技能雷达 · GITHUB

值得安装的 Agent Skills。

汇总公开仓库中已验证的 Skills。安装前先看清它能做什么、包内包含什么、热度如何，以及来源是否可靠。

目录范围: 已验证
Skills: 16,139
仓库: 2578
最近同步: 2026年10月14日

16,139 Skills

platform-lightning-app-coordinate

Build complete Salesforce Lightning Experience applications from natural language descriptions. Use this skill when a user requests a \"complete app\", \"Lightning app\", \"business solution\", \"management system\", or describes a scenario requiring multiple interconnected Salesforce components (objects, fields, pages, tabs, security). Orchestrates all required metadata types in proper dependency order to produce a deployable application.

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.01 文件

查看详情 →

platform-lightning-type-widget-coordinate

Orchestrate Apex-backed Lightning Type + HXL widget generation. TRIGGER only when the prompt EXPLICITLY invokes Lightning Types: user says 'Lightning Type', 'CLT', 'Custom Lightning Type', 'Apex-backed type', references '@apexClassType/...', asks to build a widget or card for a named Lightning Type, asks to create a new Lightning Type and widget together, or grounds a widget in a specific Apex class as its schema. DO NOT TRIGGER when the prompt names only a subject, domain, feature, or entity no

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.06 文件

查看详情 →

platform-list-view-generate

Use this skill when users need to create, generate, or validate Salesforce List View metadata. Trigger when users mention list views, filtered record lists, creating views, setting up record columns, filtering records by criteria, or ask about list view visibility. Also use when users say things like \"I need a view that shows...\", \"filter records by...\", \"create a list view for...\", or when they're working with ListView XML files and need validation or troubleshooting.

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.01 文件

查看详情 →

platform-mcp-tool-widget-coordinate

Orchestrate object-based Lightning Type + HXL widget generation to render the output of a custom MCP server tool backed by an Apex Invocable Action. TRIGGER only when the prompt EXPLICITLY involves rendering an MCP tool result: user says 'MCP server', 'MCP tool', 'custom MCP server', references a tool 'output schema' / 'tool output' / 'outputValues' envelope, names an 'invocable action' backing an MCP tool, or asks to build a widget or rich UI rendition for the output of an Apex-invocable-backed

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.010 文件

查看详情 →

platform-models-api-configure

Configure (or troubleshoot) an AI coding agent or CLI to route through the Salesforce Models API using a signed OrgJWT. Use this skill when pointing an agent at the Salesforce model endpoint (api.salesforce.com/ai/gpt/v1), setting up OrgJWT / Bedrock-mode auth, wiring the agent's settings, API-key helper, and credentials file for the Salesforce endpoint, or fixing Models API 401 / 404 / \"model not available\" errors. DO NOT TRIGGER when the user needs to create or configure the Salesforce Conne

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.02 文件

查看详情 →

platform-policy-rule-generate

Use this skill when authoring PolicyRuleDefinition and PolicyRuleDefinitionSet metadata XML for Salesforce Data Cloud governance policies, or when editing .policyRuleDefinition / .policyRuleDefinitionSet files. Covers the category decision tree, full schema for all policy variants (ACCESS, GOVERNANCE, RECORD, TRANSFORM), UI-compatibility rules for the Data Governance Policy Builder, output hygiene for user-facing agent responses, and validation guardrails. Do NOT use this skill for UserAccessPol

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.09 文件

查看详情 →

platform-report-generate

Use this skill when users need to create, generate, or validate Salesforce Lightning Report metadata. Trigger when users mention reports, creating reports, report metadata, .report-meta.xml files, tabular reports, summary reports, matrix reports, joined reports, report columns, report groupings, report filters, report charts, cross-filters, bucket fields, report formulas, or report time frame filters. Also use when users say things like 'create a report', 'generate a report', 'build a report on

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.011 文件

查看详情 →

platform-sandbox-configure

MUST USE this skill for ANY sandbox request — including simply getting a sandbox's details, status, license type, or pending-activation state by name or ID. TRIGGER when the user: types \"sandbox -help\"/\"sandbox help\"; mentions a sandbox ID (07E prefix); asks to list or show sandboxes; asks for the details, status, license type, or config of a sandbox by name or ID; activates or discards a completed refresh; deletes a sandbox; verifies activation or deletion; creates or refreshes a sandbox. D

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.01 文件

查看详情 →

platform-tracing-configure

Generate EventSettings metadata to enable or disable Platform Tracing (TraceSpanEvent publishing) in Event Monitoring. Use this skill for any EventSettings enablePlatformTracing metadata work. TRIGGER when: user mentions Platform Tracing, TraceSpanEvent, enable tracing in Event Monitoring Settings, event monitoring tracing toggle, enablePlatformTracing, .settings-meta.xml for Event settings tracing, turn on trace span events, or stop publishing trace spans. DO NOT TRIGGER when: user wants Agentf

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.02 文件

查看详情 →

platform-trial-org-create

Use this skill to create a Salesforce trial, developer, or Trialforce org against an already-authenticated host org, the same way a developer/Trialforce web signup form provisions one. INVOKE when the user asks to: create a trial org, sign up a new trial or developer org, provision a Trialforce org from a template, or check the status of a trial-org signup they started. Trigger phrases: 'create a trial org', 'sign up a trial org', 'spin up a dev org', 'Trialforce signup', 'provision trial from t

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.08 文件

查看详情 →

platform-trust-archive-manage

ALWAYS USE THIS SKILL for anything involving Salesforce Archive (also called Trusted Services Archive) — search, view, unarchive, analyze, mask, and erase (RTBF) archived records via the Archive Connect API, and reading archive job status from the ArchiveActivity object. TRIGGER when: user mentions Salesforce Archive, Trusted Services Archive, archive/unarchive records, ArchiveActivity, archive jobs, archive policy, archive analyzer, archived record search, archive storage, archive failure logs,

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.04 文件

查看详情 →

platform-widget-generate

Use this skill to author a complete HXL WidgetBundle (UEM body + schema.json + -meta.xml). TRIGGER when: user asks for a widget, mosaic, fragment, card, or rich UI surface for any subject, domain, feature, or entity noun; the prompt names only an entity or data shape without invoking Lightning Types, CLTs, or Apex-backed types. DO NOT TRIGGER when: the prompt explicitly says 'Lightning Type', 'CLT', 'Custom Lightning Type', 'Apex-backed type', or references '@apexClassType/...' (use platform-lig

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.07 文件

查看详情 →

sales-agentforce-pipeline-management-configure

Use to configure, set up, or repair the Sales Management agent and Agentforce Pipeline Management in a Salesforce org. Automates metadata creation for flows, prompt templates, permission sets, and data source configuration. TRIGGER when: user wants to enable Pipeline Management, configure Sales pipeline features, set up the Sales Management agent for opportunity field updates (including autonomous updates), connect enabled data sources like Einstein Conversation Insights or Einstein Activity Cap

安装量: 3
GitHub Stars: 953
最近更新: 9月1日

Apache-2.047 文件

查看详情 →

codex-dynamic-workflows

Plan and run AI-agent dynamic workflows for complex tasks that benefit from explicit orchestration, goal mode, subagents or simulated work packets, approval gates, integration, verification, and reusable workflow artifacts. Use when the user invokes this skill, asks for a swarm, subagents, parallel agents, a dynamic workflow, a large migration or audit, multi-track research plus implementation, or Claude Code-style workflow orchestration.

安装量: 3
GitHub Stars: 524
最近更新: 7月17日

查看详情 →

codex-cli-model-bridge

Install, audit, repair, and manage Codex custom model Providers and model catalogs backed by a loopback CLIProxyAPI or Codex Router. Use whenever the user asks to add, remove, upgrade, restore, or diagnose third-party models in Codex or the Codex desktop model picker; mentions Grok, OpenCode Go, DeepSeek, Gemini, GLM Coding Plan, GLM-5.3, subscription-backed CLI models, custom modelprovider, modelcatalogjson, or Codex Fast mode; or wants the same local proxy models synchronized between Codex and

安装量: 3
GitHub Stars: 435
最近更新: 9月2日

查看详情 →

aim

When data lands with a thin ask — files, a repo, a paste, a chat scrollback — read it and propose what the user is trying to do with it, as a proposal to confirm rather than a question to answer. Use the moment material arrives without a fully-formed ask, or when the ask reads thinner than the data suggests.

安装量: 3
GitHub Stars: 1012
最近更新: 8月18日

查看详情 →

autobahn

Carve guardrail-adjacent items out of scope with safe alternatives before risk-adjacent work starts, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved prompt, never the risky input. Use when a task includes stealth, scraping, privacy, IP, policy, licensing, security, or other safety-adjacent material that could be silently dropped, over-elaborated, or needlessly diluted. Fires on the impulse, not only the topic: the moment you notice yourself about t

安装量: 3
GitHub Stars: 1012
最近更新: 8月18日

查看详情 →

catchup

Rebuild the human's lost context on a project from live state, in plain language: what needs them, what changed, what new words mean. Use when the human returns after a gap, says they can't follow the project anymore, asks what happened or what a term means, or before deciding what to do next when their mental model is stale. Read-only; it briefs, it does not act.

安装量: 3
GitHub Stars: 1012
最近更新: 8月18日

查看详情 →

debloat

Compress an artifact that has accreted into bloat — padding, over-qualification, fused sentences, walls of enumeration, adjacent restatement — down to its load-bearing density, meaning preserved. Use when prose is correct and current but has grown verbose or patched-over and you want it tight without a full rewrite.

安装量: 3
GitHub Stars: 1012
最近更新: 8月18日

查看详情 →

dedash

Remove em-dashes and the dashes standing in for them from a user-owned scope, reading each occurrence in context and choosing the punctuation or wording that fits.

安装量: 3
GitHub Stars: 1012
最近更新: 8月18日

查看详情 →

detool

Make durable artifacts portable by replacing incidental stack, vendor, model, CLI, path, quota, or harness nouns with the mechanism they mean, while keeping provenance, runbooks, and tool-subject claims concrete.

安装量: 3
GitHub Stars: 1012
最近更新: 8月18日

查看详情 →

factchk

Verify reality-grounded claims against external sources in both directions before they ship — could the 'absurd' be real, could the 'obvious' be false or long-established? Use whenever an artifact, or the sentence you are about to write, asserts something as plausible, realistic, absurd, novel, or impossible from intuition rather than a checked source; before relying on a factual claim in prose, a design rationale, a research claim, or a plan. Fires on metacognitive doubt — when you can't actual

安装量: 3
GitHub Stars: 1012
最近更新: 8月18日

查看详情 →

feynman

Press a decision you just made until you can explain it to a skeptic in your own words, or surface the gap where you can't. The Feynman test aimed at a choice: understanding is cheapest to fake the moment after you decide, so a fresh critic presses for what you can't actually explain. Use right after picking an option, especially one an agent laid out without arguing for.

安装量: 3
GitHub Stars: 1012
最近更新: 8月18日

查看详情 →

hate

Attack a plan, design, or argument like you want it to fail before you commit real effort — return the single load-bearing objection and the cheapest experiment that would prove it matters, not a checklist. User-invoked on purpose: a hate-it reflex always in the agent's reach would bias it toward demolition. Weighs many failure axes but owns the synthesis to one root.

安装量: 3
GitHub Stars: 1012
最近更新: 8月18日

查看详情 →