opencode-skills-collection 4.0.26 → 4.0.28

package/bundled-skills/.antigravity-install-manifest.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "updatedAt": "2026-08-09T00:46:22.025Z",
+  "updatedAt": "2026-08-11T00:48:21.801Z",
   "entries": [
     "00-andruia-consultant",
     "007",
@@ -1371,6 +1371,7 @@
     "pdf-official",
     "pentest-checklist",
     "pentest-commands",
+    "people-data",
     "performance-engineer",
     "performance-optimization",
     "performance-optimizer",
@@ -1832,6 +1833,7 @@
     "train-sentence-transformers",
     "transformers-js",
     "travel-health-analyzer",
+    "travel-planner",
     "tree-ring-memory",
     "trello-automation",
     "triage",

package/bundled-skills/context-agent/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: context-agent
 description: Agente de contexto para continuidade entre sessoes. Salva resumos, decisoes, tarefas pendentes e carrega briefing automatico na sessao seguinte.
-risk: safe
+risk: critical
 source: community
 date_added: '2026-03-06'
 author: renat
@@ -20,26 +20,36 @@ tools:
 
 # Context Agent
 
-## Overview
+> Este guia e intencionalmente escrito em portugues brasileiro. O cabecalho
+> Os cabecalhos `When to Use` e `Limitations` permanecem em ingles apenas para
+> compatibilidade com a descoberta e a validacao automatica do catalogo.
+
+> [!WARNING]
+> Esta skill escreve contexto, registros, um banco SQLite e `MEMORY.md` em
+> caminhos locais; a manutencao tambem pode arquivar e remover resumos antigos.
+> Confirme os caminhos, mantenha um backup e obtenha aprovacao explicita antes
+> de executar `init`, `save`, `archive` ou `maintain`.
+
+## Visao Geral
 
 Agente de contexto para continuidade entre sessoes. Salva resumos, decisoes, tarefas pendentes e carrega briefing automatico na sessao seguinte.
 
 ## When to Use This Skill
 
-- When the user mentions "salvar contexto" or related topics
-- When the user mentions "salva o contexto" or related topics
-- When the user mentions "proxima sessao" or related topics
-- When the user mentions "briefing sessao" or related topics
-- When the user mentions "resumo sessao" or related topics
-- When the user mentions "continuidade sessao" or related topics
+- Quando o usuario mencionar "salvar contexto" ou assuntos relacionados
+- Quando o usuario mencionar "salva o contexto" ou assuntos relacionados
+- Quando o usuario mencionar "proxima sessao" ou assuntos relacionados
+- Quando o usuario mencionar "briefing sessao" ou assuntos relacionados
+- Quando o usuario mencionar "resumo sessao" ou assuntos relacionados
+- Quando o usuario mencionar "continuidade sessao" ou assuntos relacionados
 
-## Do Not Use This Skill When
+## Quando Nao Usar Esta Skill
 
-- The task is unrelated to context agent
-- A simpler, more specific tool can handle the request
-- The user needs general-purpose assistance without domain expertise
+- A tarefa nao estiver relacionada a continuidade de contexto
+- Uma ferramenta mais simples e especifica puder atender ao pedido
+- O usuario precisar apenas de assistencia geral, sem esta especializacao
 
-## How It Works
+## Como Funciona
 
 Continuidade perfeita entre sessões do Claude Code. Captura, comprime e
 restaura contexto automaticamente — tópicos, decisões, tarefas, erros,
@@ -171,23 +181,27 @@ e decisões tomadas — sem precisar de nenhuma ação manual.
 - Para formato detalhado dos arquivos: `references/context-format.md`
 - Para regras de compressão e arquivamento: `references/compression-rules.md`
 
-## Best Practices
+## Boas Praticas
 
-- Provide clear, specific context about your project and requirements
-- Review all suggestions before applying them to production code
-- Combine with other complementary skills for comprehensive analysis
+- Forneca contexto claro e especifico sobre o projeto e seus requisitos
+- Revise todas as sugestoes antes de aplica-las em codigo de producao
+- Combine esta skill com outras skills complementares quando necessario
 
-## Common Pitfalls
+## Armadilhas Comuns
 
-- Using this skill for tasks outside its domain expertise
-- Applying recommendations without understanding your specific context
-- Not providing enough project context for accurate analysis
+- Usar esta skill em tarefas fora de seu dominio
+- Aplicar recomendacoes sem entender o contexto especifico
+- Fornecer contexto insuficiente para uma analise precisa
 
-## Related Skills
+## Skills Relacionadas
 
-- `context-guardian` - Complementary skill for enhanced analysis
+- `context-guardian` - Skill complementar para preservar contexto antes da compactacao
 
 ## Limitations
-- Use this skill only when the task clearly matches the scope described above.
-- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
-- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
+
+- Use esta skill somente quando a tarefa corresponder claramente ao escopo acima.
+- A implementacao incluida usa caminhos absolutos especificos do Windows e do
+  autor; adapte e valide todos os caminhos antes de qualquer execucao.
+- Nao trate a saida como substituta de validacao, testes ou revisao especializada.
+- Pare e peca esclarecimentos quando faltarem entradas, permissoes, limites de
+  seguranca ou criterios de sucesso.

package/bundled-skills/context-driven-development/SKILL.md

@@ -20,7 +20,8 @@ Guide for implementing and maintaining context as a managed artifact alongside c
 - Clarify goals, constraints, and required inputs.
 - Apply relevant best practices and validate outcomes.
 - Provide actionable steps and verification.
-- If detailed examples are required, open `resources/implementation-playbook.md`.
+- Use the workflow, artifact relationships, and validation checklist below when
+  detailed implementation guidance is required.
 
 ## Use this skill when
 

package/bundled-skills/context-guardian/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: context-guardian
 description: Guardiao de contexto que preserva dados criticos antes da compactacao automatica. Snapshots, verificacao de integridade e zero perda de informacao.
-risk: safe
+risk: critical
 source: community
 date_added: '2026-03-06'
 author: renat
@@ -20,26 +20,36 @@ tools:
 
 # Context Guardian
 
-## Overview
+> Este guia e intencionalmente escrito em portugues brasileiro. O cabecalho
+> Os cabecalhos `When to Use` e `Limitations` permanecem em ingles apenas para
+> compatibilidade com a descoberta e a validacao automatica do catalogo.
+
+> [!WARNING]
+> Esta skill cria snapshots e pode remove-los durante a poda. Confirme o
+> diretorio de dados, mantenha um backup e obtenha aprovacao explicita antes de
+> executar `save` ou `prune`; nunca presuma autorizacao para alterar `MEMORY.md`
+> ou outros arquivos de contexto do usuario.
+
+## Visao Geral
 
 Guardiao de contexto que preserva dados criticos antes da compactacao automatica. Snapshots, verificacao de integridade e zero perda de informacao.
 
 ## When to Use This Skill
 
-- When the user mentions "compactacao contexto" or related topics
-- When the user mentions "perda de contexto" or related topics
-- When the user mentions "snapshot contexto" or related topics
-- When the user mentions "preservar contexto" or related topics
-- When the user mentions "contexto critico" or related topics
-- When the user mentions "antes de compactar" or related topics
+- Quando o usuario mencionar "compactacao contexto" ou assuntos relacionados
+- Quando o usuario mencionar "perda de contexto" ou assuntos relacionados
+- Quando o usuario mencionar "snapshot contexto" ou assuntos relacionados
+- Quando o usuario mencionar "preservar contexto" ou assuntos relacionados
+- Quando o usuario mencionar "contexto critico" ou assuntos relacionados
+- Quando o usuario mencionar "antes de compactar" ou assuntos relacionados
 
-## Do Not Use This Skill When
+## Quando Nao Usar Esta Skill
 
-- The task is unrelated to context guardian
-- A simpler, more specific tool can handle the request
-- The user needs general-purpose assistance without domain expertise
+- A tarefa nao estiver relacionada a preservacao de contexto
+- Uma ferramenta mais simples e especifica puder atender ao pedido
+- O usuario precisar apenas de assistencia geral, sem esta especializacao
 
-## How It Works
+## Como Funciona
 
 Sistema de integridade de contexto que protege projetos tecnicoss complexos contra
 perda de informacao durante compactacao automatica do Claude Code. Enquanto o
@@ -303,23 +313,28 @@ Proximo Claude continua com precisao total, zero re-trabalho.
   mesmo se uma camada falhar, as outras duas preservam a informacao
 - Snapshots antigos (>10) podem ser podados manualmente
 
-## Best Practices
+## Boas Praticas
 
-- Provide clear, specific context about your project and requirements
-- Review all suggestions before applying them to production code
-- Combine with other complementary skills for comprehensive analysis
+- Forneca contexto claro e especifico sobre o projeto e seus requisitos
+- Revise todas as sugestoes antes de aplica-las em codigo de producao
+- Combine esta skill com outras skills complementares quando necessario
 
-## Common Pitfalls
+## Armadilhas Comuns
 
-- Using this skill for tasks outside its domain expertise
-- Applying recommendations without understanding your specific context
-- Not providing enough project context for accurate analysis
+- Usar esta skill em tarefas fora de seu dominio
+- Aplicar recomendacoes sem entender o contexto especifico
+- Fornecer contexto insuficiente para uma analise precisa
 
-## Related Skills
+## Skills Relacionadas
 
-- `context-agent` - Complementary skill for enhanced analysis
+- `context-agent` - Skill complementar para persistencia entre sessoes
 
 ## Limitations
-- Use this skill only when the task clearly matches the scope described above.
-- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
-- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
+
+- Use esta skill somente quando a tarefa corresponder claramente ao escopo acima.
+- Os exemplos de integracao usam caminhos absolutos especificos do Windows e do
+  autor; adapte e valide todos os caminhos antes de qualquer execucao.
+- O script cria arquivos e a operacao `prune` remove snapshots antigos; exija
+  aprovacao para o caminho exato e preserve um backup recuperavel.
+- Pare e peca esclarecimentos quando faltarem entradas, permissoes, limites de
+  seguranca ou criterios de sucesso.

package/bundled-skills/context-window-management/SKILL.md

@@ -46,6 +46,7 @@ Different strategies based on context size
 
 **When to use**: Building any multi-turn conversation system
 
+```typescript
 interface ContextTier {
     maxTokens: number;
     strategy: 'full' | 'summarize' | 'rag';
@@ -86,6 +87,7 @@ async function prepareContext(messages: Message[]): PreparedContext {
             return { messages: [...relevant, ...recentMessages(messages)], model: tier.model };
     }
 }
+```
 
 ### Serial Position Optimization
 
@@ -93,6 +95,7 @@ Place important content at start and end
 
 **When to use**: Constructing prompts with significant context
 
+```typescript
 // LLMs weight beginning and end more heavily
 // Structure prompts to leverage this
 
@@ -131,6 +134,7 @@ function buildOptimalPrompt(components: {
 
     return parts.join('\n\n');
 }
+```
 
 ### Intelligent Summarization
 
@@ -138,6 +142,7 @@ Summarize by importance, not just recency
 
 **When to use**: Context exceeds optimal size
 
+```typescript
 interface MessageWithMetadata extends Message {
     importance: number;  // 0-1 score
     hasCriticalInfo: boolean;  // User preferences, decisions
@@ -186,6 +191,7 @@ async function smartSummarize(
     // Restore original order
     return keep.sort((a, b) => a.timestamp - b.timestamp);
 }
+```
 
 ### Token Budget Allocation
 
@@ -193,6 +199,7 @@ Allocate token budget across context components
 
 **When to use**: Need predictable context management
 
+```typescript
 interface TokenBudget {
     system: number;      // System prompt
     criticalContext: number;  // User prefs, key info
@@ -241,6 +248,7 @@ async function buildWithBudget(
 
     return prepared;
 }
+```
 
 ## Validation Checks
 

package/bundled-skills/conversation-memory/SKILL.md

@@ -8,7 +8,6 @@ date_added: 2026-02-27
 ---
 
 # Conversation Memory
-
 Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory
 
 ## Capabilities
@@ -46,16 +45,14 @@ Different memory tiers for different purposes
 
 **When to use**: Building any conversational AI
 
+```typescript
 interface MemorySystem {
     // Buffer: Current conversation (in context)
     buffer: ConversationBuffer;
-
     // Short-term: Recent interactions (session)
     shortTerm: ShortTermMemory;
-
     // Long-term: Persistent across sessions
     longTerm: LongTermMemory;
-
     // Entity: Facts about people, places, things
     entity: EntityMemory;
 }
@@ -64,13 +61,11 @@ class TieredMemory implements MemorySystem {
     async addMessage(message: Message): Promise<void> {
         // Always add to buffer
         this.buffer.add(message);
-
         // Extract entities
         const entities = await extractEntities(message);
         for (const entity of entities) {
             await this.entity.upsert(entity);
         }
-
         // Check for memorable content
         if (await isMemoryWorthy(message)) {
             await this.shortTerm.add({
@@ -94,21 +89,18 @@ class TieredMemory implements MemorySystem {
 
     async buildContext(query: string): Promise<string> {
         const parts: string[] = [];
-
         // Relevant long-term memories
         const longTermRelevant = await this.longTerm.search(query, 3);
         if (longTermRelevant.length) {
             parts.push('## Relevant Memories\n' +
                 longTermRelevant.map(m => `- ${m.content}`).join('\n'));
         }
-
         // Relevant entities
         const entities = await this.entity.getRelevant(query);
         if (entities.length) {
             parts.push('## Known Entities\n' +
                 entities.map(e => `- ${e.name}: ${e.facts.join(', ')}`).join('\n'));
         }
-
         // Recent conversation
         const recent = this.buffer.getRecent(10);
         parts.push('## Recent Conversation\n' + formatMessages(recent));
@@ -116,6 +108,7 @@ class TieredMemory implements MemorySystem {
         return parts.join('\n\n');
     }
 }
+```
 
 ### Entity Memory
 
@@ -123,6 +116,7 @@ Store and update facts about entities
 
 **When to use**: Need to remember details about people, places, things
 
+```typescript
 interface Entity {
     id: string;
     name: string;
@@ -131,7 +125,6 @@ interface Entity {
     lastMentioned: number;
     mentionCount: number;
 }
-
 interface Fact {
     content: string;
     confidence: number;
@@ -150,7 +143,6 @@ class EntityMemory {
 
             Message: "${message.content}"
         `);
-
         const { entities } = JSON.parse(extraction);
         for (const entity of entities) {
             await this.upsert(entity, message.id);
@@ -159,7 +151,6 @@ class EntityMemory {
 
     async upsert(entity: ExtractedEntity, sourceId: string): Promise<void> {
         const existing = await this.store.get(entity.name.toLowerCase());
-
         if (existing) {
             // Merge facts, avoiding duplicates
             for (const fact of entity.facts) {
@@ -193,6 +184,7 @@ class EntityMemory {
         }
     }
 }
+```
 
 ### Memory-Aware Prompting
 
@@ -200,6 +192,7 @@ Include relevant memories in prompts
 
 **When to use**: Making LLM calls with memory context
 
+```typescript
 async function promptWithMemory(
     query: string,
     memory: MemorySystem,
@@ -237,6 +230,7 @@ ${query}
 
     return response;
 }
+```
 
 ## Sharp Edges
 
@@ -258,6 +252,7 @@ Retrieval over millions of items.
 
 Recommended fix:
 
+```typescript
 // Implement memory lifecycle management
 
 class ManagedMemory {
@@ -309,6 +304,7 @@ class ManagedMemory {
         return Object.values(factors).reduce((a, b) => a + b, 0);
     }
 }
+```
 
 ### Retrieved memories not relevant to current query
 
@@ -328,6 +324,7 @@ Including all retrieved memories.
 
 Recommended fix:
 
+```typescript
 // Intelligent memory retrieval
 
 async function retrieveRelevant(
@@ -357,6 +354,7 @@ async function retrieveRelevant(
         .sort((a, b) => b.relevance - a.relevance)
         .slice(0, maxResults);
 }
+```
 
 ### Memories from one user accessible to another
 
@@ -376,6 +374,7 @@ Cross-user retrieval.
 
 Recommended fix:
 
+```typescript
 // Strict user isolation in memory
 
 class IsolatedMemory {
@@ -426,6 +425,7 @@ class IsolatedMemory {
         }
     }
 }
+```
 
 ## Validation Checks
 

package/bundled-skills/docs/integrations/jetski-cortex.md

@@ -1,9 +1,9 @@
 ---
 title: Jetski/Cortex + Gemini Integration Guide
-description: "Use agentic-awesome-skills with Jetski/Cortex without hitting context-window overflow with 2,005+ skills."
+description: "Use agentic-awesome-skills with Jetski/Cortex without hitting context-window overflow with 2,007+ skills."
 ---
 
-# Jetski/Cortex + Gemini: safe integration with 2,005+ skills
+# Jetski/Cortex + Gemini: safe integration with 2,007+ skills
 
 > **Custom-host integration:** This guide documents a low-level, direct-manifest lazy loader for Jetski/Cortex and similar hosts. For Codex or Claude Code, the recommended path is [AAS Core](../users/aas-core.md), which provides neutral, deterministic catalog retrieval and validates exact agent-selected IDs through a bounded, read-only MCP server.
 
@@ -25,7 +25,7 @@ Never do:
 - concatenate all `SKILL.md` content into a single system prompt;
 - re-inject the entire library for **every** request.
 
-With 2,005+ skills, this approach fills the context window before user messages are even added, causing truncation.
+With 2,007+ skills, this approach fills the context window before user messages are even added, causing truncation.
 
 ---
 

package/bundled-skills/docs/integrations/jetski-gemini-loader/README.md

@@ -23,7 +23,7 @@ This example shows one way to integrate **agentic-awesome-skills** with a Jetski
 - How to enforce a **maximum number of skills per turn** via `maxSkillsPerTurn`.
 - How to choose whether to **truncate or error** when too many skills are requested via `overflowBehavior`.
 
-This pattern avoids context overflow when you have 2,005+ skills installed.
+This pattern avoids context overflow when you have 2,007+ skills installed.
 
 Manifest contract references:
 

package/bundled-skills/docs/maintainers/repo-growth-seo.md

@@ -29,7 +29,7 @@ Preferred homepage:
 Preferred social preview:
 
 - lead with `AAS Core` and the profile → stack → plan flow;
-- present `2,005+ Agentic Skills` as supporting catalog evidence, not a second product;
+- present `2,007+ Agentic Skills` as supporting catalog evidence, not a second product;
 - mention Codex and Claude as the current Core agent path, with broader host compatibility as distribution support;
 - avoid dense text and tiny logos that disappear in social cards.
 

package/bundled-skills/docs/maintainers/skills-update-guide.md

@@ -72,7 +72,7 @@ The update process refreshes:
 - Canonical skills index (`skills_index.json`)
 - Compatibility mirror (`data/skills_index.json`)
 - Web app skills data (`apps\web-app\public\skills.json`)
-- All 2,005+ skills from the skills directory
+- All 2,007+ skills from the skills directory
 
 ## When to Update
 

package/bundled-skills/docs/users/aas-core.md

@@ -30,7 +30,7 @@ AAS MCP does not scan the repository and does not decide which skills are best.
 > **Release boundary:** AAS Core landed after release 14.6.0. Use an exact Core-capable release rather than an unreviewed moving tag.
 
 ```bash
-npm exec --yes --ignore-scripts --package=agentic-awesome-skills@15.11.0 -- aas mcp configure \
+npm exec --yes --ignore-scripts --package=agentic-awesome-skills@15.12.0 -- aas mcp configure \
   --host codex \
   --scope user \
   --config /absolute/path/to/codex/config.toml \

package/bundled-skills/docs/users/bundles.md

@@ -1064,4 +1064,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open
 
 ---
 
-_Last updated: June 2026 | Total Skills: 2,005+ | Total Bundles: 58_
+_Last updated: June 2026 | Total Skills: 2,007+ | Total Bundles: 58_

package/bundled-skills/docs/users/claude-code-skills.md

@@ -17,7 +17,7 @@ Configure AAS Core for Claude Code, describe the task and constraints, let Claud
 - It lets Claude search the verified local catalog without loading the full library into context.
 - It preserves Claude's exact selection without using metadata as an eligibility gate.
 - It keeps MCP discovery read-only and CLI changes approval-gated.
-- It includes 2,005+ skills instead of a narrow single-domain starter pack.
+- It includes 2,007+ skills instead of a narrow single-domain starter pack.
 - It supports the standard `.claude/skills/` path and the Claude Code plugin marketplace flow.
 - It also ships generated bundle plugins so teams can install focused packs like `Essentials` or `Security Developer` from the marketplace metadata.
 - It includes onboarding docs, bundles, and workflows so new users do not need to guess where to begin.

package/bundled-skills/docs/users/gemini-cli-skills.md

@@ -12,7 +12,7 @@ Install into the Gemini skills path, then ask Gemini to apply one skill at a tim
 
 - It installs directly into the expected Gemini skills path.
 - It includes both core software engineering skills and deeper agent/LLM-oriented skills.
-- It helps new users get started with bundles and workflows rather than forcing a cold start from 2,005+ files.
+- It helps new users get started with bundles and workflows rather than forcing a cold start from 2,007+ files.
 - It is useful whether you want a broad internal skill library or a single repo to test many workflows quickly.
 
 ## Install Gemini CLI Skills

package/bundled-skills/docs/users/kiro-integration.md

@@ -18,7 +18,7 @@ Kiro is AWS's agentic AI IDE that combines:
 
 Kiro's agentic capabilities are enhanced by skills that provide:
 
-- **Domain expertise** across 2,005+ specialized areas
+- **Domain expertise** across 2,007+ specialized areas
 - **Best practices** from Anthropic, OpenAI, Google, Microsoft, and AWS
 - **Workflow automation** for common development tasks
 - **AWS-specific patterns** for serverless, infrastructure, and cloud architecture

package/bundled-skills/docs/users/usage.md

@@ -39,7 +39,7 @@ If you came in through a **Claude Code** or **Codex** plugin instead of AAS Core
 
 When you ran `npx agentic-awesome-skills` or cloned the repository, you:
 
-✅ **Downloaded 2,005+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
+✅ **Downloaded 2,007+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
 ✅ **Made them available** to your AI assistant
 ❌ **Did NOT enable them all automatically** (they're just sitting there, waiting)
 
@@ -231,7 +231,7 @@ Let's actually use a skill right now. Follow these steps:
 
 ## Direct-install Step 5: Pick Skills Manually
 
-Don't try to use all 2,005+ skills at once. Here's a sensible approach:
+Don't try to use all 2,007+ skills at once. Here's a sensible approach:
 
 If you want a tool-specific starting point before choosing skills, use:
 
@@ -362,7 +362,7 @@ Usually no, but if your AI doesn't recognize a skill:
 
 ### "Can I load all skills into the model at once?"
 
-No. Even though you have 2,005+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
+No. Even though you have 2,007+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
 
 The intended pattern is:
 

package/bundled-skills/docs/users/visual-guide.md

@@ -40,7 +40,7 @@ agentic-awesome-skills/
 ├── 📄 CONTRIBUTING.md                  ← Contributor workflow
 ├── 📄 CATALOG.md                       ← Full generated catalog
 │
-├── 📁 skills/                          ← 2,005+ skills live here
+├── 📁 skills/                          ← 2,007+ skills live here
 │   │
 │   ├── 📁 brainstorming/
 │   │   └── 📄 SKILL.md                 ← Skill definition
@@ -53,7 +53,7 @@ agentic-awesome-skills/
 │   │   └── 📁 2d-games/
 │   │       └── 📄 SKILL.md             ← Nested skills also supported
 │   │
-│   └── ... (2,005+ total)
+│   └── ... (2,007+ total)
 │
 ├── 📁 apps/
 │   └── 📁 web-app/                     ← Interactive browser
@@ -106,7 +106,7 @@ agentic-awesome-skills/
 
 ```
                     ┌─────────────────────────┐
-                    │  2,005+ SKILLS          │
+                    │  2,007+ SKILLS          │
                     └────────────┬────────────┘
                                  │
         ┌────────────────────────┼────────────────────────┐
@@ -207,7 +207,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
 │   ├── 📁 brainstorming/                 │
 │   ├── 📁 stripe-integration/            │
 │   ├── 📁 react-best-practices/          │
-│   └── ... (2,005+ total)                │
+│   └── ... (2,007+ total)                │
 └─────────────────────────────────────────┘
 ```
 

package/bundled-skills/loki-mode/examples/todo-app-generated/backend/package-lock.json

@@ -11,7 +11,7 @@
         "better-sqlite3": "^12.11.1",
         "cors": "^2.8.6",
         "express": "^4.18.2",
-        "express-rate-limit": "^8.5.2"
+        "express-rate-limit": "^8.6.0"
       },
       "devDependencies": {
         "@types/better-sqlite3": "^7.6.13",
@@ -691,11 +691,12 @@
       }
     },
     "node_modules/express-rate-limit": {
-      "version": "8.5.2",
-      "resolved": "https://registry.npmjs.org/express-rate-limit/-/express-rate-limit-8.5.2.tgz",
-      "integrity": "sha512-5Kb34ipNX694DH48vN9irak1Qx30nb0PLYHXfJgw4YEjiC3ZEmZJhwOp+VfiCYwFzvFTdB9QkArYS5kXa2cx2A==",
+      "version": "8.6.0",
+      "resolved": "https://registry.npmjs.org/express-rate-limit/-/express-rate-limit-8.6.0.tgz",
+      "integrity": "sha512-XKJXDsASUOo0LLtFwW5hCcQGH0N4WQc/Rn8/Pvoia+TJFOkkFPvrtW9lZOeeNcxQJspvOIERMwiRLsVFlhHEkA==",
       "license": "MIT",
       "dependencies": {
+        "debug": "^4.4.3",
         "ip-address": "^10.2.0"
       },
       "engines": {
@@ -708,6 +709,29 @@
         "express": ">= 4.11"
       }
     },
+    "node_modules/express-rate-limit/node_modules/debug": {
+      "version": "4.4.3",
+      "resolved": "https://registry.npmjs.org/debug/-/debug-4.4.3.tgz",
+      "integrity": "sha512-RGwwWnwQvkVfavKVt22FGLw+xYSdzARwm0ru6DhTVA3umU5hZc28V3kO4stgYryrTlLpuvgI9GiijltAjNbcqA==",
+      "license": "MIT",
+      "dependencies": {
+        "ms": "^2.1.3"
+      },
+      "engines": {
+        "node": ">=6.0"
+      },
+      "peerDependenciesMeta": {
+        "supports-color": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/express-rate-limit/node_modules/ms": {
+      "version": "2.1.3",
+      "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
+      "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==",
+      "license": "MIT"
+    },
     "node_modules/file-uri-to-path": {
       "version": "1.0.0",
       "resolved": "https://registry.npmjs.org/file-uri-to-path/-/file-uri-to-path-1.0.0.tgz",

package/bundled-skills/loki-mode/examples/todo-app-generated/backend/package.json

@@ -12,7 +12,7 @@
     "better-sqlite3": "^12.11.1",
     "cors": "^2.8.6",
     "express": "^4.18.2",
-    "express-rate-limit": "^8.5.2"
+    "express-rate-limit": "^8.6.0"
   },
   "devDependencies": {
     "@types/better-sqlite3": "^7.6.13",

package/bundled-skills/people-data/SKILL.md

@@ -0,0 +1,104 @@
+---
+name: people-data
+description: "Research LinkedIn professional profiles and public business-contact data, including email/phone lookup, people search, and YouTube channel business-email discovery."
+category: research
+risk: safe
+source: https://github.com/agentbody/skills/blob/main/skills/people-data/SKILL.md
+source_repo: agentbody/skills
+source_type: community
+date_added: "2026-08-07"
+author: agentbody
+tags: [linkedin, youtube, people-search, business-contacts, research]
+tools: [claude, cursor, gemini]
+license: "MIT"
+license_source: "https://github.com/agentbody/skills/blob/main/LICENSE"
+---
+
+# People Data
+
+## Overview
+
+Perform authorized professional-profile and public business-contact research through the Agent Body MCP server at `/mcp/people-data`. It covers LinkedIn profile retrieval, email and phone lookup, filtered people search, and YouTube channel business-email discovery.
+
+Read [references/tool-reference.md](references/tool-reference.md) for exact tool names and input fields.
+
+## When to Use This Skill
+
+- Use when the user asks to look up, enrich, or verify a LinkedIn professional profile.
+- Use when the user needs a business email or phone number for a LinkedIn profile they are authorized to contact.
+- Use when the user wants to find people by role, company, location, seniority, or other LinkedIn filters.
+- Use when the user wants to find public business contact emails for YouTube channels.
+- Use when the user asks to validate or deduplicate people-search results before outreach.
+
+## How It Works
+
+### Step 1: Choose one operation
+
+- `linkedin_person_profile` with `linkedin_url` retrieves one professional profile.
+- `linkedin_email_lookup` with `profileUrl` looks up one profile email address.
+- `linkedin_phone_lookup` with `profileUrl` looks up one profile phone number.
+- `linkedin_people_search` accepts optional filters and returns a `nextPageToken` for continuation.
+- `youtube_email_finder` takes `channels` (1-1000 channel URLs) and optional `scrape_fresh_emails` to find public business emails.
+
+### Step 2: Prefer canonical URLs and explicit filters
+
+Use canonical profile or channel URLs when available. For name-only searches, add explicit role, company, location, or keyword filters. `companyFilter` must be `current`, `past`, or `all`.
+
+### Step 3: Verify and present only returned data
+
+Confirm that returned identities match the request, deduplicate search results by canonical profile identity, and never construct or guess an email address or phone number. Preserve per-channel found/not-found state from YouTube results.
+
+## Examples
+
+### Example 1: Look up one LinkedIn profile
+
+Call `linkedin_person_profile` with:
+
+```json
+{
+  "linkedin_url": "https://www.linkedin.com/in/example-person"
+}
+```
+
+### Example 2: Find public business emails for YouTube channels
+
+Call `youtube_email_finder` with:
+
+```json
+{
+  "channels": ["https://www.youtube.com/@example"],
+  "scrape_fresh_emails": false
+}
+```
+
+## Best Practices
+
+- ✅ Use canonical profile or channel URLs instead of guessing handles.
+- ✅ Confirm the returned identity matches the person or channel before presenting it.
+- ✅ Use only public, authorized, or explicitly permitted business data.
+- ✅ Keep `nextPageToken` unchanged when continuing a `linkedin_people_search`.
+- ❌ Do not fabricate, guess, or infer email addresses or phone numbers.
+- ❌ Do not bypass access controls or collect private profiles without authorization.
+
+## Limitations
+
+- Requires an Agent Body API key and access to the `/mcp/people-data` MCP server; results depend on the live tool schema.
+- Email and phone lookup may return no result for profiles without public contact data; a missing result is not evidence that a person has no contact information.
+- Search filters are optional, but unfiltered name-only searches can return ambiguous matches that need manual verification.
+- `youtube_email_finder` only finds public business emails and may report channels where no email is found.
+
+## Security & Safety Notes
+
+- Never print, log, or commit API keys or other credentials.
+- Use contact information only for authorized business purposes and respect privacy, anti-harassment, and outreach rules.
+- Do not use this skill to build contact lists without a lawful basis or to contact people who have opted out.
+- This skill is read-only: it queries business data and does not modify files or systems.
+
+## Common Pitfalls
+
+- **Problem:** Using the wrong input key for profile versus email/phone lookups.
+  **Solution:** Profile lookup uses `linkedin_url`; email and phone lookup use `profileUrl`.
+- **Problem:** Guessing an email when lookup returns nothing.
+  **Solution:** Report the missing result and stop; never invent contact data.
+- **Problem:** Repeating the same people-search page.
+  **Solution:** Pass the returned `nextPageToken` unchanged to continue instead of replaying the initial query.

package/bundled-skills/people-data/references/tool-reference.md

@@ -0,0 +1,36 @@
+# People Data Tool Reference
+
+MCP server: `/mcp/people-data`
+
+Successful calls return the business result in `data`.
+
+REST uses `POST /v1/tools/{tool_id}/call`.
+
+| Tool ID | MCP Tool | Required input | Purpose |
+|---|---|---|---|
+| `linkedin.email_lookup` | `linkedin_email_lookup` | `profileUrl` (URI) | Look up an email address from a LinkedIn profile URL |
+| `linkedin.phone_lookup` | `linkedin_phone_lookup` | `profileUrl` (URI) | Look up a phone number from a LinkedIn profile URL |
+| `linkedin.person_profile` | `linkedin_person_profile` | `linkedin_url` (URI) | Retrieve one professional profile |
+| `linkedin.people_search` | `linkedin_people_search` | None | Search people with explicit filters |
+| `youtube.email_finder` | `youtube_email_finder` | `channels` | Find public business emails for channels |
+
+## People search fields
+
+`linkedin_people_search` accepts these optional fields:
+
+- Strings: `name`, `companyFilter`, `keyword`, `nextPageToken`.
+- String arrays: `jobTitle`, `excludeJobTitles`, `seniority`, `jobFunction`, `skills`, `yearsOfExperience`, `yearsInCurrentRole`, `education`, `company`, `domain`, `excludeCompanies`, `location`, `industry`, `companySize`.
+- Booleans: `currentTitlesOnly`, `includeRelatedJobTitles`.
+
+`companyFilter` must be `current`, `past`, or `all`. Pass a returned `nextPageToken` unchanged to continue a search.
+
+## YouTube email input
+
+```json
+{
+  "channels": ["https://www.youtube.com/@example"],
+  "scrape_fresh_emails": false
+}
+```
+
+`channels` must contain 1-1000 non-empty strings. The result contains a `channels` array; preserve per-channel found/not-found state instead of inventing missing addresses.

package/bundled-skills/travel-planner/SKILL.md

@@ -0,0 +1,230 @@
+---
+name: travel-planner
+description: "旅行/行程规划需求时使用:规划去某地旅行、X天X城、带老人孩子、自驾、假期安排等。产出逐日行程表、预算估算(经济/舒适/奢华三档)、交通住宿建议、景点美食清单。必须先问预算,预算未确认只输出问题清单;事实数据带来源和查询日期。"
+category: travel
+risk: safe
+source: community
+source_repo: saudademjj/luopan
+source_type: community
+date_added: "2026-08-08"
+author: saudademjj
+tags: [travel, itinerary, planning, trip, chinese]
+license: "MIT"
+license_source: "https://github.com/saudademjj/luopan/blob/main/LICENSE"
+---
+
+# 旅行规划 (Travel Planner)
+
+## When to Use
+
+- 用户提出任何旅行、出游、行程规划相关需求时使用;用户未明说"规划"但请求涉及目的地、天数、路线或行程安排的,同样适用
+- 覆盖自由行、家庭游、亲子游、商务出差、自驾等所有类型
+
+
+为用户的旅行需求生成一份完整、可执行、节奏合理的规划。输出一律用中文。
+以下四个步骤**按顺序执行,不得跳步、不得提前输出**。
+
+## 第一步:收集需求(必问预算)
+
+在开始任何联网查询或规划前,先收集齐以下信息。用户请求里没明确给出的,用**一次提问**问清(不要逐条追问,按顺序打包成 4-7 个问题):
+
+1. **出发地**:用户所在城市/出发城市(影响大交通与预算口径;用户未提时默认按用户所在地推断,并在输出页眉注明推断假设)
+2. **目的地**:城市/地区,必要时细分到区域
+3. **日期与天数**:起止日期或"X天"+ 大致出发时间
+4. **同行人与人数**:个人 / 情侣 / 带老人 / 带孩子 / 团队——老人小孩直接影响节奏
+5. **预算——必须问**:人均或总预算、口径(含不含机票/购物)。用户没提预算就必须问,不能跳过、不能自己默认。若用户说"没想好",给出档位让他选:经济(青旅/公共交通)、舒适(中档酒店/地铁为主)、奢华(高星酒店/包车)。**预算未确认前,只输出问题清单,不输出任何行程内容——包括草稿、框架、示例,都不要给。**若用户明确拒绝提供预算,默认按舒适档规划,并在输出页眉注明"按默认舒适档估算"。用户回答预算后,才进入第二步。
+6. **偏好**:节奏(松弛/紧凑/无所谓)、兴趣(美食/人文/自然/购物/夜生活/小众)、避雷内容
+7. **限制**:签证/证件、身体条件、天气敏感度、是否需要 WiFi/翻译/无障碍
+
+**目的地范围红线**:行程范围严格等于用户指定的目的地(指定城市名即其行政市域,指定地区即该地区域)。**不得擅自加入其他城市/区域**——包括"顺路""高铁 1 小时内"的周边一日游,哪怕你认为单城天数偏长。若天数确实偏多:(1)优先放慢节奏、加深单城玩法——冷门点位、博物馆、街区深度游、留半天休息日;(2)周边一日游只能作为**问题清单里的一道选择题**先问用户("X天单城可能偏长,是否考虑加 1-2 天周边一日游?"),用户明确同意后才纳入主行程;未获同意则主行程保持单城。若用户明确要求"环线/深度游"等跨区域形态,当行程必须覆盖跨出指定区域的部分时,在输出开头向用户**明确解释每个跨区点的原因**,并给出严格限定在指定区域内的替代方案,让用户拍板,不得擅自决定。
+
+## 第二步:联网调研(实时信息)
+
+用 WebSearch/WebFetch 联网核实以下内容,输出中标注信息来源与查询日期:
+
+- **目的地当前状况**:最佳季节、当月天气气温、节庆或大型活动(影响人流与价格)
+- **大交通**:出发地→目的地航班/高铁/大巴的价格区间与耗时、机场/车站→市区方式
+- **住宿**:按预算档位推荐区域,各区域特点与大致价位
+- **景点**:必去景点开放时间、门票、预约要求、排队预期;小众景点
+- **签证/入境**(国际旅行必查):要求、材料、办理时间
+- **当地实用信息**:时差、货币、语言、安全、电源插头
+
+调研纪律:
+- 搜索时带年份/月份关键词,优先取最新信息;**区分"攻略观点"与"事实性信息"**(开放时间、票价、签证政策以官方为准)
+- **来源分级**:事实性数据(票价/开放时间/政策)优先官方渠道(景区官网、政府公告、12306、航司、场馆官方公众号),权威媒体次之;**自媒体与"野榜"(小红书、自媒体榜单、平台号攻略)只作线索不作依据**——仅出自自媒体的信息须标注"来源为自媒体,需官方确认",不得当确定事实写;美食/口碑类推荐须多个本地来源交叉验证,单一榜单不作推荐理由
+- **可追溯**:每个事实性数据(票价、开放时间、闭馆日、签证要求、班次时刻)都要能追溯到来源——查询所得项标注来源与查询日期(如"某航司官网 2026-08""官方公告 2026-02"),未查到的一律明确写"未查到,需自行确认"
+- **绝不编造**:查不到或不确定的,明确写"需以官网/预订平台为准"
+- 若联网工具不可用,在输出开头声明:"以下为知识库信息,票价/开放时间/航班等实时信息可能过期,请以官方渠道为准"
+
+## 第三步:构建行程框架
+
+**先定优先级,再排天**,然后逐条校验以下规则(**R1-R13 全部必须满足,编号用于对照,不是可选项**):
+
+**R1 优先级分级**:用调研结果与目的地公认热度,把候选景点分为**必去级**(城市顶级地标——5A/国家级场馆/当地共识必打卡)、**值得去级**(有特色但可取舍)、**可选级**(锦上添花,如次级景点、小众点位)。**必去级必须进主行程,绝不放备选**;可选级只作补充,不能当行程主卖点。排序依据是热度数据与官方评级,不是模型自己的偏好。若必去级总量超出天数可承载(按 R3 体量、R4 独占一天计算排不下),不得静默删减:按热度与官方评级降序,**把取舍选项一次写入问题清单让用户拍板**(如"3 天排不下全部必去景点,以下二选一:…)",用户同意后才可移出主行程,并在自检表备注注明原因与依据。
+
+**R2 高商业化旅游街避雷**:商业化严重、目标客群是游客的街区/美食街(特征:全国统一的小吃摊、网红店聚集、本地人不去),不得排为必去级,也不得作为美食推荐的主要来源。这类地点要么降级为"顺路可逛",要么写进避雷说明(标注"商业化严重、餐饮全国统一、坑多,逛可以、吃住别选这里");美食推荐以本地人常去为主——老字号、居民区、菜场周边小店。
+
+**R3 体量定负荷**:判断"赶不赶"看**体量**而非个数。每天 2-3 个主景点(或 1 个大景点 + 周边);两个重量级(大型景区/国家级场馆/纪念地)不得同日,重量级只能配轻量级(街区/广场/商场)。自驾行程中,**长途驾驶本身计入每日体量**:单日车程 ≥4 小时视为一个重量级,"车程+游玩"合并评估当天负荷;两个长驱日之间必须隔开。
+
+**R4 顶流园区独占一天**:一天都逛不完的顶流园区(如口碑顶流的超大型园区)必须独占一天,不得与任何其他主景点同日——宁可整体少排景点,也不压缩大园。唯一例外见 R5。
+
+**R5 收尾型并日(例外)**:主景点玩完后,同区域次一级景点的**"收尾型"并日**可接受(经实测验证的成熟玩法)——前提:次一级点只安排核心区段(如主园林 4-5h 后接次一级景区遗址区夕阳收尾 2-2.5h,非全园),并注明可替换为休整/商圈。不得做全园。
+
+**R6 时间预估带缓冲**:每个景点先按**纯浏览时间**估算,再**统一加 1-2 小时缓冲**,覆盖入场/安检/排队、找路、吃饭、休息、拍照、离场等实际因素,避免按两套口径重复计入。热门大型园区直接按**一整天到闭园**估,绝不压缩。宁可排松,不可排满。
+
+**R7 不砍核心景点**:5 天及以上的单城行程不得砍核心景点——必去级与热门值得去级都要保住;排不下就拆天、挪位、合并轻量级,而不是从行程里删景点。
+
+**R8 大型博物馆半天起步**:国家级大馆(藏品数十万件的省级以上博物馆)至少 4-6 小时,标注建议时长前先确认场馆体量,不许把大馆塞进"上午 3 小时"。
+
+**R9 顶级商圈**:中档及以上预算的行程应纳入顶级商场/商圈体验,放在晚间、雨天或休整日。以**本地人日常消费为主的品质商圈**为准;若该商圈同时属于 R2 所述高商业化游客街,降级为"顺路可逛",改为推荐商场内部高品质餐饮/展览作为替代;用户明确无购物偏好时不强制纳入。
+
+**R10 行程锚定住宿区域**:先定住宿区域(按预算+全程动线),之后每一天都从"酒店出发"的视角估算交通衔接——住市中心枢纽则各日从容;住宿偏远时逐日重估通勤,不允许出现"从偏远酒店出发还要 1 小时才到第一站"的安排。全程建议住同一家酒店,避免中途搬行李;自驾环线无法同店连住时,以"行李随车、每晚只收拾次日小包"变通并注明。
+
+**R11 地理就近**:同一天排同一区域,减少来回奔波。
+
+**R12 全局去重**:所有天排完后整体检查一遍——同一街区/市集/夜游点不得在多个晚上重复出现(顺路路过与专门安排视为重复)。重复的合并或替换为同类替代(如换本地人常去的另一处),保证每天体验有差异,不把行程排成"同一批地方的循环"。
+
+**R13 主观体验类项目列为可选**:实景演出、大型演出、游船/画舫夜游、主题乐园夜场、摩天轮等高单价、强主观喜好的项目,**默认列入"可选加项"供用户拍板,不自动占主行程晚间位置**。用户未明确偏好时,全行程此类晚间项目至多保留 1 个(选最经典的那个),其余进可选清单(注明价格与确认渠道)。必要交通性乘船(如登岛只能坐船)不算游船项目,正常排。
+
+通用要求(适用于每一天):
+- 节奏默认中等;带老人小孩或用户要求松弛时每日主景点数减至 1 个或只排半天,商务出差留弹性
+- 受天气影响的活动(户外、夜景、游船)必须有**备选方案**
+- 热点餐厅/博物馆等标注预约提示
+
+## 第四步:按模板输出
+
+**输出前强制检查(不可跳过)**:正式撰写输出前,重读本文件"第三步"的 R1-R13 与文末"质量红线",逐条对照已排定的行程;发现不合规(体量失衡、必去级缺失或进了备选、重复安排、时长未带缓冲等)先在草稿中修正,再进入模板输出。输出完成后,按模板末尾的"规则自检表"逐条填写。
+
+严格按照以下模板输出,顺序与层级不变,Markdown 格式:
+
+# [目的地] X天Y夜行程规划
+> 规划日期 / 信息查询日期 / 人数与类型 / 预算档位
+
+## 📋 行程总览
+- 天数、日期、季节与天气概要
+- 每日一句话主题(如 D1 老城区漫步、D2 海边)
+
+## 🗓️ 逐日行程表
+### Day 1(日期 星期)
+- **上午**:…
+- **下午**:…
+- **晚上**:…
+- **交通**:…(地铁/公交/步行/打车/自驾里程 + 大致耗时)
+- **备选**:…(天气/预约不上时的方案)
+
+## 💰 预算估算(人均)
+| 项目 | 经济 | 舒适 | 奢华 | 备注 |
+|---|---|---|---|---|
+| 往返大交通 | | | | |
+| 住宿(X晚) | | | | |
+| 餐饮 | | | | |
+| 门票/活动 | | | | |
+| 市内交通 | | | | 自驾含租车/油费/过路费/异地还车费 |
+| **合计** | | | | |
+
+> 说明:预算表只输出**用户所选档位**对应的列(经济/舒适/奢华);哪些项为联网查询所得(**注明来源与查询日期**),哪些为估算(注明口径)。查询所得金额逐一标注,如"¥1200(航司官网 2026-08)"
+
+## 🚄 交通与住宿建议
+- 抵达/离开交通:班次建议时段、价格区间、订票平台提醒
+- 市内交通:地铁卡/APP/打车软件与大致成本;自驾含租车车型/取还车点/保险/加油提示
+- 住宿区域:按预算档位推荐,列出各区域优缺点与价位
+
+## 🏞️ 景点与美食清单
+- **必去**:理由 + 建议时长 + 预约提示
+- **小众/隐藏**:值得绕路去的
+- **避雷**:商业化严重/口碑差/坑多的地方,写明避雷原因(全国统一小吃、宰客、溢价);顺路可一句带过,不推荐专门安排时间
+- **美食**:当地必吃 + 推荐餐厅类型/区域,以本地人常去为主(老字号/居民区/菜场周边),标注需预约的
+
+## ⚠️ 注意事项
+- 签证/证件(国际旅行)、气候与穿衣、安全与风俗、实用信息(时差/货币/网络/电源);自驾含驾驶安全、限行时段、边防/边境证件、加油点
+
+## ✅ 出行前二次确认清单
+把最容易变化、且规划时依赖查询结果的信息集中列出,提醒用户在预订/出发前核对官方渠道(每一项注明:查到什么、什么时候查的、去哪里确认):
+- 签证政策(入境要求/材料/办理时间)——官方:使领馆/出入境管理局
+- 航班/高铁时刻与行李额——官方:航司/12306
+- 景点开放时间、闭馆日、预约——官方:景点官网/官方小程序
+- 汇率与当地支付方式——官方:银行/支付平台
+- 天气预警(雨季/台风/寒潮)——官方:气象部门
+
+## 📎 数据来源索引
+按景点/事项分组列出本次规划引用的所有事实性数据:项目 → 查到值 → 来源 → 查询日期。仅列确有查询结果的数据;未查到的在逐日行程相应位置标"⚠️需自行确认"。
+
+## ✅ 规则自检表(置于行程文档最末,交付前必须逐条填写)
+
+| 规则 | 判定 | 备注(具体证据,不得留空) |
+|---|---|---|
+| R1 优先级分级:必去级全部在主行程、绝不在备选 | | |
+| R2 高商业化旅游街:未排为必去、未作美食主来源 | | |
+| R3 体量:无两重量级同日,重量级只配轻量级;自驾单日车程≥4h 计入体量 | | |
+| R4 顶流园区独占一天(R5 收尾型例外除外) | | |
+| R5 收尾型并日:只游核心区段、注明可替换 | | |
+| R6 时长带缓冲:每段含排队/交通/拍照余量,顶流按整天 | | |
+| R7 5 天及以上单城:核心景点无删减 | | |
+| R8 大馆半天起步(4-6h) | | |
+| R9 中档及以上预算含品质商圈(高商业化游客街除外,无购物偏好不强制) | | |
+| R10 住宿锚定:每日从酒店出发算通勤 | | |
+| R11 地理就近:同日同区域 | | |
+| R12 全局去重:无同一街区/市集/夜游点多晚重复 | | |
+| R13 主观体验类(演出/游船/夜场/摩天轮):默认可选加项,晚间至多1个 | | |
+| 红线① 预算已确认后才规划(拒绝提供预算时注明按默认舒适档) | | |
+| 红线② 范围=指定目的地,无擅自加城市 | | |
+| 红线③ 实时数据可追溯(来源+查询日期),无编造 | | |
+| 红线④ 节奏合理:无塞满行程,每天安排人能走完 | | |
+| 红线⑤ 模板结构与输出语言(中文)固定不变 | | |
+
+- 判定:✓ 符合 / △ 检查中发现并已修正后符合 / — 不适用(如非国际行程)
+- 规则编号与正文 R1-R13 一一对应;任何一条为 △ 都意味着交付前修改过,备注应说明改了什么
+
+**以下排版规则与质量红线为技能内部约束,仅供规划时执行,不得作为行程文档的一部分输出:**
+
+**排版规则(与模板同等重要)**:
+- **来源与行程分层**:逐日行程主体只写时间/地点/活动/交通衔接,行内不逐句挂"来源:xxx";来源集中到"数据来源索引"小节(位于二次确认清单之后、规则自检表之前);仅有争议或未查到的数据才在行内标"⚠️需自行确认"
+- **预算表**:来源统一放表下"说明"或数据来源索引,不在备注列逐格贴来源
+- **推荐与事实分层**:景点美食清单中,推荐理由(为什么值得去/吃)与事实数据(票价/开放时间/预约)分行或分列呈现,不揉杂
+
+---
+*以上信息查询于 [日期],票价与开放时间以官方渠道为准。需要调整节奏、预算或某一天安排,直接说。*
+
+### 质量红线(最后兜底,优先级最高,与正文冲突时以红线为准)
+
+1. **必问预算**——用户没给预算就只提问、不出行程(任何形式的草稿/框架都不行),预算确认后才开始规划;拒绝提供时按舒适档并注明
+2. **范围红线**——主行程只覆盖用户指定目的地,未经同意不得添加其他城市的周边一日游。想加必须先问;未获同意时,周边游至多在"备选方案"小节约一句并注明"超出你要求的范围,仅作参考"
+3. **不编造**——实时数据可追溯(来源+查询日期);查不到就写"需自行确认"
+4. **节奏合理优先**于塞满行程,每天的安排必须是人能走完的;因节奏删减项目时,被删项目须经用户确认(R1 取舍机制),不得静默丢弃
+5. **模板结构与输出语言(中文)固定不变**
+
+## Examples
+
+### 示例 1:标准规划流程
+
+用户:"帮我规划成都 3 天 2 晚,带父母,预算舒适档。"
+
+技能:一次提问补齐剩余信息(出发地、具体日期、节奏偏好、是否忌口等),等待用户确认预算与答案;预算确认后联网调研,再按模板输出。输出片段:
+
+```
+# 成都 3天2夜行程规划
+> 规划日期:2026-08-08 / 信息查询日期:2026-08-08 / 2 成人 2 老人 / 舒适档
+
+## 📋 行程总览
+- 3 天 2 夜,8 月下旬,晴热多雷阵雨(来源:气象部门 2026-08)
+- D1 武侯祠—锦里老城区 / D2 熊猫基地一整天 / D3 杜甫草堂—宽窄巷子
+
+## 🗓️ 逐日行程表
+### Day 1(2026-08-21 周五)
+- **上午**:武侯祠(约 2.5h 含缓冲,门票 50 元,来源:景区官网 2026-08)
+- …
+```
+
+### 示例 2:预算未确认时不输出行程
+
+用户:"帮我规划去西安玩。"
+
+技能:只输出问题清单(目的地细节、日期天数、同行人、**预算档位**、偏好、限制),不给出任何行程草稿或示例。
+
+## Limitations
+
+- 实时信息(票价/开放时间/签证政策/航班班次)以规划时的联网查询为准,可能过期,须以官方渠道确认;技能不保证其准确性
+- 查询不到的数据只能标注"需自行确认",不得编造
+- 行程为建议而非预订承诺,预订前须走完"出行前二次确认清单"
+- 突发情况(大型活动临时管制、极端天气、景点临时闭园)无法提前预测,备选方案不能替代现场确认
+- 无联网环境时只能输出知识库级信息,并按要求在输出开头声明

package/bundled-skills/unified-ai-gateway/SKILL.md

@@ -24,6 +24,15 @@ guidance; it does not install the server or change Codex configuration by
 itself. The official Codex plugin bundles the MCP definition, while skill-only
 installations require the manual setup below.
 
+## Version Note
+
+The current public project release is `v0.4.3`. The inspection procedure below
+intentionally pins the reviewed, immutable `v0.4.0` image and its recorded
+digests; those values are a historical security baseline and must not be
+silently replaced with a mutable tag. For a normal provider-free demo, use the
+current `v0.4.3` command in the [project README](https://github.com/happy520ai/unified-ai-system#try-it-in-60-seconds).
+A new content review is required before changing this pinned procedure.
+
 ## Prerequisites And Setup
 
 1. Confirm that Codex CLI and Docker are installed and Docker is running.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-skills-collection",
-  "version": "4.0.26",
+  "version": "4.0.28",
   "description": "OpenCode CLI plugin that automatically downloads and keeps skills up to date.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

package/skills_index.json

@@ -11978,7 +11978,7 @@
     "category": "ai-ml",
     "name": "context-agent",
     "description": "Agente de contexto para continuidade entre sessoes. Salva resumos, decisoes, tarefas pendentes e carrega briefing automatico na sessao seguinte.",
-    "risk": "safe",
+    "risk": "critical",
     "source": "community",
     "date_added": "2026-03-06",
     "plugin": {
@@ -12120,7 +12120,7 @@
     "category": "ai-ml",
     "name": "context-guardian",
     "description": "Guardiao de contexto que preserva dados criticos antes da compactacao automatica. Snapshots, verificacao de integridade e zero perda de informacao.",
-    "risk": "safe",
+    "risk": "critical",
     "source": "community",
     "date_added": "2026-03-06",
     "plugin": {