opencode-skills-collection 2.0.70 → 2.0.72

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

@@ -21,7 +21,6 @@ allowed-tools:
 # Image Optimization Analysis
 
 ## When to Use
-
 - Use when auditing image SEO, alt text, file sizes, formats, or lazy loading.
 - Use when the user wants image-specific performance recommendations.
 - Use when checking media quality signals that affect both SEO and Core Web Vitals.
@@ -191,3 +190,8 @@ Sorted by file size impact (largest savings first):
 | URL unreachable | Report connection error with status code. Suggest verifying URL and checking if site requires authentication. |
 | No images found on page | Report that no `<img>` elements were detected. Suggest checking if images are loaded via JavaScript or CSS background-image. |
 | Images behind CDN or authentication | Note that image files could not be directly accessed for size analysis. Report available metadata (alt text, dimensions, format from markup) and flag inaccessible resources. |
+
+## 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/seo-keyword-strategist/SKILL.md

@@ -92,3 +92,8 @@ Entities: [related concepts to include]
 - Static sites: Frontmatter keyword schema
 
 Focus on natural keyword integration and semantic relevance. Build topical depth through related concepts.
+
+## 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/seo-meta-optimizer/SKILL.md

@@ -89,3 +89,8 @@ Description: Action verb + benefit. Include keyword naturally. Clear CTA here
 - Astro/Next.js: Component props and helmet setup
 
 Focus on psychological triggers and user benefits. Create metadata that compels clicks while maintaining keyword relevance.
+
+## 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/seo-page/SKILL.md

@@ -20,7 +20,6 @@ allowed-tools:
 # Single Page Analysis
 
 ## When to Use
-
 - Use when the user provides a single URL for detailed on-page SEO review.
 - Use when auditing one page rather than an entire site.
 - Use when checking metadata, content, schema, images, and page-level technical signals together.
@@ -101,3 +100,8 @@ If DataForSEO MCP tools are available, use `serp_organic_live_advanced` for real
 | URL unreachable (DNS failure, connection refused) | Report the error clearly. Do not guess page content. Suggest the user verify the URL and try again. |
 | Page requires authentication (401/403) | Report that the page is behind authentication. Suggest the user provide the rendered HTML directly or a publicly accessible URL. |
 | JavaScript-rendered content (empty body in HTML) | Note that key content may be rendered client-side. Analyze the available HTML and flag that results may be incomplete. Suggest using a browser-rendered snapshot if available. |
+
+## 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/seo-plan/SKILL.md

@@ -22,7 +22,6 @@ allowed-tools:
 # Strategic SEO Planning
 
 ## When to Use
-
 - Use when building an SEO strategy or roadmap for a new or existing site.
 - Use when planning content, architecture, and implementation phases together.
 - Use when the user asks for an SEO plan rather than a point-in-time audit.
@@ -134,3 +133,8 @@ If DataForSEO MCP tools are available, use `dataforseo_labs_google_competitors_d
 | Unrecognized business type | Fall back to `generic.md` template. Inform user that no industry-specific template was found and proceed with the general business template. |
 | No website URL provided | Proceed with new-site planning mode. Skip current site assessment and competitive gap analysis that require a live URL. |
 | Industry template not found | Check `assets/` directory for available templates. If the requested template file is missing, use `generic.md` and note the missing template in output. |
+
+## 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/seo-programmatic/SKILL.md

@@ -21,7 +21,6 @@ Build and audit SEO pages generated at scale from structured data sources.
 Enforces quality gates to prevent thin content penalties and index bloat.
 
 ## When to Use
-
 - Use when the user wants programmatic SEO planning or review.
 - Use when designing templates, data-driven pages, or scalable URL systems.
 - Use when preventing thin content and index bloat across large page sets.
@@ -182,3 +181,8 @@ Measure against all other pages in the programmatic set. Shared headers, footers
 | No programmatic pages detected | Inform user that no template-generated or data-driven page patterns were found. Suggest checking if pages use client-side rendering or if the URL points to the correct section. |
 | Thin content threshold exceeded | Trigger quality gate warning. Report the unique content percentage and flag pages below 40% uniqueness. Require user acknowledgment before proceeding. |
 | Quality gate violation | Halt analysis at the HARD STOP threshold (500+ pages without justification or <30% unique content). Present findings and require explicit user approval to continue. |
+
+## 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/seo-schema/SKILL.md

@@ -21,7 +21,6 @@ allowed-tools:
 # Schema Markup Analysis & Generation
 
 ## When to Use
-
 - Use when detecting, validating, or generating Schema.org structured data.
 - Use when the user asks about JSON-LD, rich results, or markup opportunities.
 - Use when schema validation is the main task, rather than a broader SEO audit.
@@ -176,3 +175,8 @@ When generating schema for a page:
 | No schema markup found | Report that no JSON-LD, Microdata, or RDFa was detected. Recommend appropriate schema types based on page content analysis. |
 | Invalid JSON-LD syntax | Parse and report specific syntax errors (missing brackets, trailing commas, unquoted keys). Provide corrected JSON-LD output. |
 | Deprecated schema type detected | Flag the deprecated type with its retirement date. Recommend the current replacement type or advise removal if no replacement exists. |
+
+## 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/seo-sitemap/SKILL.md

@@ -21,7 +21,6 @@ allowed-tools:
 # Sitemap Analysis & Generation
 
 ## When to Use
-
 - Use when analyzing an existing XML sitemap or generating a new one.
 - Use when the user mentions sitemap issues, sitemap generation, or sitemap validation.
 - Use when checking URL coverage, sitemap limits, and sitemap quality rules.
@@ -127,3 +126,8 @@ allowed-tools:
 - `sitemap.xml` (or split files with index)
 - `STRUCTURE.md`: site architecture documentation
 - URL count and organization summary
+
+## 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/seo-snippet-hunter/SKILL.md

@@ -111,3 +111,8 @@ You are a featured snippet optimization specialist formatting content for positi
 - Schema.org markup templates
 
 Focus on clear, direct answers. Format content to maximize featured snippet eligibility.
+
+## 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/seo-structure-architect/SKILL.md

@@ -105,3 +105,8 @@ H1: Primary Keyword Focus
 - Step-by-step for processes
 
 Focus on logical flow and scannable content. Create clear information hierarchy for users and search engines.
+
+## 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/seo-technical/SKILL.md

@@ -17,7 +17,6 @@ allowed-tools:
 # Technical SEO Audit
 
 ## When to Use
-
 - Use when the user wants a technical SEO review focused on crawlability, indexability, performance, or rendering.
 - Use when auditing robots.txt, canonicalization, JavaScript SEO, Core Web Vitals, or AI crawler access.
 - Use when the task is infrastructure- and implementation-oriented rather than content-focused.
@@ -173,3 +172,8 @@ If DataForSEO MCP tools are available, use `on_page_instant_pages` for real page
 | robots.txt not found | Note that no robots.txt was detected at the root domain. Recommend creating one with appropriate directives. Continue audit on remaining categories. |
 | HTTPS not configured | Flag as a critical issue. Report whether HTTP is served without redirect, mixed content exists, or SSL certificate is missing/expired. |
 | Core Web Vitals data unavailable | Note that CrUX data is not available (common for low-traffic sites). Suggest using Lighthouse lab data as a proxy and recommend increasing traffic before re-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/sequence-psychologist/SKILL.md

@@ -8,7 +8,6 @@ date_added: "2026-04-04"
 You are a **Behavioral Psychologist specializing in persuasion sequencing and relationship psychology**. Your task is to design email nurture sequences and multi-touch communication flows using psychological principles of curiosity loops, reciprocity, commitment, and emotional pacing.
 
 ## When to Use
-
 - Use when an email, onboarding, or sales sequence needs a better step-by-step persuasion arc.
 - Use when each touchpoint should prepare the next instead of repeating the same appeal.
 
@@ -113,3 +112,8 @@ Before finalizing output, the agent asks:
 - [ ] Did I give value before asking?
 - [ ] Did I resolve open loops on time?
 - [ ] Does the sequence feel respectful and useful?
+
+## 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/server-management/SKILL.md

@@ -164,3 +164,8 @@ When something's wrong:
 
 ## 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/service-mesh-expert/SKILL.md

@@ -59,3 +59,8 @@ Expert service mesh architect specializing in Istio, Linkerd, and cloud-native n
 - Monitor mesh overhead (latency, resource usage)
 - Keep sidecar resources appropriately sized
 - Use destination rules for consistent load balancing
+
+## 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/service-mesh-observability/SKILL.md

@@ -396,3 +396,8 @@ spec:
 - [Linkerd Observability](https://linkerd.io/2.14/features/dashboard/)
 - [OpenTelemetry](https://opentelemetry.io/)
 - [Kiali](https://kiali.io/)
+
+## 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/sexual-health-analyzer/SKILL.md

@@ -8,7 +8,6 @@ source: community
 # 性健康分析技能
 
 ## When to Use
-
 - 需要分析性健康记录、筛查情况、避孕效果或相关风险模式时使用。
 - 任务涉及 IIEF-5 评分、STD 筛查管理、性活动统计或跨模块关联分析。
 - 用户请求性健康趋势报告或结构化风险分析时使用。
@@ -1124,3 +1123,8 @@ source: community
 **版本**: v1.0.0
 **最后更新**: 2025-01-06
 **维护者**: WellAlly Tech
+
+## 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/shadcn/SKILL.md

@@ -247,3 +247,8 @@ npx shadcn@latest view @shadcn/button
 - [rules/base-vs-radix.md](./rules/base-vs-radix.md) — asChild vs render, Select, ToggleGroup, Slider, Accordion
 - [cli.md](./cli.md) — Commands, flags, presets, templates
 - [customization.md](./customization.md) — Theming, CSS variables, extending components
+
+## 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/shader-programming-glsl/SKILL.md

@@ -120,3 +120,8 @@ void mainImage(out vec4 fragColor, in vec2 fragCoord) {
 
 **Problem:** Shader compiles but screen is black.
 **Solution:** Check if `gl_Position.w` is correct (usually 1.0). Check if uniforms are actually being set from the host application. Verify UV coordinates are within [0, 1].
+
+## 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/sharp-edges/SKILL.md

@@ -292,3 +292,8 @@ Before concluding analysis:
 - [ ] Verified error paths don't bypass security
 - [ ] Checked configuration validation
 - [ ] Constructor params validated (not just defaulted) - see config-patterns.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/shellcheck-configuration/SKILL.md

@@ -467,3 +467,8 @@ shellcheck --format=quiet script.sh
 - **ShellCheck GitHub**: https://github.com/koalaman/shellcheck
 - **ShellCheck Wiki**: https://www.shellcheck.net/wiki/
 - **Error Code Reference**: https://www.shellcheck.net/
+
+## 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/shopify-apps/SKILL.md

@@ -1494,10 +1494,14 @@ Message: Loader without authentication. Use authenticate.admin(request).
 - user needs serverless deployment -> aws-serverless (Lambda or Vercel deployment)
 
 ## When to Use
-
 - User mentions or implies: shopify app
 - User mentions or implies: shopify
 - User mentions or implies: embedded app
 - User mentions or implies: polaris
 - User mentions or implies: app bridge
 - User mentions or implies: shopify webhook
+
+## 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/shopify-automation/SKILL.md

@@ -170,3 +170,8 @@ For advanced operations:
 
 ## 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/shopify-development/SKILL.md

@@ -366,3 +366,8 @@ API Version: 2026-01 (quarterly releases, 12-month deprecation window)
 
 ## 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/signup-flow-cro/SKILL.md

@@ -359,3 +359,8 @@ If you need more context:
 
 ## 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/similarity-search-patterns/SKILL.md

@@ -34,3 +34,8 @@ Patterns for implementing efficient similarity search in production systems.
 ## Resources
 
 - `resources/implementation-playbook.md` for detailed patterns and 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/simplify-code/SKILL.md

@@ -11,7 +11,6 @@ date_added: "2026-03-25"
 Review changed code for reuse, quality, efficiency, and clarity issues. Use Codex sub-agents to review in parallel, then optionally apply only high-confidence, behavior-preserving fixes.
 
 ## When to Use
-
 - When the user asks to simplify, clean up, refactor, or review changed code.
 - When you want high-confidence, behavior-preserving improvements on a scoped diff.
 
@@ -177,3 +176,8 @@ Close with a brief result:
 - whether validation ran
 
 If the code is already clean for this rubric, say that directly instead of manufacturing edits.
+
+## 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/site-architecture/SKILL.md

@@ -13,7 +13,6 @@ metadata:
 You are an information architecture expert. Your goal is to help plan website structure — page hierarchy, navigation, URL patterns, and internal linking — so the site is intuitive for users and optimized for search engines.
 
 ## When to Use
-
 - Use when planning or restructuring page hierarchy, navigation, and URL structure.
 - Use when mapping site sections, breadcrumbs, and internal linking.
 - Use when the user asks how pages should be organized, not how an XML sitemap should be generated.
@@ -364,3 +363,8 @@ Mermaid diagram showing page relationships and navigation zones. Use `graph TD`
 - **page-cro**: For optimizing individual pages for conversion
 - **schema-markup**: For implementing breadcrumb and site navigation structured data
 - **competitor-alternatives**: For comparison page frameworks and URL 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/skill-creator/SKILL.md

@@ -588,3 +588,8 @@ Executable utilities for skill maintenance:
 - **Repository:** https://github.com/yourusername/cli-ai-skills
 - **Writing Style Guide:** `resources/templates/writing-style-guide.md`
 - **Progress Tracker Template:** `resources/templates/progress-tracker.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/skill-creator-ms/SKILL.md

@@ -617,3 +617,8 @@ Before completing a skill:
 
 ## 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/skill-developer/SKILL.md

@@ -427,3 +427,8 @@ See [TROUBLESHOOTING.md](TROUBLESHOOTING.md) for complete debugging guide.
 **Progressive Disclosure**: Reference files for detailed information ✅
 
 **Next**: Create more skills, refine patterns based on usage
+
+## 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/skill-improver/SKILL.md

@@ -144,3 +144,8 @@ The marker is the ONLY way to complete the loop. Natural language like "looks go
 - "This minor issue seems wrong, I'll skip all of them" - Evaluate each one individually
 - "The reviewer is being too strict" - The quality bar exists for a reason
 - "It's good enough" - If there are major issues, it's not good enough
+
+## 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/skill-installer/SKILL.md

@@ -297,3 +297,8 @@ apos o skill-creator finalizar uma skill.
 ## Related Skills
 
 - `skill-sentinel` - 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/skill-optimizer/SKILL.md

@@ -264,3 +264,8 @@ The analysis dimensions in this report are grounded in the following research:
 - **Information position**: Lost in the Middle (Liu et al., TACL 2024) — U-shaped LLM attention curve
 - **Format impact**: He et al. (arXiv:2411.10541) — format changes alone can cause 9-40% performance variance
 - **Instruction compliance**: IFEval (arXiv:2311.07911) — LLMs struggle with multi-constraint prompts
+
+## 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/skill-rails-upgrade/SKILL.md

@@ -407,3 +407,8 @@ Use this skill when working with analyze rails apps and provide upgrade assessme
 3. **Minimal changes** - Only add what's necessary for the new Rails version
 4. **Transparency** - Show the user exactly what will change before doing it
 5. **Reversibility** - User should be able to `git checkout` to restore if needed
+
+## 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/skill-scanner/SKILL.md

@@ -12,7 +12,6 @@ Scan agent skills for security issues before adoption. Detects prompt injection,
 **Important**: Run all scripts from the repository root using the full path via `${CLAUDE_SKILL_ROOT}`.
 
 ## When to Use
-
 - You need to evaluate a skill for prompt injection, malicious code, over-broad permissions, or supply-chain risk before adopting it.
 - You want a static scan plus manual review workflow for a skill directory.
 - The task is to decide whether a skill is safe enough to trust in an agent environment.
@@ -200,3 +199,8 @@ Example assessments:
 | `references/prompt-injection-patterns.md` | Injection patterns, jailbreaks, obfuscation techniques, false positive guide |
 | `references/dangerous-code-patterns.md` | Script security patterns: exfiltration, shells, credential theft, eval/exec |
 | `references/permission-analysis.md` | Tool risk tiers, least privilege methodology, common skill permission profiles |
+
+## 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/skill-seekers/SKILL.md

@@ -21,3 +21,8 @@ Use this skill when you need to work with -automatically convert documentation w
 This skill provides guidance and patterns for -automatically convert documentation websites, github repositories, and pdfs into claude ai skills in minutes..
 
 For more information, see the [source repository](https://github.com/yusufkaraaslan/Skill_Seekers).
+
+## 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/skill-sentinel/SKILL.md

@@ -275,3 +275,8 @@ Para detalhes tecnicos, consultar:
 ## Related Skills
 
 - `skill-installer` - 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/skill-writer/SKILL.md

@@ -106,3 +106,8 @@ Return:
 
 ## When to Use
 Use this skill when tackling tasks related to its primary domain or functionality as 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/skin-health-analyzer/SKILL.md

@@ -708,3 +708,8 @@ source: community
 
 ## When to Use
 Use this skill when tackling tasks related to its primary domain or functionality as 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/slack-automation/SKILL.md

@@ -190,3 +190,8 @@ Most list endpoints use cursor-based pagination:
 
 ## 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/slack-bot-builder/SKILL.md

@@ -1391,7 +1391,6 @@ Message: Requesting users:read.email but may not use email. Verify necessity.
 - user needs high availability -> devops (Scale webhooks, monitoring, alerting)
 
 ## When to Use
-
 - User mentions or implies: slack bot
 - User mentions or implies: slack app
 - User mentions or implies: bolt framework
@@ -1401,3 +1400,8 @@ Message: Requesting users:read.email but may not use email. Verify necessity.
 - User mentions or implies: slack workflow
 - User mentions or implies: slack interactive
 - User mentions or implies: slack oauth
+
+## 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/slack-gif-creator/SKILL.md

@@ -257,3 +257,8 @@ pip install pillow imageio numpy
 
 ## 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/sleep-analyzer/SKILL.md

@@ -11,7 +11,6 @@ source: community
 分析睡眠数据，识别睡眠模式，评估睡眠质量，并提供个性化睡眠改善建议。
 
 ## When to Use
-
 - 需要分析睡眠时长、效率、作息规律或睡眠质量时使用。
 - 任务涉及失眠模式、夜间觉醒、PSQI 评分或睡眠问题识别。
 - 需要把睡眠数据与情绪、运动或其他健康因素做关联分析时使用。
@@ -779,3 +778,8 @@ def calculate_correlation(sleep_data, other_data, lag_days=0):
 **技能版本**: v1.0
 **创建日期**: 2026-01-02
 **维护者**: WellAlly Tech
+
+## 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/slo-implementation/SKILL.md

@@ -342,3 +342,8 @@ rules:
 
 - `prometheus-configuration` - For metric collection
 - `grafana-dashboards` - For SLO visualization
+
+## 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/snowflake-development/SKILL.md

@@ -12,7 +12,6 @@ date_added: "2026-03-24"
 You are a Snowflake development expert. Apply these rules when writing SQL, building data pipelines, using Cortex AI, or working with Snowpark Python on Snowflake.
 
 ## When to Use
-
 - When the user asks for help with Snowflake SQL, data pipelines, Cortex AI, or Snowpark Python.
 - When you need Snowflake-specific guidance for dbt, performance tuning, or security hardening.
 
@@ -231,3 +230,8 @@ Snowflake-specific configs (combine with any materialization):
 | "Numeric value not recognized" | VARIANT not cast | `src:field::NUMBER(10,2)` |
 | Task not running | Forgot to resume | `ALTER TASK ... RESUME` |
 | DT refresh failing | Schema change or tracking disabled | Use explicit columns, check change tracking |
+
+## 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/social-content/SKILL.md

@@ -811,3 +811,8 @@ If you need more context:
 
 ## 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/social-orchestrator/SKILL.md

@@ -297,3 +297,8 @@ Estrategia: Publish-or-Skip (nao cancela toda campanha)
 - `instagram` - Complementary skill for enhanced analysis
 - `telegram` - Complementary skill for enhanced analysis
 - `whatsapp-cloud-api` - 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/social-proof-architect/SKILL.md

@@ -8,7 +8,6 @@ date_added: "2026-04-04"
 You are a **Social Psychologist specializing in conformity, trust, and influence**. Your task is to select, frame, and place the right type of social proof for a specific audience and context. You do not add proof as decoration. You match proof type to the trust gap.
 
 ## When to Use
-
 - Use when testimonials, logos, numbers, or case studies need to be structured for maximum trust impact.
 - Use when social proof exists but is weakly placed or not tied to the buyer's main hesitation.
 
@@ -115,3 +114,8 @@ Before finalizing output, the agent asks:
 - [ ] Did I place proof at the point of doubt?
 - [ ] Is the proof real and contextual?
 - [ ] Would this increase trust without feeling forced?
+
+## 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.