[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CB3PAH79WXP72CMA7B1KWJ":3,"skill-same:01M7CB3PAH79WXP72CMA7B1KWJ":57},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7CB3PAH79WXP72CMA7B1KWJ","sf-ai-agentforce",null,"Agentforce Builder metadata path for Builder-managed topics\u002Factions, Prompt Builder templates, GenAiFunction\u002FGenAiPlugin, Models API, and custom Lightning types. TRIGGER when: user maintains or configures Builder metadata agents, creates topics\u002Factions, works with Prompt Builder templates, or touches .genAiFunction, .genAiPlugin, or .genAiPromptTemplate metadata XML files. DO NOT TRIGGER when: Agent Script DSL .agent files (use sf-ai-agentscript), agent testing (use sf-ai-agentforce-testing), or persona design (use sf-ai-agentforce-persona).","om-scogo\u002Fskillsh-scraper","om-scogo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160466840?v=4","01M79AWB6DFVCQ7RK70CS34B96","Om Achrekar","01M79AWB6ZM9SKR8KDH1WSSM22",0,"MIT","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-ai-agentforce\u002FSkill.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sf-ai-agentforce\ndescription: >\n  Agentforce Builder metadata path for Builder-managed topics\u002Factions, Prompt\n  Builder templates, GenAiFunction\u002FGenAiPlugin, Models API, and custom\n  Lightning types.\n  TRIGGER when: user maintains or configures Builder metadata agents,\n  creates topics\u002Factions, works with Prompt Builder templates, or touches\n  .genAiFunction, .genAiPlugin, or .genAiPromptTemplate metadata XML files.\n  DO NOT TRIGGER when: Agent Script DSL .agent files (use sf-ai-agentscript),\n  agent testing (use sf-ai-agentforce-testing), or persona design\n  (use sf-ai-agentforce-persona).\nlicense: MIT\ncompatibility: \"Requires API v66.0+ (Spring '26)\"\nmetadata:\n  version: \"2.2.0\"\n  author: \"Jag Valaiyapathy\"\n---\n\n# sf-ai-agentforce: Standard Agentforce Platform Development\n\nUse this skill for the **Setup UI \u002F Agent Builder** path: declarative topics, Builder-managed actions, `GenAiFunction` \u002F `GenAiPlugin` metadata, **Prompt Builder templates stored as `GenAiPromptTemplate` metadata**, Models API usage from Apex, and custom Lightning types.\n\n> For new code-first agent development, prefer [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md).\n>\n> If the work produces or edits a `.agent` file — including Builder Script \u002F Canvas work that results in an authoring bundle — use [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md).\n\n## When This Skill Owns the Task\n\nUse `sf-ai-agentforce` when the user is:\n- maintaining existing Builder-based agents\n- working in Setup → Agentforce → Agents\n- creating or fixing `GenAiFunction`, `GenAiPlugin`, or `GenAiPromptTemplate` metadata\n- wiring Builder topics to Flow \u002F Apex \u002F Prompt Builder actions\n- using Models API or LightningTypeBundle in the context of Builder-based agents\n\nDo **not** use it for:\n- `.agent` files or deterministic FSM design → [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md)\n- agent test suites and coverage loops → [sf-ai-agentforce-testing](..\u002Fsf-ai-agentforce-testing\u002FSKILL.md)\n- persona \u002F voice design → [sf-ai-agentforce-persona](..\u002Fsf-ai-agentforce-persona\u002FSKILL.md)\n\n---\n\n## Required Context to Gather First\n\nAsk for or infer:\n- whether this is a Builder \u002F Setup UI project or a code-first Agent Script project\n- whether the user is editing Builder metadata or a `.agent` authoring bundle\n- agent type: Service Agent or Employee Agent\n- whether the work targets topics, actions, Prompt Builder templates, Models API, or custom Lightning types\n- what supporting Flow \u002F Apex \u002F metadata dependencies already exist\n- whether the user needs authoring help, publish help, or troubleshooting\n\n---\n\n## Two Agentforce Paths\n\n| Path | Skill | Best fit |\n|---|---|---|\n| Builder metadata path | `sf-ai-agentforce` | Declarative maintenance, existing Builder agents, metadata-driven action registration |\n| Agent Script authoring bundle path | `sf-ai-agentscript` | Code-first `.agent` authoring, deterministic routing, version-controlled agent logic |\n\nIf the user is starting from scratch and wants strong control over flow\u002Fstate, route to Agent Script.\n\n---\n\n## Builder Workflow Summary\n\n1. Confirm this is a **Builder \u002F Setup UI** project\n2. Pick Service Agent vs Employee Agent\n3. For Service Agents, provision the running user (prefer `sf org create agent-user`)\n4. For Employee Agents, plan visibility with a Permission Set containing `\u003CagentAccesses>`\n5. Define topics with strong descriptions, scope, and instructions\n6. Prepare supporting actions (Flow, Apex, Prompt Builder template)\n7. Configure inputs \u002F outputs carefully\n8. Validate dependencies and template status\n9. Publish, then activate\n\nExpanded workflow: [references\u002Fbuilder-workflow.md](references\u002Fbuilder-workflow.md)\n\n---\n\n## Key Platform Rules\n\n### Topic quality matters\nTopic descriptions are routing instructions for the planner. They must be:\n- specific\n- scenario-based\n- non-overlapping with sibling topics\n\n### Actions are wrappers around real targets\n| Target type | Typical use | Registered via |\n|---|---|---|\n| Flow | safest default for Builder actions | `GenAiFunction` |\n| Apex | complex business logic via `@InvocableMethod` | `GenAiFunction` |\n| Prompt Builder template | generated summaries \u002F drafts \u002F recommendations | `GenAiFunction` |\n\n### Prompt Template vs GenAiPromptTemplate\n- **Prompt Template** is the plain-English \u002F UI term used in Prompt Builder.\n- **`GenAiPromptTemplate`** is the current Metadata API type for source-driven template work.\n- Prefer current source format: `genAiPromptTemplates\u002F*.genAiPromptTemplate-meta.xml`.\n- For flexible Prompt Builder templates, plan around the **5-input maximum** and consolidate inputs when needed.\n- Prompt content should reference inputs with the current merge-field shape, e.g. `{!$Input:TargetRecord}` or `{!$Input:AdditionalContext}`.\n\n### Supporting metadata deploys first\nBefore publishing the agent itself, deploy the supporting stack:\n1. metadata \u002F fields if needed\n2. Apex if needed\n3. Flows if needed\n4. `GenAiPromptTemplate` \u002F `GenAiFunction` \u002F `GenAiPlugin`\n5. then publish the agent\n\n### Service Agent running user\nFor Service Agents, prefer the native GA command:\n`sf org create agent-user --target-org \u003Calias> --json`\nUse the returned username in the running-user configuration.\n\n### Employee Agent visibility\nFor Employee Agents, ensure end users receive a Permission Set containing `\u003CagentAccesses>`. Without this, the agent can be active but still invisible in Lightning Experience.\nSee [..\u002Fsf-permissions\u002Freferences\u002Fagent-access-guide.md](..\u002Fsf-permissions\u002Freferences\u002Fagent-access-guide.md).\n\n### Publish does not activate\nAfter publish, run `sf agent activate` separately.\nFor automation, prefer `sf agent activate --api-name \u003CAgentName> --version \u003Cn> --target-org \u003Calias> --json` so the rollout is deterministic and machine-readable.\n\n---\n\n## Metadata Guidance\n\n### GenAiFunction\nUse when registering a single callable action. Validate:\n- target exists\n- target is active \u002F deployable\n- input names match the target contract\n- output names match the target contract\n- capability text clearly says when the action should be used\n\n### GenAiPlugin\nUse when grouping related functions into one logical package.\n\n### GenAiPromptTemplate\nUse for generated content, not deterministic business rules.\n\nPrefer the current metadata shape:\n- metadata type: `GenAiPromptTemplate`\n- folder: `genAiPromptTemplates\u002F`\n- file suffix: `.genAiPromptTemplate-meta.xml`\n- content lives under `templateVersions`\n- use published template versions before wiring actions that depend on them\n\n### Models API\nUse when the solution belongs in Apex-driven AI orchestration rather than Builder-only actions.\n\n### Custom Lightning Types\nUse when the action needs richer structured input or output presentation.\n\nExpanded references:\n- [references\u002Fmetadata-reference.md](references\u002Fmetadata-reference.md)\n- [references\u002Fgenaiprompttemplate.md](references\u002Fgenaiprompttemplate.md)\n\n---\n\n## Cross-Skill Integration\n\n### Recommended Orchestration Order\n\n```text\nsf-metadata → sf-apex → sf-flow → sf-ai-agentforce → sf-deploy\n```\n\n### Required delegations\n| Requirement | Delegate to | Why |\n|---|---|---|\n| Create \u002F fix Flows | [sf-flow](..\u002Fsf-flow\u002FSKILL.md) | Action target creation and Flow validation |\n| Create \u002F fix Apex actions | [sf-apex](..\u002Fsf-apex\u002FSKILL.md) | `@InvocableMethod` and Apex correctness |\n| Deploy \u002F publish | [sf-deploy](..\u002Fsf-deploy\u002FSKILL.md) | Deployment orchestration |\n| Test the agent | [sf-ai-agentforce-testing](..\u002Fsf-ai-agentforce-testing\u002FSKILL.md) | Formal test execution and assertions |\n| Employee Agent visibility \u002F access | [sf-permissions](..\u002Fsf-permissions\u002FSKILL.md) | Permission Set `\u003CagentAccesses>` setup |\n\n---\n\n## High-Signal Failure Patterns\n\n| Symptom | Likely cause | Read next |\n|---|---|---|\n| Action not available in Builder | target metadata missing or not deployed | [references\u002Fmetadata-reference.md](references\u002Fmetadata-reference.md) |\n| Prompt action fails during publish or activation | template is Draft, missing inputs, or old metadata shape is being used | [references\u002Fgenaiprompttemplate.md](references\u002Fgenaiprompttemplate.md) |\n| Need more than 5 template inputs | flex template input limit hit | [references\u002Fgenaiprompttemplate.md](references\u002Fgenaiprompttemplate.md) |\n| Apex AI logic times out | Models API work placed in the wrong context | [references\u002Fmodels-api.md](references\u002Fmodels-api.md) |\n| Rich input\u002Foutput UI not rendering | Lightning type config or prerequisites are incomplete | [references\u002Fcustom-lightning-types.md](references\u002Fcustom-lightning-types.md) |\n| Agent publishes but is not usable | forgot explicit activation | [references\u002Fcli-commands.md](references\u002Fcli-commands.md) |\n| Service Agent publish\u002Fruntime failure | missing or invalid running user | [..\u002Fsf-ai-agentscript\u002Freferences\u002Fagent-user-setup.md](..\u002Fsf-ai-agentscript\u002Freferences\u002Fagent-user-setup.md) |\n| Employee Agent active but not visible to users | missing `\u003CagentAccesses>` permission set | [..\u002Fsf-permissions\u002Freferences\u002Fagent-access-guide.md](..\u002Fsf-permissions\u002Freferences\u002Fagent-access-guide.md) |\n\n---\n\n## Reference Map\n\n### Start here\n- [references\u002Fbuilder-workflow.md](references\u002Fbuilder-workflow.md)\n- [references\u002Fmetadata-reference.md](references\u002Fmetadata-reference.md)\n- [references\u002Fgenaiprompttemplate.md](references\u002Fgenaiprompttemplate.md)\n- [references\u002Fcli-commands.md](references\u002Fcli-commands.md)\n\n### Terminology and template planning\n- [references\u002Fprompt-templates.md](references\u002Fprompt-templates.md)\n- [references\u002Fmodels-api.md](references\u002Fmodels-api.md)\n- [references\u002Fcustom-lightning-types.md](references\u002Fcustom-lightning-types.md)\n\n### Rubric\n- [references\u002Fscoring-rubric.md](references\u002Fscoring-rubric.md)\n\n### Cross-skill reads\n- [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md)\n- [sf-ai-agentforce-testing](..\u002Fsf-ai-agentforce-testing\u002FSKILL.md)\n- [sf-flow](..\u002Fsf-flow\u002FSKILL.md)\n- [sf-apex](..\u002Fsf-apex\u002FSKILL.md)\n- [sf-permissions](..\u002Fsf-permissions\u002FSKILL.md)\n- [sf-deploy](..\u002Fsf-deploy\u002FSKILL.md)\n\n---\n\n## Score Guide\n\n| Score | Meaning |\n|---|---|\n| 90+ | Ready to deploy |\n| 80–89 | Strong, minor cleanup only |\n| 70–79 | Review before deploy |\n| 60–69 | Needs work |\n| \u003C 60 | Block deployment |\n\nFull rubric: [references\u002Fscoring-rubric.md](references\u002Fscoring-rubric.md)\n","# sf-ai-agentforce: Standard Agentforce Platform Development\n\nUse this skill for the **Setup UI \u002F Agent Builder** path: declarative topics, Builder-managed actions, `GenAiFunction` \u002F `GenAiPlugin` metadata, **Prompt Builder templates stored as `GenAiPromptTemplate` metadata**, Models API usage from Apex, and custom Lightning types.\n\n> For new code-first agent development, prefer [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md).\n>\n> If the work produces or edits a `.agent` file — including Builder Script \u002F Canvas work that results in an authoring bundle — use [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md).\n\n## When This Skill Owns the Task\n\nUse `sf-ai-agentforce` when the user is:\n- maintaining existing Builder-based agents\n- working in Setup → Agentforce → Agents\n- creating or fixing `GenAiFunction`, `GenAiPlugin`, or `GenAiPromptTemplate` metadata\n- wiring Builder topics to Flow \u002F Apex \u002F Prompt Builder actions\n- using Models API or LightningTypeBundle in the context of Builder-based agents\n\nDo **not** use it for:\n- `.agent` files or deterministic FSM design → [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md)\n- agent test suites and coverage loops → [sf-ai-agentforce-testing](..\u002Fsf-ai-agentforce-testing\u002FSKILL.md)\n- persona \u002F voice design → [sf-ai-agentforce-persona](..\u002Fsf-ai-agentforce-persona\u002FSKILL.md)\n\n---\n\n## Required Context to Gather First\n\nAsk for or infer:\n- whether this is a Builder \u002F Setup UI project or a code-first Agent Script project\n- whether the user is editing Builder metadata or a `.agent` authoring bundle\n- agent type: Service Agent or Employee Agent\n- whether the work targets topics, actions, Prompt Builder templates, Models API, or custom Lightning types\n- what supporting Flow \u002F Apex \u002F metadata dependencies already exist\n- whether the user needs authoring help, publish help, or troubleshooting\n\n---\n\n## Two Agentforce Paths\n\n| Path | Skill | Best fit |\n|---|---|---|\n| Builder metadata path | `sf-ai-agentforce` | Declarative maintenance, existing Builder agents, metadata-driven action registration |\n| Agent Script authoring bundle path | `sf-ai-agentscript` | Code-first `.agent` authoring, deterministic routing, version-controlled agent logic |\n\nIf the user is starting from scratch and wants strong control over flow\u002Fstate, route to Agent Script.\n\n---\n\n## Builder Workflow Summary\n\n1. Confirm this is a **Builder \u002F Setup UI** project\n2. Pick Service Agent vs Employee Agent\n3. For Service Agents, provision the running user (prefer `sf org create agent-user`)\n4. For Employee Agents, plan visibility with a Permission Set containing `\u003CagentAccesses>`\n5. Define topics with strong descriptions, scope, and instructions\n6. Prepare supporting actions (Flow, Apex, Prompt Builder template)\n7. Configure inputs \u002F outputs carefully\n8. Validate dependencies and template status\n9. Publish, then activate\n\nExpanded workflow: [references\u002Fbuilder-workflow.md](references\u002Fbuilder-workflow.md)\n\n---\n\n## Key Platform Rules\n\n### Topic quality matters\nTopic descriptions are routing instructions for the planner. They must be:\n- specific\n- scenario-based\n- non-overlapping with sibling topics\n\n### Actions are wrappers around real targets\n| Target type | Typical use | Registered via |\n|---|---|---|\n| Flow | safest default for Builder actions | `GenAiFunction` |\n| Apex | complex business logic via `@InvocableMethod` | `GenAiFunction` |\n| Prompt Builder template | generated summaries \u002F drafts \u002F recommendations | `GenAiFunction` |\n\n### Prompt Template vs GenAiPromptTemplate\n- **Prompt Template** is the plain-English \u002F UI term used in Prompt Builder.\n- **`GenAiPromptTemplate`** is the current Metadata API type for source-driven template work.\n- Prefer current source format: `genAiPromptTemplates\u002F*.genAiPromptTemplate-meta.xml`.\n- For flexible Prompt Builder templates, plan around the **5-input maximum** and consolidate inputs when needed.\n- Prompt content should reference inputs with the current merge-field shape, e.g. `{!$Input:TargetRecord}` or `{!$Input:AdditionalContext}`.\n\n### Supporting metadata deploys first\nBefore publishing the agent itself, deploy the supporting stack:\n1. metadata \u002F fields if needed\n2. Apex if needed\n3. Flows if needed\n4. `GenAiPromptTemplate` \u002F `GenAiFunction` \u002F `GenAiPlugin`\n5. then publish the agent\n\n### Service Agent running user\nFor Service Agents, prefer the native GA command:\n`sf org create agent-user --target-org \u003Calias> --json`\nUse the returned username in the running-user configuration.\n\n### Employee Agent visibility\nFor Employee Agents, ensure end users receive a Permission Set containing `\u003CagentAccesses>`. Without this, the agent can be active but still invisible in Lightning Experience.\nSee [..\u002Fsf-permissions\u002Freferences\u002Fagent-access-guide.md](..\u002Fsf-permissions\u002Freferences\u002Fagent-access-guide.md).\n\n### Publish does not activate\nAfter publish, run `sf agent activate` separately.\nFor automation, prefer `sf agent activate --api-name \u003CAgentName> --version \u003Cn> --target-org \u003Calias> --json` so the rollout is deterministic and machine-readable.\n\n---\n\n## Metadata Guidance\n\n### GenAiFunction\nUse when registering a single callable action. Validate:\n- target exists\n- target is active \u002F deployable\n- input names match the target contract\n- output names match the target contract\n- capability text clearly says when the action should be used\n\n### GenAiPlugin\nUse when grouping related functions into one logical package.\n\n### GenAiPromptTemplate\nUse for generated content, not deterministic business rules.\n\nPrefer the current metadata shape:\n- metadata type: `GenAiPromptTemplate`\n- folder: `genAiPromptTemplates\u002F`\n- file suffix: `.genAiPromptTemplate-meta.xml`\n- content lives under `templateVersions`\n- use published template versions before wiring actions that depend on them\n\n### Models API\nUse when the solution belongs in Apex-driven AI orchestration rather than Builder-only actions.\n\n### Custom Lightning Types\nUse when the action needs richer structured input or output presentation.\n\nExpanded references:\n- [references\u002Fmetadata-reference.md](references\u002Fmetadata-reference.md)\n- [references\u002Fgenaiprompttemplate.md](references\u002Fgenaiprompttemplate.md)\n\n---\n\n## Cross-Skill Integration\n\n### Recommended Orchestration Order\n\n```text\nsf-metadata → sf-apex → sf-flow → sf-ai-agentforce → sf-deploy\n```\n\n### Required delegations\n| Requirement | Delegate to | Why |\n|---|---|---|\n| Create \u002F fix Flows | [sf-flow](..\u002Fsf-flow\u002FSKILL.md) | Action target creation and Flow validation |\n| Create \u002F fix Apex actions | [sf-apex](..\u002Fsf-apex\u002FSKILL.md) | `@InvocableMethod` and Apex correctness |\n| Deploy \u002F publish | [sf-deploy](..\u002Fsf-deploy\u002FSKILL.md) | Deployment orchestration |\n| Test the agent | [sf-ai-agentforce-testing](..\u002Fsf-ai-agentforce-testing\u002FSKILL.md) | Formal test execution and assertions |\n| Employee Agent visibility \u002F access | [sf-permissions](..\u002Fsf-permissions\u002FSKILL.md) | Permission Set `\u003CagentAccesses>` setup |\n\n---\n\n## High-Signal Failure Patterns\n\n| Symptom | Likely cause | Read next |\n|---|---|---|\n| Action not available in Builder | target metadata missing or not deployed | [references\u002Fmetadata-reference.md](references\u002Fmetadata-reference.md) |\n| Prompt action fails during publish or activation | template is Draft, missing inputs, or old metadata shape is being used | [references\u002Fgenaiprompttemplate.md](references\u002Fgenaiprompttemplate.md) |\n| Need more than 5 template inputs | flex template input limit hit | [references\u002Fgenaiprompttemplate.md](references\u002Fgenaiprompttemplate.md) |\n| Apex AI logic times out | Models API work placed in the wrong context | [references\u002Fmodels-api.md](references\u002Fmodels-api.md) |\n| Rich input\u002Foutput UI not rendering | Lightning type config or prerequisites are incomplete | [references\u002Fcustom-lightning-types.md](references\u002Fcustom-lightning-types.md) |\n| Agent publishes but is not usable | forgot explicit activation | [references\u002Fcli-commands.md](references\u002Fcli-commands.md) |\n| Service Agent publish\u002Fruntime failure | missing or invalid running user | [..\u002Fsf-ai-agentscript\u002Freferences\u002Fagent-user-setup.md](..\u002Fsf-ai-agentscript\u002Freferences\u002Fagent-user-setup.md) |\n| Employee Agent active but not visible to users | missing `\u003CagentAccesses>` permission set | [..\u002Fsf-permissions\u002Freferences\u002Fagent-access-guide.md](..\u002Fsf-permissions\u002Freferences\u002Fagent-access-guide.md) |\n\n---\n\n## Reference Map\n\n### Start here\n- [references\u002Fbuilder-workflow.md](references\u002Fbuilder-workflow.md)\n- [references\u002Fmetadata-reference.md](references\u002Fmetadata-reference.md)\n- [references\u002Fgenaiprompttemplate.md](references\u002Fgenaiprompttemplate.md)\n- [references\u002Fcli-commands.md](references\u002Fcli-commands.md)\n\n### Terminology and template planning\n- [references\u002Fprompt-templates.md](references\u002Fprompt-templates.md)\n- [references\u002Fmodels-api.md](references\u002Fmodels-api.md)\n- [references\u002Fcustom-lightning-types.md](references\u002Fcustom-lightning-types.md)\n\n### Rubric\n- [references\u002Fscoring-rubric.md](references\u002Fscoring-rubric.md)\n\n### Cross-skill reads\n- [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md)\n- [sf-ai-agentforce-testing](..\u002Fsf-ai-agentforce-testing\u002FSKILL.md)\n- [sf-flow](..\u002Fsf-flow\u002FSKILL.md)\n- [sf-apex](..\u002Fsf-apex\u002FSKILL.md)\n- [sf-permissions](..\u002Fsf-permissions\u002FSKILL.md)\n- [sf-deploy](..\u002Fsf-deploy\u002FSKILL.md)\n\n---\n\n## Score Guide\n\n| Score | Meaning |\n|---|---|\n| 90+ | Ready to deploy |\n| 80–89 | Strong, minor cleanup only |\n| 70–79 | Review before deploy |\n| 60–69 | Needs work |\n| \u003C 60 | Block deployment |\n\nFull rubric: [references\u002Fscoring-rubric.md](references\u002Fscoring-rubric.md)\n",{"name":5,"license":15,"metadata":24,"description":27,"compatibility":28},{"author":25,"version":26},"Jag Valaiyapathy","2.2.0","Agentforce Builder metadata path for Builder-managed topics\u002Factions, Prompt Builder templates, GenAiFunction\u002FGenAiPlugin, Models API, and custom Lightning types. TRIGGER when: user maintains or configures Builder metadata agents, creates topics\u002Factions, works with Prompt Builder templates, or touches .genAiFunction, .genAiPlugin, or .genAiPromptTemplate metadata XML files. DO NOT TRIGGER when: Agent Script DSL .agent files (use sf-ai-agentscript), agent testing (use sf-ai-agentforce-testing), or persona design (use sf-ai-agentforce-persona).\n","Requires API v66.0+ (Spring '26)","main","8859218955d9504cd18b59e7892100718039d3b4","data\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-ai-agentforce",1,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper","https:\u002F\u002Fgithub.com\u002Fom-scogo","SDE-1 @ Scogo ","2026-07-18 12:22:46",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add om-scogo\u002Fskillsh-scraper --skill sf-ai-agentforce",{"tool":43,"command":44},"bunx","bunx skills add om-scogo\u002Fskillsh-scraper --skill sf-ai-agentforce",{"tool":46,"command":47},"pnpm","pnpm dlx skills add om-scogo\u002Fskillsh-scraper --skill sf-ai-agentforce","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-ai-agentforce\u002FSkill.md",true,[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"metadata.json","REFERENCE","参考文档",439,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-ai-agentforce\u002Fmetadata.json",[58,65,70,77,82,89],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7D6MC9FAAEV4CMNYX8W7JTG","arxiv-search","Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002Fskills\u002Farxiv-search\u002FSKILL.md",[],[],{"skillNo":66,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7D6M85CKKN87TA98VCQV4H7","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002FSkill.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7D4ZTCS4DR3CE4JY06X84T2","working-with-legacy-code","Safely change and test untested codebases using Feathers' \"Working Effectively with Legacy Code\". Use when the user mentions \"legacy code\", \"no tests\", \"untested codebase\", \"how do I test this\", \"seams\", \"characterization tests\", \"golden master\", \"sprout method\", \"afraid to change this code\", \"monster method\", \"dependency breaking\", or \"inherited a messy codebase\". Also trigger when changing code without tests safely, getting a class under test when constructors, statics, or singletons block it, adding features to tangled modules, or planning incremental test coverage for an old codebase. Covers the legacy-code change algorithm, seams, characterization tests, sprout\u002Fwrap, and dependency-breaking techniques. For refactoring code that already has tests, see refactoring-patterns. For day-to-day code quality, see clean-code.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002Fworking-with-legacy-code\u002FSKILL.md",[],[],{"skillNo":78,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7D4ZHZKJD2RSNGAF63V14P4","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002FSkill.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7D4ZB4CJBFW5JE67CPH2QRV","web-typography","Select, pair, and implement typefaces for web projects. Use when the user mentions \"font pairing\", \"which typeface\", \"line height\", \"responsive typography\", \"web font loading\", \"type hierarchy\", \"variable fonts\", \"FOUT\u002FFOIT\", \"typographic scale\", or \"the text is hard to read\". Also trigger when choosing between system fonts and web fonts, optimizing font-loading performance, or designing readable long-form content. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002Fweb-typography\u002FSKILL.md",[],[],{"skillNo":90,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7D4Z4MVYVY3NMJ18BNV6WNA","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002FSkill.md",[],[]]