n**Agent preset.** What one session contributes to those registries: its tool plugins, its persona and prompt sections, its compaction policy. One instance per session, mounted under that session's scope and unwound with it.\n\n**A service with a consumer outside the agent plane cannot move into a preset.** `subagents` is the worked example: the registry answers cross-session queries for the host api-proxy, so a per-session copy both starves that host row — it waits forever for a service nothing provides — and collides on the second session, since a provider name registers once. The preset contributes the delegation *tools*; the registry and its backends stay host-side.\n\nA preset is a directory holding one `agent.cordis.yml`, optionally beside a `preset.yml` carrying display metadata — `name` and `description` (and, for shipped presets, a roster `order`). Write the metadata too: a preset without it shows up in every picker as its bare directory name.\n\nLocally authored presets live one directory per preset under `${DSH_HOME:-$HOME\u002F.zenwit}\u002F.agent-presets\u002F`, and the shipped set sits beside the deployment's own config. Use those when the user asks where to look. A deployment can configure other roots, so the path you read or edit comes from `list()` or `resolve()` — which is also where `copy()` reports what it just created.\n\n## The roster service\n\n`ctx.agentPresets` owns discovery, authoring, and mounting. You reach it by mounting a temporary plugin that injects it and registers a tool for yourself — `cordis_mount` returns only the mount acknowledgement, so a registered tool is how a service answer gets back to you, and it becomes callable on your next step.\n\nRead `cordis_inspect what:\"api\" name:\"agentPresets\"` for the current signatures before writing the code. What this skill relies on:\n\n- `list()` — every preset with its `id`, `trust` (`system` for the shipped set, `user` for authored ones), and the absolute `path` of its composition file. This is how you locate any composition without knowing the install layout; the directory is that path's parent.\n- `read(id)` — one preset's composition text, without a file tool or a path.\n- `copy(from, id, name?)` — the only authoring write (see below).\n- `standingKeyFor(id)` — mount-validate one preset (see below).\n\n```js\nreturn {\n  name: 'preset-tools',\n  inject: ['agentPresets', 'tools'],\n  apply(ctx) {\n    harness.registerTool(ctx, harness.defineTool({\n      name: 'preset_check',\n      description: 'Mount-validate one preset by id.',\n      parameters: { id: { type: 'string', required: true } },\n      output: { schema: { type: 'string' }, render(_a, v) { return [{ type: 'text', text: v }] } },\n      async execute(args) {\n        try {\n          await ctx.agentPresets.standingKeyFor(args.id)\n          return 'mounted OK'\n        } catch (error) {\n          return error.message\n        }\n      },\n    }))\n  },\n}\n```\n\nUnmount the plugin with `cordis_unmount` when you are done; it is a probe, not a capability to leave behind.\n\n## Authoring a preset\n\n1. **Start from a copy.** `copy(from, id, name)` copies a whole preset directory into the user root — composition, metadata, skill directories, assets. It validates the id against `[a-z0-9][a-z0-9-]*` (it becomes the directory name, so no leading hyphen), refuses an id any root already supplies, rolls a failed copy back, and rewrites the copy's `preset.yml` to keep the source's description while dropping its name and roster `order`. Prefer it over a shell copy: it needs no sandbox escalation, it lands the copy in whichever root this deployment made writable, and the copy is exactly as loadable as its source. `resolve(id)` then names the file it created — that path, not a guessed one, is what the following edits target. `standard` is the full coding agent and the usual source.\n2. **Expect the file sandbox on every edit after the copy.** The user preset root lies outside the session workspace, so under the default `workspace-write` policy the first write there is denied. Only writes are: reading any composition by absolute path needs no escalation. Retry that exact command once with `sandbox_permissions` escalation and a short justification — the user sees and approves it. Batch your writes (one heredoc per file) rather than escalating many small commands. `copy()` itself runs host-side and needs none of this; the edits do.\n3. **Write the copy's `description`** in `preset.yml`, and its `name` if you passed none to `copy()`.\n4. **Edit `agent.cordis.yml`** row by row, keeping the plane rule and the realm rule.\n5. **Mount-validate the result**, then hand off to the user for a real session — both under *Verifying a change*.\n\nA composition written from scratch usually forgets a group realm or a consumer row; a copy starts loadable.\n\n## The rule that catches people\n\n**A row that publishes a service may not sit loose in a preset.** Registering a service without an isolate realm puts it in the process-global realm, so the second session mounting that preset collides with the first. The mount rejects it rather than letting the collision surface later.\n\nWhether a row publishes a service is not visible from its name, and package READMEs are absent from an installed deployment. Read it off the live runtime instead: `cordis_inspect what:\"services\"` lists every service with the fiber that owns it, so a service attributed to a fiber other than the row you are adding is one that row consumes rather than provides. For a row not in your current composition, mount-validate and read the rejection — it names the offending service.\n\nWhen a preset genuinely owns a service, wrap the provider **and every consumer that reaches it** in one group carrying an `isolate` realm. The shipped `standard` composition does this for `workflows`, which nothing outside an agent reads — its `delegation` group, with the delegation tools omitted here:\n\n```yaml\n- id: delegation\n  name: cordis:group\n  group: true\n  isolate:\n    workflows: true\n  config:\n    - id: workflow-worker-thread\n      name: '@deepseek-ai\u002Fdsh-workflow-worker-thread'\n      config:\n        provider: spawn\n    - id: tool-workflow\n      name: '@deepseek-ai\u002Fdsh-tool-workflow'\n```\n\n`true` means a realm private to each mounting session. A string label instead joins subtrees into one shared realm; `provide()` still throws on the second registration under that symbol, so a label does not pool instances and is not what a preset needs.\n\nA consumer left outside the group resolves the host's registry, which the preset did not populate, and then contributes nothing. Mount-validation catches that as a row that never activated.\n\nRealms are for services a preset owns, not for every group. A host capability the preset only consumes must stay outside a realm, or the row cannot resolve it: `tool-bash`, `tool-jobs`, and `tool-goal` publish nothing and sit loose in `standard`, which explains in comments which host instance each one resolves and why a realm would break it. Wrapping a consumer row in a realm of its own is the same error as leaving one outside its provider's realm.\n\n## Verifying a change\n\n**`standingKeyFor(id)` is the check.** It composes the preset's plugin subtree for real — the same mount a session start performs, minus the agent — and rejects the four ways a composition fails:\n\n- a row whose package does not resolve (`Cannot find package …`);\n- a row whose config is invalid (`invalid config: $.\u003Cfield> missing required value`);\n- a row that never activated (`N row(s) did not activate: \u003Cid>: waiting for \u003Cservice>`);\n- a service published into the root realm, which arrives as one of two messages. A name the host does not supply lands in the root realm and the mount audit rejects it: `row(s) published process-global service(s) [\u003Cname>]; a preset service must sit behind an isolate realm or move to the host composition` — this is the shape a preset's own forgotten realm takes. A name the host already supplies collides before the audit: `service \"\u003Cname>\" has been registered at \u003COwner>`. Both name the offending service.\n\nIt returns normally when the composition mounts. Run it as the final check on a finished edit rather than after every line: a successful mount installs a standing generation that lives until the process exits, while a failed one disposes its subtree and leaves nothing behind.\n\n**Do not treat the roster's `broken` field as validation.** `list()` reports `broken` from a shape check — the file parses in the loader's YAML dialect and holds named rows — which every failure above passes. It catches a damaged file, not an unusable composition.\n\n`cordis_inspect` reports THIS session's composition, so it confirms what a row does in the runtime you are already in, never what your new preset will do.\n\nAfter a clean mount-validation, ask the user to start a session on the new preset and confirm the tool list; the preset decides tool schemas and prompt sections, and only a real session shows the agent that composition produces.\n\n`cordis_mount` evaluates JavaScript against the live runtime and disappears on restart. It is for probing, not for shipping a capability: a capability belongs in a composition file.\n\n## Native product subagents\n\nCodex and Claude Code providers already live in the host composition. A preset chooses either product by contributing the same ordinary delegation-tool row used for spawn and fork; never move a product provider into the preset and never add a product-specific settings field.\n\nCopy these disabled templates from a shipped full preset and remove `disabled` only for the products the user requested:\n\n```yaml\n- id: tool-subagent-codex\n  name: '@deepseek-ai\u002Fdsh-tool-subagent'\n  disabled: true\n  config:\n    provider: codex\n    toolName: subagent_codex\n    enableRunInBackground: false\n    maxDepth: provider-managed\n\n- id: tool-subagent-claude-code\n  name: '@deepseek-ai\u002Fdsh-tool-subagent'\n  disabled: true\n  config:\n    provider: claude-code\n    toolName: subagent_claude_code\n    enableRunInBackground: false\n    maxDepth: provider-managed\n```\n\nThe two rows are independent. Leaving both disabled preserves the copied preset, enabling one exposes only that product tool, and enabling both exposes both. The host must provide `codex` or `claude` on `PATH`; the preset does not install, authenticate, select a model for, or probe either product.\n\n## What not to move into a preset\n\n`agent-loop` registers the one agent factory and throws on a second. The registries own the per-session layering and cannot themselves be per-session. Session persistence must stay host-side or the session list fragments. The sandbox, approval, and permission rows are a deliberate boundary: a preset is exactly as privileged as the plugins it names, so letting one relax its own confinement would defeat the confinement.\n","# Editing Cordis compositions\n\nEvery capability in this harness is a plugin row in a `cordis.yml`. There is no separate configuration language: changing what an agent can do means changing which rows are composed for it.\n\n## Off-limits\n\n**Never edit, delete, or overwrite a preset that ships with the deployment** — the `agent-presets` directory beside the deployment's own config, which supplies `standard`, `code`, `minimal`, and `cordis`. Never escalate the sandbox to reach it, even when a change there looks quicker. An upgrade overwrites that install, and corrupting `cordis` disables preset authoring itself. Reading a shipped composition is the intended way to start; writing to one is not, and neither is editing the host composition to work around a preset limitation.\n\nTo change what a shipped preset does, copy it and edit the copy. Locally authored presets under the user root are yours to create, edit, and delete.\n\n## Decide the plane first\n\nTwo planes, and the choice is not about how \"agent-related\" something feels — it is about whether the thing must be shared.\n\n**Host composition.** The registries themselves (`tools`, `systemPrompt`, `agents`, `agent-loop`, `sessions`), anything crossing sessions (persistence, session query, storage, settings, credentials, telemetry), the sandbox and approval stack, the model route, and the subagent registry with its spawn\u002Ffork backends. One instance for the process.\n\n**Agent preset.** What one session contributes to those registries: its tool plugins, its persona and prompt sections, its compaction policy. One instance per session, mounted under that session's scope and unwound with it.\n\n**A service with a consumer outside the agent plane cannot move into a preset.** `subagents` is the worked example: the registry answers cross-session queries for the host api-proxy, so a per-session copy both starves that host row — it waits forever for a service nothing provides — and collides on the second session, since a provider name registers once. The preset contributes the delegation *tools*; the registry and its backends stay host-side.\n\nA preset is a directory holding one `agent.cordis.yml`, optionally beside a `preset.yml` carrying display metadata — `name` and `description` (and, for shipped presets, a roster `order`). Write the metadata too: a preset without it shows up in every picker as its bare directory name.\n\nLocally authored presets live one directory per preset under `${DSH_HOME:-$HOME\u002F.zenwit}\u002F.agent-presets\u002F`, and the shipped set sits beside the deployment's own config. Use those when the user asks where to look. A deployment can configure other roots, so the path you read or edit comes from `list()` or `resolve()` — which is also where `copy()` reports what it just created.\n\n## The roster service\n\n`ctx.agentPresets` owns discovery, authoring, and mounting. You reach it by mounting a temporary plugin that injects it and registers a tool for yourself — `cordis_mount` returns only the mount acknowledgement, so a registered tool is how a service answer gets back to you, and it becomes callable on your next step.\n\nRead `cordis_inspect what:\"api\" name:\"agentPresets\"` for the current signatures before writing the code. What this skill relies on:\n\n- `list()` — every preset with its `id`, `trust` (`system` for the shipped set, `user` for authored ones), and the absolute `path` of its composition file. This is how you locate any composition without knowing the install layout; the directory is that path's parent.\n- `read(id)` — one preset's composition text, without a file tool or a path.\n- `copy(from, id, name?)` — the only authoring write (see below).\n- `standingKeyFor(id)` — mount-validate one preset (see below).\n\n```js\nreturn {\n  name: 'preset-tools',\n  inject: ['agentPresets', 'tools'],\n  apply(ctx) {\n    harness.registerTool(ctx, harness.defineTool({\n      name: 'preset_check',\n      description: 'Mount-validate one preset by id.',\n      parameters: { id: { type: 'string', required: true } },\n      output: { schema: { type: 'string' }, render(_a, v) { return [{ type: 'text', text: v }] } },\n      async execute(args) {\n        try {\n          await ctx.agentPresets.standingKeyFor(args.id)\n          return 'mounted OK'\n        } catch (error) {\n          return error.message\n        }\n      },\n    }))\n  },\n}\n```\n\nUnmount the plugin with `cordis_unmount` when you are done; it is a probe, not a capability to leave behind.\n\n## Authoring a preset\n\n1. **Start from a copy.** `copy(from, id, name)` copies a whole preset directory into the user root — composition, metadata, skill directories, assets. It validates the id against `[a-z0-9][a-z0-9-]*` (it becomes the directory name, so no leading hyphen), refuses an id any root already supplies, rolls a failed copy back, and rewrites the copy's `preset.yml` to keep the source's description while dropping its name and roster `order`. Prefer it over a shell copy: it needs no sandbox escalation, it lands the copy in whichever root this deployment made writable, and the copy is exactly as loadable as its source. `resolve(id)` then names the file it created — that path, not a guessed one, is what the following edits target. `standard` is the full coding agent and the usual source.\n2. **Expect the file sandbox on every edit after the copy.** The user preset root lies outside the session workspace, so under the default `workspace-write` policy the first write there is denied. Only writes are: reading any composition by absolute path needs no escalation. Retry that exact command once with `sandbox_permissions` escalation and a short justification — the user sees and approves it. Batch your writes (one heredoc per file) rather than escalating many small commands. `copy()` itself runs host-side and needs none of this; the edits do.\n3. **Write the copy's `description`** in `preset.yml`, and its `name` if you passed none to `copy()`.\n4. **Edit `agent.cordis.yml`** row by row, keeping the plane rule and the realm rule.\n5. **Mount-validate the result**, then hand off to the user for a real session — both under *Verifying a change*.\n\nA composition written from scratch usually forgets a group realm or a consumer row; a copy starts loadable.\n\n## The rule that catches people\n\n**A row that publishes a service may not sit loose in a preset.** Registering a service without an isolate realm puts it in the process-global realm, so the second session mounting that preset collides with the first. The mount rejects it rather than letting the collision surface later.\n\nWhether a row publishes a service is not visible from its name, and package READMEs are absent from an installed deployment. Read it off the live runtime instead: `cordis_inspect what:\"services\"` lists every service with the fiber that owns it, so a service attributed to a fiber other than the row you are adding is one that row consumes rather than provides. For a row not in your current composition, mount-validate and read the rejection — it names the offending service.\n\nWhen a preset genuinely owns a service, wrap the provider **and every consumer that reaches it** in one group carrying an `isolate` realm. The shipped `standard` composition does this for `workflows`, which nothing outside an agent reads — its `delegation` group, with the delegation tools omitted here:\n\n```yaml\n- id: delegation\n  name: cordis:group\n  group: true\n  isolate:\n    workflows: true\n  config:\n    - id: workflow-worker-thread\n      name: '@deepseek-ai\u002Fdsh-workflow-worker-thread'\n      config:\n        provider: spawn\n    - id: tool-workflow\n      name: '@deepseek-ai\u002Fdsh-tool-workflow'\n```\n\n`true` means a realm private to each mounting session. A string label instead joins subtrees into one shared realm; `provide()` still throws on the second registration under that symbol, so a label does not pool instances and is not what a preset needs.\n\nA consumer left outside the group resolves the host's registry, which the preset did not populate, and then contributes nothing. Mount-validation catches that as a row that never activated.\n\nRealms are for services a preset owns, not for every group. A host capability the preset only consumes must stay outside a realm, or the row cannot resolve it: `tool-bash`, `tool-jobs`, and `tool-goal` publish nothing and sit loose in `standard`, which explains in comments which host instance each one resolves and why a realm would break it. Wrapping a consumer row in a realm of its own is the same error as leaving one outside its provider's realm.\n\n## Verifying a change\n\n**`standingKeyFor(id)` is the check.** It composes the preset's plugin subtree for real — the same mount a session start performs, minus the agent — and rejects the four ways a composition fails:\n\n- a row whose package does not resolve (`Cannot find package …`);\n- a row whose config is invalid (`invalid config: $.\u003Cfield> missing required value`);\n- a row that never activated (`N row(s) did not activate: \u003Cid>: waiting for \u003Cservice>`);\n- a service published into the root realm, which arrives as one of two messages. A name the host does not supply lands in the root realm and the mount audit rejects it: `row(s) published process-global service(s) [\u003Cname>]; a preset service must sit behind an isolate realm or move to the host composition` — this is the shape a preset's own forgotten realm takes. A name the host already supplies collides before the audit: `service \"\u003Cname>\" has been registered at \u003COwner>`. Both name the offending service.\n\nIt returns normally when the composition mounts. Run it as the final check on a finished edit rather than after every line: a successful mount installs a standing generation that lives until the process exits, while a failed one disposes its subtree and leaves nothing behind.\n\n**Do not treat the roster's `broken` field as validation.** `list()` reports `broken` from a shape check — the file parses in the loader's YAML dialect and holds named rows — which every failure above passes. It catches a damaged file, not an unusable composition.\n\n`cordis_inspect` reports THIS session's composition, so it confirms what a row does in the runtime you are already in, never what your new preset will do.\n\nAfter a clean mount-validation, ask the user to start a session on the new preset and confirm the tool list; the preset decides tool schemas and prompt sections, and only a real session shows the agent that composition produces.\n\n`cordis_mount` evaluates JavaScript against the live runtime and disappears on restart. It is for probing, not for shipping a capability: a capability belongs in a composition file.\n\n## Native product subagents\n\nCodex and Claude Code providers already live in the host composition. A preset chooses either product by contributing the same ordinary delegation-tool row used for spawn and fork; never move a product provider into the preset and never add a product-specific settings field.\n\nCopy these disabled templates from a shipped full preset and remove `disabled` only for the products the user requested:\n\n```yaml\n- id: tool-subagent-codex\n  name: '@deepseek-ai\u002Fdsh-tool-subagent'\n  disabled: true\n  config:\n    provider: codex\n    toolName: subagent_codex\n    enableRunInBackground: false\n    maxDepth: provider-managed\n\n- id: tool-subagent-claude-code\n  name: '@deepseek-ai\u002Fdsh-tool-subagent'\n  disabled: true\n  config:\n    provider: claude-code\n    toolName: subagent_claude_code\n    enableRunInBackground: false\n    maxDepth: provider-managed\n```\n\nThe two rows are independent. Leaving both disabled preserves the copied preset, enabling one exposes only that product tool, and enabling both exposes both. The host must provide `codex` or `claude` on `PATH`; the preset does not install, authenticate, select a model for, or probe either product.\n\n## What not to move into a preset\n\n`agent-loop` registers the one agent factory and throws on a second. The registries own the per-session layering and cannot themselves be per-session. Session persistence must stay host-side or the session list fragments. The sandbox, approval, and permission rows are a deliberate boundary: a preset is exactly as privileged as the plugins it names, so letting one relax its own confinement would defeat the confinement.\n",{"name":5,"description":7},"master","62087459d3d7f4149ee9a33bff63ed9ca4b6c1d8","dsh-plugin-desktop\u002Fresources\u002Fagent-presets\u002Fcordis\u002Fskills\u002Fediting-cordis-compositions","https:\u002F\u002Fgithub.com\u002FQiuzixiao\u002Fdeepseek-harness-desktop","https:\u002F\u002Fdshdesktop.cn","https:\u002F\u002Fgithub.com\u002FQiuzixiao","2026-09-10 18:31:27",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Qiuzixiao\u002Fdeepseek-harness-desktop --skill editing-cordis-compositions",{"tool":37,"command":38},"bunx","bunx skills add Qiuzixiao\u002Fdeepseek-harness-desktop --skill editing-cordis-compositions",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Qiuzixiao\u002Fdeepseek-harness-desktop --skill editing-cordis-compositions","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FQiuzixiao\u002Fdeepseek-harness-desktop\u002Fblob\u002Fmaster\u002Fdsh-plugin-desktop\u002Fresources\u002Fagent-presets\u002Fcordis\u002Fskills\u002Fediting-cordis-compositions\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7AS86XE0PJQ0MCDH5DPZCFC","short-drama-domain","Short-drama project object map and task routing. Use when the user works with screenplay artifacts, episode scenes, continuity, diagnosis, revision, or delivery. This skill provides operational vocabulary and questions, not a mandatory writing style.","https:\u002F\u002Fgithub.com\u002FQiuzixiao\u002Fdeepseek-harness-desktop\u002Fblob\u002Fmaster\u002Fdsh-short-drama\u002Fmanaged-presets\u002Fscreenplay-v1\u002Fskills\u002Fshort-drama-domain\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7AS837QRW3BDY2W6PHXB2AB","creative-project-organization","从梗概开始创作、生成设定\u002F人物\u002F大纲\u002F正文等文件时，在首批落盘前规划内容分组和保存位置；新增独立交付物时复核布局。自动适配项目语言和命名习惯，也用于用户要求的项目整理。无需用户提出归档要求。","https:\u002F\u002Fgithub.com\u002FQiuzixiao\u002Fdeepseek-harness-desktop\u002Fblob\u002Fmaster\u002Fdsh-short-drama\u002Fmanaged-presets\u002Fscreenplay-v1\u002Fskills\u002Fcreative-project-organization\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7AS7YHQTH0H79BZGANZF6V5","skill-sink","技能沉淀机制：把创作中验证有效的经验、方法论与个人文风，提炼成可复用的 DSH skill。当创作中发现可复用经验、用户要沉淀个人文风、或要把反复出现的规则固化成技能时使用。","https:\u002F\u002Fgithub.com\u002FQiuzixiao\u002Fdeepseek-harness-desktop\u002Fblob\u002Fmaster\u002Fdsh-plugin-desktop\u002Fresources\u002Fagent-presets\u002Fshort-drama\u002Fskills\u002Fskill-sink\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7AS7S0NS2PQVSNFQFRES3PW","short-drama-zonggang","短剧创作总纲与情绪账务引擎方法论。以「恨账—存债\u002F付息\u002F兑付」债务系统为内核，覆盖选题、故事骨架、压爽循环与卡点、付费闸门、台词正文格式、验收自检与失效模式库。当用户要创作短剧剧本、立项选题、写分集大纲、写正文台词、设计付费卡点，或评审\u002F修改\u002F验收短剧时，先加载本 Skill。","https:\u002F\u002Fgithub.com\u002FQiuzixiao\u002Fdeepseek-harness-desktop\u002Fblob\u002Fmaster\u002Fdsh-plugin-desktop\u002Fresources\u002Fagent-presets\u002Fshort-drama\u002Fskills\u002Fshort-drama-zonggang\u002FSKILL.md",[],[],{"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":80,"publishedAt":19},"01M7AS7KHM1F0V7HM33VDGAEQG","short-drama-structure","把已确认的故事前提排成短剧四幕二十拍、分集节奏和场次骨架（4×5 节拍表、卡点与高潮兑现）。当用户已有故事梗概，要求拆成四幕\u002F20 拍\u002F分集\u002F场次表、中段松散需要重排转折，或想设置悬念、反转、付费卡点及高潮兑现路径时使用。不适用于从零提炼创意、单场对白润色或平台投稿咨询。","https:\u002F\u002Fgithub.com\u002FQiuzixiao\u002Fdeepseek-harness-desktop\u002Fblob\u002Fmaster\u002Fdsh-plugin-desktop\u002Fresources\u002Fagent-presets\u002Fshort-drama\u002Fskills\u002Fshort-drama-structure\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},"01M7AS7EEA9D20P4R5BBSPNBCN","short-drama-scene","当用户提供剧本片段、分场或对白，要求更可拍\u002F更有戏\u002F减少解释\u002F改得口语化时调用；重点处理单场冲突、动作进出、状态变化、信息差、潜台词和对白瘦身。不适用于从零搭故事结构、设计整部剧的悬念卡点或行业投稿咨询。","https:\u002F\u002Fgithub.com\u002FQiuzixiao\u002Fdeepseek-harness-desktop\u002Fblob\u002Fmaster\u002Fdsh-plugin-desktop\u002Fresources\u002Fagent-presets\u002Fshort-drama\u002Fskills\u002Fshort-drama-scene\u002FSKILL.md",[],[]]