[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CRX2BZ9KHVDR4G46BENXRQ":3,"skill-same:01M6CRX2BZ9KHVDR4G46BENXRQ":114},{"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":23,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6CRX2BZ9KHVDR4G46BENXRQ","make-skill",null,"Create a focused workspace Skill from reusable decisions, knowledge, templates, or workflows in the current conversation. Use for \u002Fmake-skill with a focus argument and requests such as save this workflow or turn this into a skill; do not use for one-off summaries or ordinary file creation.","agentscope-ai\u002FQwenPaw","agentscope-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211762292?v=4","01M6CRT6543BZGGVK3P85GC08Q","AgentScope-AI","01M6CRT698G78F0SPC659YEK6E",37745,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmake-skill-en\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"make","make skill","workspace","for","Workspace Skill","requests","with","as","argument","focus","creation","save","create","file","decisions","workflow","reusable","workflows","use","knowledge","do","conversation","2026-11-10 10:12:30",false,"---\nname: make-skill\ndescription: \"Create a focused workspace Skill from reusable decisions, knowledge, templates, or workflows in the current conversation. Use for \u002Fmake-skill with a focus argument and requests such as save this workflow or turn this into a skill; do not use for one-off summaries or ordinary file creation.\"\nmetadata:\n  builtin_skill_version: \"2.3\"\n  qwenpaw:\n    emoji: \"✍️\"\n    requires: {}\n---\n\n# Make Skill\n\nCreate one new workspace Skill from the current conversation through planning, user approval, draft authoring, validation, and publication.\n\nResolve `\u003Cworkspace>` from the runtime directory context: use the current agent's absolute workspace path (also the working directory when no separate project is configured). Pass that same value throughout the lifecycle, independently of the task's project directory and the script `cwd`. Lifecycle artifacts belong under `\u003Cworkspace>\u002F.qwenpaw\u002Fmake-skill\u002F`; published Skills belong under `\u003Cworkspace>\u002Fskills\u002F`.\n\n## Script interface\n\nRun `\u003Cpython> scripts\u002F\u003Cscript>` through `execute_shell_command`, setting `cwd` to this Skill's `\u003Cdir>` from the available-skills entry. Use the executable path in `QWENPAW_DESKTOP_PY_RUNTIME` as `\u003Cpython>` when set; otherwise use `python`.\n\nEach script reads one JSON object from stdin (or `--input \u003Cfile>`) and returns one JSON object. Every input includes `workspace`; the table lists the other top-level fields.\n\n| Operation | Script | Other input fields | Successful result |\n|---|---|---|---|\n| Create a plan | `create_plan.py` | `plan` | `plan_id`, normalized `plan` |\n| Revise that plan | `create_plan.py` | `plan_id`, complete new `plan` | Same `plan_id`, normalized `plan` |\n| Initialize after approval | `init_draft.py` | `plan_id` | `draft_id`, `skill_dir` |\n| Validate a draft | `validate_skill.py` | `draft_id` | `digest` |\n| Publish a validated draft | `publish_skill.py` | `draft_id`, `expected_digest` from validation | Publication result |\n\n`plan_id` identifies one editable plan; keep it across revisions, including renames. `draft_id` identifies the initialized draft for validation, testing, and publication; `skill_dir` is where its package files belong. Use the returned values unchanged, not IDs inferred from names or paths.\n\n## Plan\n\nThe focus in `\u002Fmake-skill \u003Cfocus>` is required. For a natural-language request, infer it from the request and current conversation. Later user corrections replace conflicting earlier rules. Preserve stable guidance, contracts, templates, and workflows that should change future behavior; exclude one-off data, temporary paths, secrets, and retry chatter.\n\nRead [primary type and package](references\u002Ftype-and-package.md), then choose one primary type and only the files it needs. When the proposed test mode is not `off`, read [behavior testing](references\u002Fbehavior-testing.md) before defining its target.\n\n### Batch workflows\n\nA stored batch is a parameterized `run_tool_batch` program bundled with a workflow Skill. Use `batch: true` when a reusable region's actions, branches, and success condition can be stated before execution and one stored entrypoint saves meaningful agent-tool round trips. The region may be the whole workflow, one substantial helper, or one semantic tool-native action; action count is not the criterion. Runtime data, observations, and a final agent review do not prevent batching when the rule for handling them is already known.\n\nUse `batch: false` only when execution must invent the next action or success condition at runtime, or a shared entrypoint has no practical reuse value. If the user explicitly requests Batch, apply that choice to the plan without reopening eligibility.\n\nOnly after selecting `batch: true`, read [run batch](references\u002Frun-batch.md) before finalizing the workflow and file tree. When `batch: false`, do not read it.\n\n### Save and review the plan\n\nPlanning is read-only except for saving the plan through `create_plan.py`: use conversation evidence and existing artifacts, but do not execute or probe the proposed workflow, create package files, or initialize a draft. For first creation, omit `plan_id` and pass a complete candidate:\n\n```json\n{\n  \"workspace\": \"\u003Cworkspace>\",\n  \"plan\": {\n    \"revision\": 1,\n    \"focus\": \"One-sentence extraction scope\",\n    \"name\": \"lowercase-hyphen-name\",\n    \"goal\": \"Outcome for a future agent\",\n    \"type\": \"workflow\",\n    \"batch\": true,\n    \"steps\": [\"A user-reviewable workflow step\"],\n    \"package\": [\"SKILL.md\", \"scripts\u002Frun.batch.json\"],\n    \"execution\": \"foreground\",\n    \"test\": {\"mode\": \"off\", \"target\": \"\"},\n    \"warnings\": []\n  }\n}\n```\n\nTo revise, add the returned `plan_id` to the top-level input above and replace `plan` with the complete revised candidate, not a partial patch. This updates the existing plan without creating a copy. If an update reports `missing-plan`, return to planning and approval instead of building. A saved plan is not evidence of user approval.\n\nRender the normalized plan in English and show the selected value together with every available choice so the user can revise it without knowing the schema. The user-visible plan must contain this compact options table; do not replace it with prose or an approval hint. Omit the `Batch` row for a non-workflow:\n\n| Option | Selected | Available |\n|---|---|---|\n| Type | current English label | instruction \u002F template \u002F workflow |\n| Batch (workflow only) | enabled or disabled | enabled \u002F disabled |\n| Execution | foreground or background | foreground \u002F background |\n| Behavior test | current English label | off \u002F smoke \u002F eval (full behavioral evaluation) |\n\nAlso show the name, goal, workflow, complete file tree, test target when applicable, and warnings. Pass the internal values `instruction\u002Ftemplate\u002Fworkflow`, `true\u002Ffalse`, `foreground\u002Fbackground`, and `off\u002Fsmoke\u002Feval` to the script. Do not invent a `full` enum or any choice outside the script schema. Do not show a Batch closing reason, schema, revision, or internal enum. Ask the user to approve, modify, or cancel, then end the response without further tool calls.\n\nOnly a new user message explicitly approving the latest displayed `create_plan.py` result permits Build. Invoking `\u002Fmake-skill` starts planning; earlier task discussion or a hand-written outline does not replace this plan and approval step.\n\n- After a modification, merge the feedback, increment `revision`, and update the same plan. Revise serially within the current conversation, then show the complete returned plan for approval; earlier approval does not carry over.\n- Stop on cancellation, retaining the plan without creating a draft. Distinguish acknowledgment from approval; if the user's intent is unclear, ask one brief confirmation and wait.\n- Do not ask separately about execution or testing.\n\nThis version creates new Skills only. Resolve a name conflict through a newly approved revision; never overwrite an existing Skill.\n\n## Build\n\nAfter approval, run `init_draft.py` with the saved `plan_id`. Initialization snapshots the current plan into a new draft; later plan edits do not update that draft. It does not accept an inline replacement. If the plan is missing or invalid, return to planning instead of proceeding to Build.\n\n`execution` selects whether the current agent or a background subagent completes Skill creation. After initialization, for `background`, use `spawn_subagent` with `background: true` and give the generic subagent the complete approved plan, latest corrections, `workspace`, `draft_id`, and `skill_dir` to author the files, validate, run the approved behavior test, and publish without requesting approval again. Report the creation result when finished; running the generated Skill outside the approved behavior test requires a separate user request.\n\nCreate only approved files under the returned `skill_dir`. Start the generated `SKILL.md` with valid frontmatter:\n\n```yaml\n---\nname: lowercase-hyphen-name\ndescription: Briefly state the capability and when to use it.\n---\n```\n\nKeep the body to essential procedure and constraints without repeating the description. Type metadata is unnecessary.\n\nBefore validation, read the package from the perspective of a future agent that cannot see the source conversation. Remove references to source task directories, prior outputs, temporary IDs, current-case examples, or make-skill draft\u002Fpublish language unless that resource is deliberately packaged and reusable. When adapting an existing helper, generalize its paths, docstrings, and reporting, and check that its implementation still matches the final reusable rules. Keep this as one authoring pass; do not add case-specific lifecycle checks.\n\n## Validate, test, and publish\n\nBefore executing any draft script or batch, run `validate_skill.py` for the initialized draft.\n\nFix reported static or security errors in the draft and validate again. Testing is independent of Batch: run exactly the approved behavior test according to [behavior testing](references\u002Fbehavior-testing.md), and let `off` perform no draft execution. When a test or Batch run fails, retain the draft, report the concrete error, revise the Skill if the correction is clear, then validate again; do not hide the failure behind a fallback.\n\nPublish the unchanged validated draft with `publish_skill.py`, using the validation result's `digest` as `expected_digest`.\n\nOn success, report the package tree, validation summary, test result when one ran, and invocation `\u002F\u003Cname>`. On conflict or failure, retain the draft and report the error. Publishing a Skill is already persistent; do not also write it to `MEMORY.md` or daily memory unless the user separately asks.\n","# Make Skill\n\nCreate one new workspace Skill from the current conversation through planning, user approval, draft authoring, validation, and publication.\n\nResolve `\u003Cworkspace>` from the runtime directory context: use the current agent's absolute workspace path (also the working directory when no separate project is configured). Pass that same value throughout the lifecycle, independently of the task's project directory and the script `cwd`. Lifecycle artifacts belong under `\u003Cworkspace>\u002F.qwenpaw\u002Fmake-skill\u002F`; published Skills belong under `\u003Cworkspace>\u002Fskills\u002F`.\n\n## Script interface\n\nRun `\u003Cpython> scripts\u002F\u003Cscript>` through `execute_shell_command`, setting `cwd` to this Skill's `\u003Cdir>` from the available-skills entry. Use the executable path in `QWENPAW_DESKTOP_PY_RUNTIME` as `\u003Cpython>` when set; otherwise use `python`.\n\nEach script reads one JSON object from stdin (or `--input \u003Cfile>`) and returns one JSON object. Every input includes `workspace`; the table lists the other top-level fields.\n\n| Operation | Script | Other input fields | Successful result |\n|---|---|---|---|\n| Create a plan | `create_plan.py` | `plan` | `plan_id`, normalized `plan` |\n| Revise that plan | `create_plan.py` | `plan_id`, complete new `plan` | Same `plan_id`, normalized `plan` |\n| Initialize after approval | `init_draft.py` | `plan_id` | `draft_id`, `skill_dir` |\n| Validate a draft | `validate_skill.py` | `draft_id` | `digest` |\n| Publish a validated draft | `publish_skill.py` | `draft_id`, `expected_digest` from validation | Publication result |\n\n`plan_id` identifies one editable plan; keep it across revisions, including renames. `draft_id` identifies the initialized draft for validation, testing, and publication; `skill_dir` is where its package files belong. Use the returned values unchanged, not IDs inferred from names or paths.\n\n## Plan\n\nThe focus in `\u002Fmake-skill \u003Cfocus>` is required. For a natural-language request, infer it from the request and current conversation. Later user corrections replace conflicting earlier rules. Preserve stable guidance, contracts, templates, and workflows that should change future behavior; exclude one-off data, temporary paths, secrets, and retry chatter.\n\nRead [primary type and package](references\u002Ftype-and-package.md), then choose one primary type and only the files it needs. When the proposed test mode is not `off`, read [behavior testing](references\u002Fbehavior-testing.md) before defining its target.\n\n### Batch workflows\n\nA stored batch is a parameterized `run_tool_batch` program bundled with a workflow Skill. Use `batch: true` when a reusable region's actions, branches, and success condition can be stated before execution and one stored entrypoint saves meaningful agent-tool round trips. The region may be the whole workflow, one substantial helper, or one semantic tool-native action; action count is not the criterion. Runtime data, observations, and a final agent review do not prevent batching when the rule for handling them is already known.\n\nUse `batch: false` only when execution must invent the next action or success condition at runtime, or a shared entrypoint has no practical reuse value. If the user explicitly requests Batch, apply that choice to the plan without reopening eligibility.\n\nOnly after selecting `batch: true`, read [run batch](references\u002Frun-batch.md) before finalizing the workflow and file tree. When `batch: false`, do not read it.\n\n### Save and review the plan\n\nPlanning is read-only except for saving the plan through `create_plan.py`: use conversation evidence and existing artifacts, but do not execute or probe the proposed workflow, create package files, or initialize a draft. For first creation, omit `plan_id` and pass a complete candidate:\n\n```json\n{\n  \"workspace\": \"\u003Cworkspace>\",\n  \"plan\": {\n    \"revision\": 1,\n    \"focus\": \"One-sentence extraction scope\",\n    \"name\": \"lowercase-hyphen-name\",\n    \"goal\": \"Outcome for a future agent\",\n    \"type\": \"workflow\",\n    \"batch\": true,\n    \"steps\": [\"A user-reviewable workflow step\"],\n    \"package\": [\"SKILL.md\", \"scripts\u002Frun.batch.json\"],\n    \"execution\": \"foreground\",\n    \"test\": {\"mode\": \"off\", \"target\": \"\"},\n    \"warnings\": []\n  }\n}\n```\n\nTo revise, add the returned `plan_id` to the top-level input above and replace `plan` with the complete revised candidate, not a partial patch. This updates the existing plan without creating a copy. If an update reports `missing-plan`, return to planning and approval instead of building. A saved plan is not evidence of user approval.\n\nRender the normalized plan in English and show the selected value together with every available choice so the user can revise it without knowing the schema. The user-visible plan must contain this compact options table; do not replace it with prose or an approval hint. Omit the `Batch` row for a non-workflow:\n\n| Option | Selected | Available |\n|---|---|---|\n| Type | current English label | instruction \u002F template \u002F workflow |\n| Batch (workflow only) | enabled or disabled | enabled \u002F disabled |\n| Execution | foreground or background | foreground \u002F background |\n| Behavior test | current English label | off \u002F smoke \u002F eval (full behavioral evaluation) |\n\nAlso show the name, goal, workflow, complete file tree, test target when applicable, and warnings. Pass the internal values `instruction\u002Ftemplate\u002Fworkflow`, `true\u002Ffalse`, `foreground\u002Fbackground`, and `off\u002Fsmoke\u002Feval` to the script. Do not invent a `full` enum or any choice outside the script schema. Do not show a Batch closing reason, schema, revision, or internal enum. Ask the user to approve, modify, or cancel, then end the response without further tool calls.\n\nOnly a new user message explicitly approving the latest displayed `create_plan.py` result permits Build. Invoking `\u002Fmake-skill` starts planning; earlier task discussion or a hand-written outline does not replace this plan and approval step.\n\n- After a modification, merge the feedback, increment `revision`, and update the same plan. Revise serially within the current conversation, then show the complete returned plan for approval; earlier approval does not carry over.\n- Stop on cancellation, retaining the plan without creating a draft. Distinguish acknowledgment from approval; if the user's intent is unclear, ask one brief confirmation and wait.\n- Do not ask separately about execution or testing.\n\nThis version creates new Skills only. Resolve a name conflict through a newly approved revision; never overwrite an existing Skill.\n\n## Build\n\nAfter approval, run `init_draft.py` with the saved `plan_id`. Initialization snapshots the current plan into a new draft; later plan edits do not update that draft. It does not accept an inline replacement. If the plan is missing or invalid, return to planning instead of proceeding to Build.\n\n`execution` selects whether the current agent or a background subagent completes Skill creation. After initialization, for `background`, use `spawn_subagent` with `background: true` and give the generic subagent the complete approved plan, latest corrections, `workspace`, `draft_id`, and `skill_dir` to author the files, validate, run the approved behavior test, and publish without requesting approval again. Report the creation result when finished; running the generated Skill outside the approved behavior test requires a separate user request.\n\nCreate only approved files under the returned `skill_dir`. Start the generated `SKILL.md` with valid frontmatter:\n\n```yaml\n---\nname: lowercase-hyphen-name\ndescription: Briefly state the capability and when to use it.\n---\n```\n\nKeep the body to essential procedure and constraints without repeating the description. Type metadata is unnecessary.\n\nBefore validation, read the package from the perspective of a future agent that cannot see the source conversation. Remove references to source task directories, prior outputs, temporary IDs, current-case examples, or make-skill draft\u002Fpublish language unless that resource is deliberately packaged and reusable. When adapting an existing helper, generalize its paths, docstrings, and reporting, and check that its implementation still matches the final reusable rules. Keep this as one authoring pass; do not add case-specific lifecycle checks.\n\n## Validate, test, and publish\n\nBefore executing any draft script or batch, run `validate_skill.py` for the initialized draft.\n\nFix reported static or security errors in the draft and validate again. Testing is independent of Batch: run exactly the approved behavior test according to [behavior testing](references\u002Fbehavior-testing.md), and let `off` perform no draft execution. When a test or Batch run fails, retain the draft, report the concrete error, revise the Skill if the correction is clear, then validate again; do not hide the failure behind a fallback.\n\nPublish the unchanged validated draft with `publish_skill.py`, using the validation result's `digest` as `expected_digest`.\n\nOn success, report the package tree, validation summary, test result when one ran, and invocation `\u002F\u003Cname>`. On conflict or failure, retain the draft and report the error. Publishing a Skill is already persistent; do not also write it to `MEMORY.md` or daily memory unless the user separately asks.\n",{"name":5,"metadata":51,"description":7},{"qwenpaw":52,"builtin_skill_version":55},{"emoji":53,"requires":54},"✍️",{},"2.3","main","401662d8cbd2a77cdd2ab75235b2d8d449b5131b","src\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmake-skill-en",3285,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw","http:\u002F\u002Fqwenpaw.agentscope.io\u002F","https:\u002F\u002Fgithub.com\u002Fagentscope-ai","2026-11-13 15:25:45",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add agentscope-ai\u002FQwenPaw --skill make-skill",{"tool":70,"command":71},"bunx","bunx skills add agentscope-ai\u002FQwenPaw --skill make-skill",{"tool":73,"command":74},"pnpm","pnpm dlx skills add agentscope-ai\u002FQwenPaw --skill make-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmake-skill-en\u002FSKILL.md",true,[78,84,88,92,98,102,106,110],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fbehavior-testing.md","REFERENCE","参考文档",2582,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmake-skill-en\u002Freferences\u002Fbehavior-testing.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Frun-batch.md",5940,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmake-skill-en\u002Freferences\u002Frun-batch.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Ftype-and-package.md",1827,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmake-skill-en\u002Freferences\u002Ftype-and-package.md",{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Fcreate_plan.py","SCRIPT","脚本",17590,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmake-skill-en\u002Fscripts\u002Fcreate_plan.py",{"path":99,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Finit_draft.py",2943,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmake-skill-en\u002Fscripts\u002Finit_draft.py",{"path":103,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fnative_cli.py",1145,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmake-skill-en\u002Fscripts\u002Fnative_cli.py",{"path":107,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Fpublish_skill.py",5869,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmake-skill-en\u002Fscripts\u002Fpublish_skill.py",{"path":111,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Fvalidate_skill.py",18069,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmake-skill-en\u002Fscripts\u002Fvalidate_skill.py",[115,129,142,152,164,182],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":122,"publishedAt":46},"01M6CRZ8QQ6RWS9P0PBDZDZSY8","portable-qoder","A stable standalone Qoder fixture Skill.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fqoder-mini\u002Fskills\u002Fportable-qoder\u002FSKILL.md",[121],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[123,124,125,126,127,128],"portable","qoder","portable qoder","fixture skill","fixture","standalone",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":140,"publishedAt":46},"01M6CRZ61PNG319SVCYZZVC7HA","report","Report fixture status.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fqoder-mini\u002Fplugins\u002Fcustom\u002Fmini-plugin-0.1.0\u002Fskills\u002Freport\u002FSKILL.md",[135],{"categoryNo":136,"categoryName":137,"taxonomyType":138,"taxonomyTypeDesc":139},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[131,141,127],"status",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":149,"publishedAt":46},"01M6CRZ3PTN8ZGW30RHF081Z00","portable-skill","A stable standalone Codex fixture Skill.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fcodex-mini\u002Fskills\u002Fportable-skill\u002FSKILL.md",[148],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[123,150,151,126,127,128],"portable skill","codex",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":46},"01M6CRZ1DNK71D5M63SQ3SPTMH","building-native-ui","Build a small native interface.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fcodex-mini\u002Fplugins\u002Fcache\u002Fmini-market\u002Fexpo\u002F1.0.0\u002Fskills\u002Fbuilding-native-ui\u002FSKILL.md",[],[159,160,161,162,163],"native","ui","building native ui","build","interface",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":171,"publishedAt":46},"01M6CRYYTRG56E165X66FRWZC8","browser_visible","当用户需要控制 browser 的浏览器启动方式时，使用本 skill。browser 默认由 Playwright 直接管理、不开放调试端口（需让其他本地工具附加时显式传 `cdp_port`）；`headed` 控制是否显示窗口，`private_mode` 保留用于兼容、不再改变默认行为，`browser_args` 传入额外的 Chromium 启动参数，`executable_path` 指定自定义浏览器可执行文件路径。","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Ftools\u002Fdeprecated_browser\u002Fskills\u002Fbrowser_visible-zh\u002FSKILL.md",[170],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[172,173,174,175,176,177,178,179,180,181],"browser visible","browser","path","chromium","playwright","cdp","port","文件","工具","mode",{"skillNo":183,"name":166,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":188,"publishedAt":46},"01M6CRYVQ9DMBB2EN4JFWC4R7F","Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit `cdp_port` to let another local tool attach); `headed` controls whether the window is visible, and `private_mode` is kept for backward compatibility and no longer changes the default.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Ftools\u002Fdeprecated_browser\u002Fskills\u002Fbrowser_visible-en\u002FSKILL.md",[187],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[172,173,189,190,191,42,192,193,194,195,196,197,198,178,181,27,199,200,201,177,202,176],"user","compatibility","default","tool","debugging","launch","when","local","control","controls","changes","window","managed","attach"]