opencode-skills-collection 2.0.70 → 2.0.72

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

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "updatedAt": "2026-04-13T20:06:36.949Z",
+  "updatedAt": "2026-04-13T22:44:31.970Z",
   "entries": [
     "00-andruia-consultant",
     "007",
@@ -128,6 +128,7 @@
     "aws-serverless",
     "aws-skills",
     "awt-e2e-testing",
+    "axiom",
     "azd-deployment",
     "azure-ai-agents-persistent-dotnet",
     "azure-ai-agents-persistent-java",
@@ -652,6 +653,7 @@
     "haskell-pro",
     "headline-psychologist",
     "health-trend-analyzer",
+    "helium-mcp",
     "helm-chart-scaffolding",
     "helpdesk-automation",
     "hierarchical-agent-memory",
@@ -705,6 +707,7 @@
     "incident-response-incident-response",
     "incident-response-smart-fix",
     "incident-runbook-templates",
+    "indexing-issue-auditor",
     "infinite-gratitude",
     "inngest",
     "instagram",
@@ -774,6 +777,7 @@
     "linear-claude-skill",
     "linkedin-automation",
     "linkedin-cli",
+    "linkedin-profile-optimizer",
     "linkerd-patterns",
     "lint-and-validate",
     "linux-privilege-escalation",
@@ -1403,6 +1407,7 @@
     "zapier-make-patterns",
     "zendesk-automation",
     "zeroize-audit",
+    "zipai-optimizer",
     "zod-validation-expert",
     "zoho-crm-automation",
     "zoom-automation",

package/bundled-skills/00-andruia-consultant/SKILL.md

@@ -58,3 +58,8 @@ Para ambos escenarios, tras recibir las respuestas:
 
 1. **Contexto Inteligente**: No mezcles datos de proyectos anteriores. Cada carpeta es una entidad única.
 2. **Estándar de Diamante**: Prioriza siempre soluciones escalables, seguras y estéticamente superiores.
+
+## 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.

package/bundled-skills/007/SKILL.md

@@ -648,3 +648,8 @@ O proprio 007 pratica o que prega:
 - `claude-code-expert` - Complementary skill for enhanced analysis
 - `cred-omega` - Complementary skill for enhanced analysis
 - `matematico-tao` - Complementary skill for enhanced analysis
+
+## 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.

package/bundled-skills/10-andruia-skill-smith/SKILL.md

@@ -42,3 +42,8 @@ Generar el código para los siguientes archivos:
 ## ⚠️ Reglas de Oro
 - **Prefijos Numéricos:** Asignar un número correlativo a la carpeta (ej. 11, 12, 13) para mantener el orden.
 - **Prompt Engineering:** Las instrucciones deben incluir técnicas de "Few-shot" o "Chain of Thought" para máxima precisión.
+
+## 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.

package/bundled-skills/20-andruia-niche-intelligence/SKILL.md

@@ -59,3 +59,8 @@ Activa este skill **después de que el nicho de mercado esté claro** y ya exist
 - Cuando quieras profundizar en regulaciones, estándares y patrones UX específicos de un sector concreto (Fintech, HealthTech, logística, etc.).
 - Antes de diseñar experiencias de usuario, flujos de seguridad o modelos de datos que dependan fuertemente del contexto del nicho.
 - Cuando necesites un dossier de inteligencia de dominio para alinear equipo de producto, diseño y tecnología alrededor de la misma comprensión del sector.
+
+## 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.

package/bundled-skills/3d-web-experience/SKILL.md

@@ -364,7 +364,6 @@ Workflow:
 Works well with: `scroll-experience`, `interactive-portfolio`, `frontend`, `landing-page-design`
 
 ## When to Use
-
 - User mentions or implies: 3D website
 - User mentions or implies: three.js
 - User mentions or implies: WebGL
@@ -372,3 +371,8 @@ Works well with: `scroll-experience`, `interactive-portfolio`, `frontend`, `land
 - User mentions or implies: 3D experience
 - User mentions or implies: spline
 - User mentions or implies: product configurator
+
+## 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.

package/bundled-skills/ab-test-setup/SKILL.md

@@ -236,3 +236,8 @@ that is the signal to **slow down and re-check the design**.
 
 ## When to Use
 This skill is applicable to execute the workflow or actions described in the overview.
+
+## 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.

package/bundled-skills/acceptance-orchestrator/SKILL.md

@@ -15,7 +15,6 @@ Orchestrate coding work as a state machine that ends only when acceptance criter
 Core rule: **do not optimize for "code changed"; optimize for "DoD proven".**
 
 ## When to Use
-
 - The task already has an issue or clear acceptance criteria and should run end-to-end with minimal human re-intervention.
 - You need structured handoff across implementation, review, deployment, and final verification.
 - You want explicit stop conditions and escalation instead of silent partial completion.
@@ -110,3 +109,8 @@ When reporting status, always include:
 - `Need Human Input`: smallest next decision, if blocked
 
 Do not report "done" unless status is `accepted`.
+
+## 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.

package/bundled-skills/accessibility-compliance-accessibility-audit/SKILL.md

@@ -43,3 +43,8 @@ $ARGUMENTS
 ## Resources
 
 - `resources/implementation-playbook.md` for detailed audit steps, tooling, and remediation examples.
+
+## 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.

package/bundled-skills/activecampaign-automation/SKILL.md

@@ -211,3 +211,8 @@ Automate ActiveCampaign CRM and marketing automation operations through Composio
 
 ## When to Use
 This skill is applicable to execute the workflow or actions described in the overview.
+
+## 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.

package/bundled-skills/ad-creative/SKILL.md

@@ -13,7 +13,6 @@ metadata:
 You are an expert performance creative strategist. Your goal is to generate high-performing ad creative at scale — headlines, descriptions, and primary text that drive clicks and conversions — and iterate based on real performance data.
 
 ## When to Use
-
 - Use when generating or iterating paid ad copy at scale.
 - Use for headlines, descriptions, primary text, and structured ad variation sets.
 - Use when performance data should inform the next round of creative.
@@ -369,3 +368,8 @@ node tools/clis/google-ads.js reports get --type ad_performance --date-range las
 - **ab-test-setup**: For structuring creative tests with statistical rigor
 - **marketing-psychology**: For psychological principles behind high-performing creative
 - **copy-editing**: For polishing ad copy before launch
+
+## 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.

package/bundled-skills/address-github-comments/SKILL.md

@@ -59,3 +59,8 @@ gh pr comment <PR_NUMBER> --body "Addressed in latest commit."
 
 ## When to Use
 This skill is applicable to execute the workflow or actions described in the overview.
+
+## 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.

package/bundled-skills/adhx/SKILL.md

@@ -125,3 +125,8 @@ User: "How many likes did this tweet get? https://x.com/handle/status/123"
 
 - [ADHX GitHub Repository](https://github.com/itsmemeworks/adhx)
 - [ADHX Website](https://adhx.com)
+
+## 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.

package/bundled-skills/advanced-evaluation/SKILL.md

@@ -454,3 +454,7 @@ Related skills in this collection:
 **Author**: Muratcan Koylan
 **Version**: 1.0.0
 
+## 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.

package/bundled-skills/advogado-criminal/SKILL.md

@@ -948,3 +948,8 @@ python agent-orchestrator/scripts/match_skills.py "caso criminal"
 ## Related Skills
 
 - `advogado-especialista` - Complementary skill for enhanced analysis
+
+## 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.

package/bundled-skills/advogado-especialista/SKILL.md

@@ -1107,3 +1107,8 @@ Esta skill implementa as seguintes politicas:
 ## Related Skills
 
 - `advogado-criminal` - Complementary skill for enhanced analysis
+
+## 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.

package/bundled-skills/aegisops-ai/SKILL.md

@@ -26,7 +26,6 @@ Terraform plans.
 hardened K8s manifests.
 
 ## When to Use
-
 - **Kernel Patch Review:** Auditing raw C-based Git diffs for memory safety.
 - **Pre-Apply IaC Audit:** Analyzing `terraform plan` outputs to prevent bill spikes.
 - **Cluster Hardening:** Generating "Least Privilege" securityContexts for deployments.
@@ -122,3 +121,8 @@ python3 main.py
 
 + - **Repository**: https://github.com/Champbreed/AegisOps-AI
 + - **Documentation**: https://github.com/Champbreed/AegisOps-AI#readme
+
+## 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.

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

@@ -1123,9 +1123,13 @@ Workflow:
 Works well with: `multi-agent-orchestration`, `agent-communication`, `autonomous-agents`
 
 ## When to Use
-
 - User mentions or implies: agent testing
 - User mentions or implies: agent evaluation
 - User mentions or implies: benchmark agents
 - User mentions or implies: agent reliability
 - User mentions or implies: test agent
+
+## 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.

package/bundled-skills/agent-framework-azure-ai-py/SKILL.md

@@ -336,3 +336,8 @@ if __name__ == "__main__":
 
 ## When to Use
 This skill is applicable to execute the workflow or actions described in the overview.
+
+## 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.

package/bundled-skills/agent-manager-skill/SKILL.md

@@ -40,3 +40,8 @@ EOF
 
 - Requires `tmux` and `python3`.
 - Agents are configured under an `agents/` directory (see the repo for examples).
+
+## 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.

package/bundled-skills/agent-memory-mcp/SKILL.md

@@ -85,3 +85,8 @@ Access at: `http://localhost:3333`
 
 ## When to Use
 This skill is applicable to execute the workflow or actions described in the overview.
+
+## 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.

package/bundled-skills/agent-memory-systems/SKILL.md

@@ -1069,7 +1069,6 @@ Message: Ensure same embedding model for indexing and querying.
 Works well with: `autonomous-agents`, `multi-agent-orchestration`, `llm-architect`, `agent-tool-builder`
 
 ## When to Use
-
 - User mentions or implies: agent memory
 - User mentions or implies: long-term memory
 - User mentions or implies: memory systems
@@ -1082,3 +1081,8 @@ Works well with: `autonomous-agents`, `multi-agent-orchestration`, `llm-architec
 - User mentions or implies: langmem
 - User mentions or implies: memgpt
 - User mentions or implies: conversation history
+
+## 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.

package/bundled-skills/agent-orchestration-improve-agent/SKILL.md

@@ -350,3 +350,8 @@ Establish regular improvement cadence:
 - **Annually**: Strategic review and architecture updates
 
 Remember: Agent optimization is an iterative process. Each cycle builds upon previous learnings, gradually improving performance while maintaining stability and safety.
+
+## 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.

package/bundled-skills/agent-orchestration-multi-agent-optimize/SKILL.md

@@ -240,3 +240,8 @@ class CostOptimizer:
 - Implement gradual, reversible changes
 
 Target Optimization: $ARGUMENTS
+
+## 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.

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

@@ -314,3 +314,8 @@ python agent-orchestrator/scripts/scan_registry.py --status
 
 - `multi-advisor` - Complementary skill for enhanced analysis
 - `task-intelligence` - Complementary skill for enhanced analysis
+
+## 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.

package/bundled-skills/agent-tool-builder/SKILL.md

@@ -695,7 +695,6 @@ Message: MCP tool definition missing inputSchema.
 Works well with: `multi-agent-orchestration`, `api-designer`, `llm-architect`, `backend`
 
 ## When to Use
-
 - User mentions or implies: agent tool
 - User mentions or implies: function calling
 - User mentions or implies: tool schema
@@ -708,3 +707,8 @@ Works well with: `multi-agent-orchestration`, `api-designer`, `llm-architect`, `
 - User mentions or implies: input_schema
 - User mentions or implies: tool_use
 - User mentions or implies: tool_result
+
+## 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.

package/bundled-skills/agentflow/SKILL.md

@@ -197,3 +197,8 @@ Or install as a Claude Code plugin:
 - [Architecture Documentation](https://github.com/UrRhb/agentflow/blob/main/docs/architecture.md)
 - [Gap Registry (45 failure modes)](https://github.com/UrRhb/agentflow/blob/main/docs/gap-registry.md)
 - [Getting Started Guide](https://github.com/UrRhb/agentflow/blob/main/docs/getting-started.md)
+
+## 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.

package/bundled-skills/agentfolio/SKILL.md

@@ -94,3 +94,7 @@ This skill is applicable when you need to **discover or compare autonomous AI ag
 - When evaluating vendors or tools to integrate.
 - When you want inspiration or best practices from existing agent products.
 
+## 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.

package/bundled-skills/agentic-actions-auditor/SKILL.md

@@ -330,3 +330,8 @@ For complete documentation beyond this methodology overview:
 - **Action Security Profiles:** See {baseDir}/references/action-profiles.md for per-action security field documentation, default configurations, and dangerous configuration patterns.
 - **Detection Vectors:** See {baseDir}/references/foundations.md for the shared attacker-controlled input model, and individual vector files `{baseDir}/references/vector-{a..i}-*.md` for per-vector detection heuristics.
 - **Cross-File Resolution:** See {baseDir}/references/cross-file-resolution.md for `uses:` reference classification, composite action and reusable workflow resolution procedures, input mapping traces, and depth-1 limit.
+
+## 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.

package/bundled-skills/agentmail/SKILL.md

@@ -12,7 +12,6 @@ AgentMail gives AI agents real email addresses (`@theagentmail.net`) with a REST
 Base URL: `https://api.theagentmail.net`
 
 ## When to Use
-
 - An AI agent needs a real inbox/outbox for signups, verification flows, or transactional communication.
 - You need to provision AgentMail accounts, send messages, read inbox contents, or register inbound webhooks.
 - You need to monitor karma usage or wire email events into agent automation.
@@ -251,3 +250,8 @@ type AttachmentMeta = { id: string; filename: string; contentType: string; size:
 type KarmaBalance = { balance: number; events: KarmaEvent[] };
 type KarmaEvent = { id: string; type: string; amount: number; timestamp: number; metadata?: Record<string, unknown> };
 ```
+
+## 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.

package/bundled-skills/agentphone/SKILL.md

@@ -14,7 +14,6 @@ metadata: {"api_base": "https://api.agentphone.to/v1"}
 AgentPhone is an API-first telephony platform for AI agents. Give your agents phone numbers, voice calls, and SMS — all managed through a simple API.
 
 ## When to Use
-
 - Use when the user wants to create or manage AI phone agents, voice agents, or telephony automations
 - Use when the user needs to buy, assign, release, or inspect phone numbers tied to an agent workflow
 - Use when the user wants to place outbound calls, inspect transcripts, or send and receive SMS through AgentPhone
@@ -1382,3 +1381,8 @@ These are starting points. Having your own phone number means your agent can do
 - [API Reference](https://docs.agentphone.to/api-reference)
 - [Official Docs](https://docs.agentphone.to)
 - [Console](https://agentphone.to)
+
+## 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.

package/bundled-skills/agents-md/SKILL.md

@@ -10,7 +10,6 @@ source: community
 AGENTS.md is the canonical agent-facing documentation. Keep it minimal—agents are capable and don't need hand-holding. Target under 60 lines; never exceed 100. Instruction-following quality degrades as document length increases.
 
 ## When to Use
-
 - The user asks to create, update, or audit `AGENTS.md` or `CLAUDE.md`.
 - The project needs concise, high-signal agent instructions derived from the actual toolchain and repo layout.
 - Existing agent documentation is too long, duplicated, or drifting away from real project conventions.
@@ -124,3 +123,8 @@ Co-Authored-By: (the agent model's name and attribution byline)
 |---------|-------------|
 | `pnpm cli sync` | Sync data |
 ```
+
+## 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.

package/bundled-skills/agents-v2-py/SKILL.md

@@ -324,3 +324,8 @@ async def create_hosted_agent_async():
 
 ## When to Use
 This skill is applicable to execute the workflow or actions described in the overview.
+
+## 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.

package/bundled-skills/ai-agent-development/SKILL.md

@@ -171,3 +171,8 @@ User Input -> Planner -> Agent -> Tools -> Memory -> Response
 - `ai-ml` - AI/ML development
 - `rag-implementation` - RAG systems
 - `workflow-automation` - Workflow patterns
+
+## 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.

package/bundled-skills/ai-agents-architect/SKILL.md

@@ -321,7 +321,6 @@ Robust output handling:
 Works well with: `rag-engineer`, `prompt-engineer`, `backend`, `mcp-builder`
 
 ## When to Use
-
 - User mentions or implies: build agent
 - User mentions or implies: AI agent
 - User mentions or implies: autonomous agent
@@ -334,3 +333,8 @@ Works well with: `rag-engineer`, `prompt-engineer`, `backend`, `mcp-builder`
 - User mentions or implies: crewai
 - User mentions or implies: autogen
 - User mentions or implies: claude agent sdk
+
+## 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.

package/bundled-skills/ai-analyzer/SKILL.md

@@ -11,7 +11,6 @@ source: community
 基于AI技术的综合健康分析系统，提供智能健康洞察、风险预测和个性化建议。
 
 ## When to Use
-
 - The user wants AI-driven health analysis across multiple health datasets or lifestyle signals.
 - You need anomaly detection, risk prediction, or personalized recommendations based on health inputs.
 - You need generated health reports or question-answering over health metrics and trends.
@@ -224,3 +223,8 @@ const allergies = exists('data/allergies.json') ? readFile('data/allergies.json'
 - 增量读取：仅读取指定时间范围的数据文件
 - 数据缓存：避免重复读取同一文件
 - 延迟计算：按需生成图表数据
+
+## 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.

package/bundled-skills/ai-engineer/SKILL.md

@@ -183,3 +183,8 @@ Expert AI engineer specializing in LLM application development, RAG systems, and
 - "Implement semantic search with reranking for improved retrieval accuracy"
 - "Design an A/B testing framework for comparing different LLM prompts"
 - "Create a real-time AI content moderation system with custom classifiers"
+
+## 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.

package/bundled-skills/ai-engineering-toolkit/SKILL.md

@@ -105,3 +105,8 @@ cp -r ai-engineering-toolkit/skills/* ~/.claude/skills/
 
 **Repository**: [github.com/viliawang-pm/ai-engineering-toolkit](https://github.com/viliawang-pm/ai-engineering-toolkit)
 **License**: MIT
+
+## 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.

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

@@ -516,3 +516,8 @@ Key findings:
 
 **The uncomfortable truth: Your beautiful, carefully-written CLAUDE.md
 might be HURTING your AI's performance. Structure > Prose. Always.**
+
+## 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.

package/bundled-skills/ai-ml/SKILL.md

@@ -250,3 +250,8 @@ Use @evaluation to create evaluation framework
 - `database` - Data management
 - `cloud-devops` - Infrastructure
 - `testing-qa` - AI testing
+
+## 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.

package/bundled-skills/ai-native-cli/SKILL.md

@@ -308,3 +308,8 @@ Implement by layer -- each phase gets you the next certification level.
 ## Additional Resources
 
 - [Agent CLI Spec Repository](https://github.com/ChaosRealmsAI/agent-cli-spec)
+
+## 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.

package/bundled-skills/ai-product/SKILL.md

@@ -745,5 +745,9 @@ Workflow:
 ```
 
 ## When to Use
-
 Use this skill when the request clearly matches the capabilities and patterns described above.
+
+## 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.

package/bundled-skills/ai-seo/SKILL.md

@@ -13,7 +13,6 @@ metadata:
 You are an expert in AI search optimization — the practice of making content discoverable, extractable, and citable by AI systems including Google AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and Copilot. Your goal is to help users get their content cited as a source in AI-generated answers.
 
 ## When to Use
-
 - Use when optimizing content to be cited by LLMs and AI search systems.
 - Use when the user asks about AI SEO, AEO, GEO, LLM visibility, or AI citations.
 - Use when traditional SEO alone is not the full question and AI-specific discoverability matters.
@@ -405,3 +404,8 @@ For implementation, use the SEO and monitoring tools available in the current en
 - **competitor-alternatives**: For building comparison pages that get cited
 - **programmatic-seo**: For building SEO pages at scale
 - **copywriting**: For writing content that's both human-readable and AI-extractable
+
+## 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.

package/bundled-skills/ai-studio-image/SKILL.md

@@ -314,3 +314,8 @@ Para guias detalhados, consulte:
 - `comfyui-gateway` - Complementary skill for enhanced analysis
 - `image-studio` - Complementary skill for enhanced analysis
 - `stability-ai` - Complementary skill for enhanced analysis
+
+## 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.

package/bundled-skills/ai-wrapper-product/SKILL.md

@@ -675,10 +675,14 @@ Workflow:
 Works well with: `llm-architect`, `micro-saas-launcher`, `frontend`, `backend`
 
 ## When to Use
-
 - User mentions or implies: AI wrapper
 - User mentions or implies: GPT product
 - User mentions or implies: AI tool
 - User mentions or implies: wrap AI
 - User mentions or implies: AI SaaS
 - User mentions or implies: Claude API product
+
+## 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.

package/bundled-skills/airflow-dag-patterns/SKILL.md

@@ -42,3 +42,8 @@ Refer to `resources/implementation-playbook.md` for detailed patterns, checklist
 ## Resources
 
 - `resources/implementation-playbook.md` for detailed patterns, checklists, and templates.
+
+## 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.

package/bundled-skills/airtable-automation/SKILL.md

@@ -171,3 +171,8 @@ Automate Airtable operations through Composio's Airtable toolkit via Rube MCP.
 
 ## When to Use
 This skill is applicable to execute the workflow or actions described in the overview.
+
+## 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.