[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X6DV8SFHTJ4G2N9CDKTJM3":3,"skill-same:01M6X6DV8SFHTJ4G2N9CDKTJM3":84},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":60,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6X6DV8SFHTJ4G2N9CDKTJM3","context-authoring",null,"Use when filling knowledge-layer context files — auth-model, tenant-boundaries, data-sensitivity, deployment-order, observability — interactive template walkthrough.","event4u-app\u002Fagent-config","event4u-app","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F199339632?v=4","01M6X5TWBNCQCE1VDKT4E9KF7N","event4u.app","01M6X5TWF4HRM266RG2Q5VVH1X",19,"MIT","https:\u002F\u002Fgithub.com\u002Fevent4u-app\u002Fagent-config\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Fcontext-authoring\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],"context","context authoring","authoring","use","config","when","tenant","layer","deployment","context files","sensitivity","files","observability","auth","model","template","knowledge","walkthrough","Meta","data","2026-11-10 10:12:30",false,"---\nmodel_tier: inherit\nname: context-authoring\ndescription: \"Use when filling knowledge-layer context files — auth-model, tenant-boundaries, data-sensitivity, deployment-order, observability — interactive template walkthrough.\"\ndomain: process\nworkspaces:\n  - agent-config-maintainer\npacks:\n  - meta\n---\n\n# context-authoring\n\n## When to use\n\nUse this skill when:\n\n- A new project has been scaffolded and the `agents\u002Fsettings\u002Fcontexts\u002F` files are still\n  template stubs from `event4u\u002Fagent-config`.\n- The user asks \"help me fill in the auth model context\", \"set up tenant\n  boundaries\", or similar knowledge-layer work.\n- A reviewer skill (`authz-review`, `data-flow-mapper`, `migration-safety`,\n  `multi-tenant-boundary-review`, `secrets-and-config-review`) reports *\"I\n  cannot proceed — `agents\u002Fsettings\u002Fcontexts\u002F\u003Cfile>.md` is still a template\"*.\n- After a significant architecture change that invalidates one of the five\n  context files.\n\nDo NOT use when:\n\n- Writing a regular roadmap or feature doc — use `agent-docs-writing`.\n- Creating a generic context document that does not map to one of the five\n  knowledge-layer templates — use `context-create`.\n- Filling in the engineering-memory YAML files (`domain-invariants.yml`, etc.)\n  — use `\u002Fmemory-add`.\n\n## The five files\n\n| File | What it answers | Who reads it |\n|---|---|---|\n| `auth-model.md` | Roles, permission model, impersonation, known exceptions | `authz-review`, `judge-security-auditor`, `threat-modeling` |\n| `tenant-boundaries.md` | Tenancy type, scope propagation, known cross-tenant paths | `multi-tenant-boundary-review`, `blast-radius-analyzer`, `judge-security-auditor` |\n| `data-sensitivity.md` | Field classification, masking rules, log-safe types | `data-flow-mapper`, logging reviewers |\n| `deployment-order.md` | Migration strategy, feature flags, rollback plan | `migration-safety`, `judge-bug-hunter`, release reviewers |\n| `observability.md` | Error tracking, log channels, metrics, known alerts | deploy reviewers, `bug-analyzer`, incident mode |\n\nThe templates ship in `src\u002Fagent-src\u002Ftemplates\u002Fcontexts\u002F` and are\ncopied into `agents\u002Fsettings\u002Fcontexts\u002F` by the installer.\n\n## Procedure: context-authoring\n\n### Step 0: Inspect\n\n1. List `agents\u002Fsettings\u002Fcontexts\u002F` — which of the five files exist? Which still contain\n   the `\u003C!-- Template shipped by event4u\u002Fagent-config. -->` HTML comment?\n2. Ask the user which file to work on. Use numbered options:\n\n   ```\n   > 1. auth-model.md — roles, permissions, impersonation\n   > 2. tenant-boundaries.md — tenancy type and scope propagation\n   > 3. data-sensitivity.md — field classification and masking\n   > 4. deployment-order.md — migrations, flags, rollback\n   > 5. observability.md — errors, logs, metrics, alerts\n   ```\n\n3. If multiple files are stubs, default to the order above — `auth-model` is\n   the prerequisite for `tenant-boundaries`; both feed `data-sensitivity`.\n\n### Step 1: Harvest evidence before asking\n\nFor the chosen file, pull what the codebase already reveals before asking\nthe user. Record the file:line citations — they become the authoritative\nsource when the user is unsure.\n\n| File | Harvest from |\n|---|---|\n| `auth-model.md` | Policy classes, Gate definitions, permission seeders, role enums, `@can` directives, middleware |\n| `tenant-boundaries.md` | Base query scopes, connection-switching middleware, tenant-resolution service, global scopes, `.env` vars like `TENANT_*` |\n| `data-sensitivity.md` | ORM hidden-field config (Eloquent `$hidden` \u002F `$casts`, Symfony `#[Ignore]`, Prisma `select` defaults, SQLAlchemy `__init__` filters), Sentry `beforeSend`, logging redaction helpers, API serialisers \u002F resources, export commands |\n| `deployment-order.md` | `database\u002Fmigrations\u002F`, feature-flag config (Pennant \u002F LaunchDarkly), deploy scripts, CI workflow, rollback runbooks in `docs\u002F` |\n| `observability.md` | `config\u002Flogging.php`, Sentry init, dashboard links in READMEs, alert rules in Terraform\u002FGrafana dashboards |\n\nStart the walkthrough by showing the harvested evidence — the user only\nhas to confirm or correct, not invent from scratch.\n\n### Step 2: Walk the template section by section\n\n1. Open the template and treat **every HTML comment** as a question for the\n   user. Do NOT fabricate answers to skip a section.\n2. Present each section as:\n\n   ```\n   **Section:** \u003Cheading>\n   **Template asks:** \u003Cwhat the comment says>\n   **Evidence I found:** \u003Cfile:line references or \"none\">\n   **Proposed content:** \u003Cdraft or \"I need your input\">\n\n   > 1. Accept the draft\n   > 2. Edit — tell me what's wrong\n   > 3. I don't know — mark as \"TBD\" with a follow-up task\n   ```\n\n3. If the user picks \"TBD\", insert an HTML comment `\u003C!-- TBD: \u003Cquestion> -->`\n   at that spot — never a fabricated value. Reviewer skills key on the\n   comment to warn about incomplete sections.\n\n### Step 3: Preserve the file contract\n\n1. Remove the top-of-file `\u003C!-- Template shipped by ... -->` comment only\n   after at least one section has been authored — an untouched file must\n   stay recognisable as a stub.\n2. Keep every heading the template ships with. Reviewer skills grep for\n   exact section names (`## Known exceptions`, `## Known alerts`, etc.).\n3. Do NOT add new top-level sections. The template surface is the\n   contract — extend existing sections, file a proposal via\n   `learning-to-rule-or-skill` to expand the template upstream.\n\n### Step 4: Validate\n\n1. Run `.\u002Fscripts-run src\u002Fscripts\u002Fcheck_portability` — project-specific content is\n   expected here, but the check catches accidental copy of other projects'\n   identifiers.\n2. Run `.\u002Fscripts-run src\u002Fscripts\u002Fcheck_references` — cross-file links between the\n   five contexts must resolve.\n3. Confirm with the user: \"is this accurate enough that a reviewer should\n   treat it as the source of truth?\" — anything less and a `\u003C!-- TBD -->`\n   marker stays.\n\n## Output format\n\n1. `agents\u002Fsettings\u002Fcontexts\u002F\u003Cfile>.md` updated with project-specific content; every\n   section either authored or explicitly marked `\u003C!-- TBD: ... -->`.\n2. A short summary comment back to the user: which sections are complete,\n   which are `TBD`, and which downstream reviewer skills are now unblocked.\n3. Optional: a proposal stub in `agents\u002Fproposals\u002F` for any template gap\n   the user hit (missing section, ambiguous field) — feeds the curated\n   self-improvement pipeline via `learning-to-rule-or-skill`.\n\n## Gotcha\n\n- The model tends to fabricate plausible roles, fields, or alerts when\n  harvesting comes up empty. Do NOT. An `\u003C!-- TBD: ... -->` marker is\n  always better than a made-up entry — reviewer skills trust this file.\n- The model tends to collapse the template once it starts editing, losing\n  the HTML comments that explain *why* a section exists. Preserve them\n  until the section is authored — they are the authoring prompt.\n- `data-sensitivity.md` is the highest-leverage file and also the one most\n  likely to be skipped as \"boring\". Prioritise it after `auth-model` —\n  missing entries here become production leaks, not review nits.\n- Do not treat this skill as a form-filler. If a project is single-tenant,\n  `tenant-boundaries.md` SHOULD be deleted, not stubbed — the checklist\n  explicitly says so at the top of the file.\n\n## Path conventions when a context cites another context\n\nIf the context file declares its own `load_context:` (chain reasoning),\nuse logical names rooted at the source — `contexts\u002F\u003Carea>\u002F\u003Cfile>.md`\nfor package material or `agents\u002Fsettings\u002Fcontexts\u002F\u003Cfile>.md` for project-local\nmaterial. The `.agent-src.uncondensed\u002F` prefix is rejected by the\nschema regex and by `scripts\u002Flint_load_context.ts`. Body links to\n`docs\u002Fguidelines\u002F...` use the verbatim `..\u002F..\u002Fdocs\u002F...` relative form.\nCanonical reference: `rule-writing` § 3b and\n`docs\u002Fcontracts\u002Fload-context-schema.md`.\n\n## Frugality Standards\n\nApply the [Frugality Charter](..\u002F..\u002Fcontexts\u002Fcontracts\u002Ffrugality-charter.md)\nto every context file you author.\n\n**Examples in this artifact:**\n- Per the charter's index nature, context files are reviewer fuel —\n  they hold mechanics, not Iron-Law obligations.\n- Per the cite-don't-restate principle, when a section mirrors a\n  rule, link the rule and stop.\n- Per the act-skip-narration rule, lookup tables open the section;\n  explanatory prose follows only if the table is ambiguous.\n\n**Pre-save self-check:**\n1. Does the context file restate Iron-Law text instead of linking\n   the rule?\n2. Does any section open with \"This document explains…\" instead of\n   the lookup material?\n3. Are placeholders (`\u003Cadd me>`, `TBD`) shipped instead of actual\n   content?\n4. Are the cited rules linked with stable anchors (verified to\n   exist)?\n\n## Do NOT\n\n- Do NOT copy content between projects. Every context file is local to its\n  repo. Reuse of another project's roles, tenants, or alerts is a\n  portability violation and a security risk.\n- Do NOT commit TBD-heavy files without flagging them in the PR\n  description. Reviewer skills will downgrade confidence, but a human\n  reviewer should know the contexts are partial.\n- Do NOT rename or restructure the template sections. Reviewer skills\n  grep for exact headings.\n","# context-authoring\n\n## When to use\n\nUse this skill when:\n\n- A new project has been scaffolded and the `agents\u002Fsettings\u002Fcontexts\u002F` files are still\n  template stubs from `event4u\u002Fagent-config`.\n- The user asks \"help me fill in the auth model context\", \"set up tenant\n  boundaries\", or similar knowledge-layer work.\n- A reviewer skill (`authz-review`, `data-flow-mapper`, `migration-safety`,\n  `multi-tenant-boundary-review`, `secrets-and-config-review`) reports *\"I\n  cannot proceed — `agents\u002Fsettings\u002Fcontexts\u002F\u003Cfile>.md` is still a template\"*.\n- After a significant architecture change that invalidates one of the five\n  context files.\n\nDo NOT use when:\n\n- Writing a regular roadmap or feature doc — use `agent-docs-writing`.\n- Creating a generic context document that does not map to one of the five\n  knowledge-layer templates — use `context-create`.\n- Filling in the engineering-memory YAML files (`domain-invariants.yml`, etc.)\n  — use `\u002Fmemory-add`.\n\n## The five files\n\n| File | What it answers | Who reads it |\n|---|---|---|\n| `auth-model.md` | Roles, permission model, impersonation, known exceptions | `authz-review`, `judge-security-auditor`, `threat-modeling` |\n| `tenant-boundaries.md` | Tenancy type, scope propagation, known cross-tenant paths | `multi-tenant-boundary-review`, `blast-radius-analyzer`, `judge-security-auditor` |\n| `data-sensitivity.md` | Field classification, masking rules, log-safe types | `data-flow-mapper`, logging reviewers |\n| `deployment-order.md` | Migration strategy, feature flags, rollback plan | `migration-safety`, `judge-bug-hunter`, release reviewers |\n| `observability.md` | Error tracking, log channels, metrics, known alerts | deploy reviewers, `bug-analyzer`, incident mode |\n\nThe templates ship in `src\u002Fagent-src\u002Ftemplates\u002Fcontexts\u002F` and are\ncopied into `agents\u002Fsettings\u002Fcontexts\u002F` by the installer.\n\n## Procedure: context-authoring\n\n### Step 0: Inspect\n\n1. List `agents\u002Fsettings\u002Fcontexts\u002F` — which of the five files exist? Which still contain\n   the `\u003C!-- Template shipped by event4u\u002Fagent-config. -->` HTML comment?\n2. Ask the user which file to work on. Use numbered options:\n\n   ```\n   > 1. auth-model.md — roles, permissions, impersonation\n   > 2. tenant-boundaries.md — tenancy type and scope propagation\n   > 3. data-sensitivity.md — field classification and masking\n   > 4. deployment-order.md — migrations, flags, rollback\n   > 5. observability.md — errors, logs, metrics, alerts\n   ```\n\n3. If multiple files are stubs, default to the order above — `auth-model` is\n   the prerequisite for `tenant-boundaries`; both feed `data-sensitivity`.\n\n### Step 1: Harvest evidence before asking\n\nFor the chosen file, pull what the codebase already reveals before asking\nthe user. Record the file:line citations — they become the authoritative\nsource when the user is unsure.\n\n| File | Harvest from |\n|---|---|\n| `auth-model.md` | Policy classes, Gate definitions, permission seeders, role enums, `@can` directives, middleware |\n| `tenant-boundaries.md` | Base query scopes, connection-switching middleware, tenant-resolution service, global scopes, `.env` vars like `TENANT_*` |\n| `data-sensitivity.md` | ORM hidden-field config (Eloquent `$hidden` \u002F `$casts`, Symfony `#[Ignore]`, Prisma `select` defaults, SQLAlchemy `__init__` filters), Sentry `beforeSend`, logging redaction helpers, API serialisers \u002F resources, export commands |\n| `deployment-order.md` | `database\u002Fmigrations\u002F`, feature-flag config (Pennant \u002F LaunchDarkly), deploy scripts, CI workflow, rollback runbooks in `docs\u002F` |\n| `observability.md` | `config\u002Flogging.php`, Sentry init, dashboard links in READMEs, alert rules in Terraform\u002FGrafana dashboards |\n\nStart the walkthrough by showing the harvested evidence — the user only\nhas to confirm or correct, not invent from scratch.\n\n### Step 2: Walk the template section by section\n\n1. Open the template and treat **every HTML comment** as a question for the\n   user. Do NOT fabricate answers to skip a section.\n2. Present each section as:\n\n   ```\n   **Section:** \u003Cheading>\n   **Template asks:** \u003Cwhat the comment says>\n   **Evidence I found:** \u003Cfile:line references or \"none\">\n   **Proposed content:** \u003Cdraft or \"I need your input\">\n\n   > 1. Accept the draft\n   > 2. Edit — tell me what's wrong\n   > 3. I don't know — mark as \"TBD\" with a follow-up task\n   ```\n\n3. If the user picks \"TBD\", insert an HTML comment `\u003C!-- TBD: \u003Cquestion> -->`\n   at that spot — never a fabricated value. Reviewer skills key on the\n   comment to warn about incomplete sections.\n\n### Step 3: Preserve the file contract\n\n1. Remove the top-of-file `\u003C!-- Template shipped by ... -->` comment only\n   after at least one section has been authored — an untouched file must\n   stay recognisable as a stub.\n2. Keep every heading the template ships with. Reviewer skills grep for\n   exact section names (`## Known exceptions`, `## Known alerts`, etc.).\n3. Do NOT add new top-level sections. The template surface is the\n   contract — extend existing sections, file a proposal via\n   `learning-to-rule-or-skill` to expand the template upstream.\n\n### Step 4: Validate\n\n1. Run `.\u002Fscripts-run src\u002Fscripts\u002Fcheck_portability` — project-specific content is\n   expected here, but the check catches accidental copy of other projects'\n   identifiers.\n2. Run `.\u002Fscripts-run src\u002Fscripts\u002Fcheck_references` — cross-file links between the\n   five contexts must resolve.\n3. Confirm with the user: \"is this accurate enough that a reviewer should\n   treat it as the source of truth?\" — anything less and a `\u003C!-- TBD -->`\n   marker stays.\n\n## Output format\n\n1. `agents\u002Fsettings\u002Fcontexts\u002F\u003Cfile>.md` updated with project-specific content; every\n   section either authored or explicitly marked `\u003C!-- TBD: ... -->`.\n2. A short summary comment back to the user: which sections are complete,\n   which are `TBD`, and which downstream reviewer skills are now unblocked.\n3. Optional: a proposal stub in `agents\u002Fproposals\u002F` for any template gap\n   the user hit (missing section, ambiguous field) — feeds the curated\n   self-improvement pipeline via `learning-to-rule-or-skill`.\n\n## Gotcha\n\n- The model tends to fabricate plausible roles, fields, or alerts when\n  harvesting comes up empty. Do NOT. An `\u003C!-- TBD: ... -->` marker is\n  always better than a made-up entry — reviewer skills trust this file.\n- The model tends to collapse the template once it starts editing, losing\n  the HTML comments that explain *why* a section exists. Preserve them\n  until the section is authored — they are the authoring prompt.\n- `data-sensitivity.md` is the highest-leverage file and also the one most\n  likely to be skipped as \"boring\". Prioritise it after `auth-model` —\n  missing entries here become production leaks, not review nits.\n- Do not treat this skill as a form-filler. If a project is single-tenant,\n  `tenant-boundaries.md` SHOULD be deleted, not stubbed — the checklist\n  explicitly says so at the top of the file.\n\n## Path conventions when a context cites another context\n\nIf the context file declares its own `load_context:` (chain reasoning),\nuse logical names rooted at the source — `contexts\u002F\u003Carea>\u002F\u003Cfile>.md`\nfor package material or `agents\u002Fsettings\u002Fcontexts\u002F\u003Cfile>.md` for project-local\nmaterial. The `.agent-src.uncondensed\u002F` prefix is rejected by the\nschema regex and by `scripts\u002Flint_load_context.ts`. Body links to\n`docs\u002Fguidelines\u002F...` use the verbatim `..\u002F..\u002Fdocs\u002F...` relative form.\nCanonical reference: `rule-writing` § 3b and\n`docs\u002Fcontracts\u002Fload-context-schema.md`.\n\n## Frugality Standards\n\nApply the [Frugality Charter](..\u002F..\u002Fcontexts\u002Fcontracts\u002Ffrugality-charter.md)\nto every context file you author.\n\n**Examples in this artifact:**\n- Per the charter's index nature, context files are reviewer fuel —\n  they hold mechanics, not Iron-Law obligations.\n- Per the cite-don't-restate principle, when a section mirrors a\n  rule, link the rule and stop.\n- Per the act-skip-narration rule, lookup tables open the section;\n  explanatory prose follows only if the table is ambiguous.\n\n**Pre-save self-check:**\n1. Does the context file restate Iron-Law text instead of linking\n   the rule?\n2. Does any section open with \"This document explains…\" instead of\n   the lookup material?\n3. Are placeholders (`\u003Cadd me>`, `TBD`) shipped instead of actual\n   content?\n4. Are the cited rules linked with stable anchors (verified to\n   exist)?\n\n## Do NOT\n\n- Do NOT copy content between projects. Every context file is local to its\n  repo. Reuse of another project's roles, tenants, or alerts is a\n  portability violation and a security risk.\n- Do NOT commit TBD-heavy files without flagging them in the PR\n  description. Reviewer skills will downgrade confidence, but a human\n  reviewer should know the contexts are partial.\n- Do NOT rename or restructure the template sections. Reviewer skills\n  grep for exact headings.\n",{"name":5,"packs":49,"domain":51,"model_tier":52,"workspaces":53,"description":7},[50],"meta","process","inherit",[54],"agent-config-maintainer","main","12bd765ce1d800501d45dfb8232102793af01290","src\u002Fskills\u002Fcontext-authoring",1,"https:\u002F\u002Fgithub.com\u002Fevent4u-app\u002Fagent-config","https:\u002F\u002Fevent4u.app","https:\u002F\u002Fgithub.com\u002Fevent4u-app","Your events in your hand","2026-11-11 22:25:41",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add event4u-app\u002Fagent-config --skill context-authoring",{"tool":70,"command":71},"bunx","bunx skills add event4u-app\u002Fagent-config --skill context-authoring",{"tool":73,"command":74},"pnpm","pnpm dlx skills add event4u-app\u002Fagent-config --skill context-authoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fevent4u-app\u002Fagent-config\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Fcontext-authoring\u002FSKILL.md",true,[78],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"evals\u002Ftriggers.json","REFERENCE","参考文档",3457,"https:\u002F\u002Fgithub.com\u002Fevent4u-app\u002Fagent-config\u002Fblob\u002Fmain\u002Fsrc\u002Fskills\u002Fcontext-authoring\u002Fevals\u002Ftriggers.json",[85,99,112,124,136,146],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":92,"publishedAt":44},"01M6X84PK96XBPENXH66JCTSD1","unknown-key-fixture","Declares a key the schema does not know.","https:\u002F\u002Fgithub.com\u002Fevent4u-app\u002Fagent-config\u002Fblob\u002Fmain\u002Ftests\u002Fscripts\u002Ffixtures\u002Fbody-portable\u002Funknown-key\u002FSKILL.md",[91],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[93,94,95,96,97,98],"unknown key fixture","Unknown key","fixture","unknown","schema","package",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":106,"publishedAt":44},"01M6X84HW7NAHZ7GZMQ9RXK1XJ","portable-fixture","Declares only semantics the MCP-lite carrier transports whole.","https:\u002F\u002Fgithub.com\u002Fevent4u-app\u002Fagent-config\u002Fblob\u002Fmain\u002Ftests\u002Fscripts\u002Ffixtures\u002Fbody-portable\u002Fportable\u002FSKILL.md",[105],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[95,107,108,109,110,98,111],"portable","portable fixture","engineer","only","MCP",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":119,"publishedAt":44},"01M6X84F29FE0RGGZ1ZTFGZTX2","non-portable-fixture","Declares a runtime semantic the carrier drops.","https:\u002F\u002Fgithub.com\u002Fevent4u-app\u002Fagent-config\u002Fblob\u002Fmain\u002Ftests\u002Fscripts\u002Ffixtures\u002Fbody-portable\u002Fnon-portable\u002FSKILL.md",[118],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[108,120,107,95,121,122,123,98],"non portable fixture","semantic","high","runtime",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":131,"publishedAt":44},"01M6X848F706PT9MDCX75JKJ6B","candidate-zero-width","A candidate whose prose carries an invisible joiner.","https:\u002F\u002Fgithub.com\u002Fevent4u-app\u002Fagent-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-scout-candidates\u002Fzero-width-injection\u002FSKILL.md",[130],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[132,133,134,135],"candidate zero width","candidate","ZeRO","prose",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":143,"publishedAt":44},"01M6X841SSC2T31VDF41SA6DG1","candidate-disclosure-suppression","A candidate whose prose tells the agent to withhold from the user.","https:\u002F\u002Fgithub.com\u002Fevent4u-app\u002Fagent-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-scout-candidates\u002Fdisclosure-suppression\u002FSKILL.md",[142],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[144,133,135,145],"candidate disclosure suppression","user",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":153,"publishedAt":44},"01M6X83TFS5AGPBPVTQNWP0BB3","candidate-dangerous-frontmatter","A candidate claiming an unscoped tool grant and a permission bypass.","https:\u002F\u002Fgithub.com\u002Fevent4u-app\u002Fagent-config\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-scout-candidates\u002Fdangerous-frontmatter\u002FSKILL.md",[152],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[154,133,155,156,157,158],"candidate dangerous frontmatter","frontmatter","shell","permission","tool"]