opencode-skills-collection 2.0.70 → 2.0.72

package/bundled-skills/closed-loop-delivery/SKILL.md

@@ -114,3 +114,8 @@ When claiming completion, always include:
 - PR status (new actionable comments count)
 
 Do not claim success without evidence.
+
+## 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/cloud-architect/SKILL.md

@@ -129,3 +129,8 @@ Expert cloud architect with deep knowledge of AWS, Azure, GCP, and emerging clou
 - "Implement a disaster recovery solution with 4-hour RTO across multiple cloud providers"
 - "Design a compliant architecture for healthcare data processing meeting HIPAA requirements"
 - "Create a FinOps strategy with automated cost optimization and chargeback reporting"
+
+## 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/cloud-devops/SKILL.md

@@ -233,3 +233,8 @@ Services: Cloud Run, GKE, Cloud Functions, BigQuery
 - `security-audit` - Security testing
 - `database` - Database operations
 - `testing-qa` - Testing workflows
+
+## 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/cloudflare-workers-expert/SKILL.md

@@ -87,3 +87,8 @@ export default {
 
 **Problem:** Request exceeded CPU time limit.
 **Solution:** Optimize loops, reduce the number of await calls, and move synchronous heavy lifting out of the request/response path. Use `ctx.waitUntil()` for tasks that don't block the response.
+
+## 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/cloudformation-best-practices/SKILL.md

@@ -77,3 +77,8 @@ Outputs:
 
 **Problem:** Stack stuck in `UPDATE_ROLLBACK_FAILED`
 **Solution:** Use `continue-update-rollback` with `--resources-to-skip` for the failing resource, then fix the root cause.
+
+## 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/coda-automation/SKILL.md

@@ -243,3 +243,8 @@ Automate Coda document and data operations through Composio's Coda toolkit via R
 
 ## 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/code-documentation-code-explain/SKILL.md

@@ -47,3 +47,8 @@ $ARGUMENTS
 ## Resources
 
 - `resources/implementation-playbook.md` for detailed examples 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/code-documentation-doc-generate/SKILL.md

@@ -49,3 +49,8 @@ $ARGUMENTS
 ## Resources
 
 - `resources/implementation-playbook.md` for detailed examples 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/code-refactoring-context-restore/SKILL.md

@@ -180,3 +180,8 @@ context-restore project:ml-pipeline --query "model training strategy"
 - Quantum-inspired vector search algorithms
 - Self-healing context reconstruction
 - Adaptive learning context strategies
+
+## 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/code-refactoring-refactor-clean/SKILL.md

@@ -52,3 +52,8 @@ $ARGUMENTS
 ## 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/code-refactoring-tech-debt/SKILL.md

@@ -387,3 +387,8 @@ Track progress with clear KPIs:
 7. **ROI Projections**: Expected returns on debt reduction investment
 
 Focus on delivering measurable improvements that directly impact development velocity, system reliability, and team morale.
+
+## 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/code-review-ai-ai-review/SKILL.md

@@ -451,3 +451,8 @@ Comprehensive AI code review combining:
 8. Auto-test generation via Qodo/CodiumAI
 
 Use this tool to transform code review from manual process to automated AI-assisted quality assurance catching issues early with instant feedback.
+
+## 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/code-review-checklist/SKILL.md

@@ -445,3 +445,8 @@ This is great because [explain why]
 ---
 
 **Pro Tip:** Use a checklist template for every review to ensure consistency and thoroughness. Customize it for your team's specific needs!
+
+## 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/code-review-excellence/SKILL.md

@@ -41,3 +41,8 @@ Transform code reviews from gatekeeping to knowledge sharing through constructiv
 ## Resources
 
 - `resources/implementation-playbook.md` for detailed review patterns 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/code-reviewer/SKILL.md

@@ -173,3 +173,8 @@ Master code reviewer focused on ensuring code quality, security, performance, an
 - "Analyze this caching strategy for race conditions and data consistency"
 - "Review this CI/CD pipeline for security and deployment best practices"
 - "Assess this error handling implementation for observability and debugging"
+
+## 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/code-simplifier/SKILL.md

@@ -15,7 +15,6 @@ https://github.com/anthropics/claude-plugins-official/blob/main/plugins/code-sim
 You are an expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions.
 
 ## When to Use
-
 - You need to simplify or clean up code without changing behavior.
 - The task involves readability improvements, reducing unnecessary complexity, or aligning recent edits with project standards.
 - You want refinement focused on clarity and maintainability rather than feature work.
@@ -125,3 +124,8 @@ if (items.length > 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/codebase-audit-pre-push/SKILL.md

@@ -237,5 +237,9 @@ Overall: 9/10
 
 - `@security-auditor` - Deeper security review  
 - `@systematic-debugging` - Investigate specific issues  
-- `@git-pushing` - Push code after audit  
+- `@git-pushing` - Push code after audit
 
+## 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/codebase-cleanup-deps-audit/SKILL.md

@@ -52,3 +52,8 @@ $ARGUMENTS
 ## Resources
 
 - `resources/implementation-playbook.md` for detailed tooling 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/codebase-cleanup-refactor-clean/SKILL.md

@@ -52,3 +52,8 @@ $ARGUMENTS
 ## 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/codebase-cleanup-tech-debt/SKILL.md

@@ -387,3 +387,8 @@ Track progress with clear KPIs:
 7. **ROI Projections**: Expected returns on debt reduction investment
 
 Focus on delivering measurable improvements that directly impact development velocity, system reliability, and team morale.
+
+## 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/codebase-to-wordpress-converter/SKILL.md

@@ -93,3 +93,8 @@ wp_nav_menu([
 - [ACF Documentation](https://www.advancedcustomfields.com/resources/)
 - [Tailwind CSS in WordPress](https://tailwindcss.com/docs/installation)
 - [WordPress Theme Handbook](https://developer.wordpress.org/themes/)
+
+## 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/codex-review/SKILL.md

@@ -38,3 +38,8 @@ See the GitHub repository for troubleshooting guides.
 
 ## Related Skills
 - context7-auto-research, tavily-web, exa-search, firecrawl-scraper
+
+## 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/cold-email/SKILL.md

@@ -13,7 +13,6 @@ metadata:
 You are an expert cold email writer. Your goal is to write emails that sound like they came from a sharp, thoughtful human — not a sales machine following a template.
 
 ## When to Use
-
 - Use when writing outbound prospecting emails or cold follow-up sequences.
 - Use when the task is getting replies from people with no existing relationship.
 - Use when the user wants sharper subject lines, openings, CTAs, or personalization.
@@ -165,3 +164,8 @@ Use this data to inform your writing — not as a checklist to satisfy.
 - **social-content**: For LinkedIn and social posts
 - **product-marketing-context**: For establishing foundational positioning
 - **revops**: For lead scoring, routing, and pipeline management
+
+## 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/comfyui-gateway/SKILL.md

@@ -421,3 +421,8 @@ comfyui-gateway/
 - `ai-studio-image` - 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/commit/SKILL.md

@@ -10,7 +10,6 @@ source: community
 Follow these conventions when creating commits for Sentry projects.
 
 ## When to Use
-
 - The user asks to commit code, prepare a commit message, or save changes in git.
 - You need Sentry-style commit formatting with conventional commit structure and issue references.
 - The task requires enforcing branch safety before committing, especially avoiding direct commits on `main` or `master`.
@@ -166,3 +165,8 @@ Reason: Caused performance regression in production.
 ## References
 
 - [Sentry Commit Messages](https://develop.sentry.dev/engineering-practices/commit-messages/)
+
+## 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/competitive-landscape/SKILL.md

@@ -30,3 +30,8 @@ Comprehensive frameworks for analyzing competition, identifying differentiation
 ## 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/competitor-alternatives/SKILL.md

@@ -754,3 +754,8 @@ 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/comprehensive-review-full-review/SKILL.md

@@ -147,3 +147,8 @@ Review is considered successful when:
 - Team has clear prioritized action plan for remediation
 
 Target: $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/comprehensive-review-pr-enhance/SKILL.md

@@ -12,7 +12,6 @@ source: community
 # Pull Request Enhancement
 
 ## When to Use
-
 - You need to turn a git diff into a reviewer-friendly pull request description.
 - You want a PR summary with change categories, risks, testing notes, and a checklist.
 - The diff is large enough that reviewers need explicit structure instead of a short ad hoc summary.
@@ -76,3 +75,8 @@ git cherry-pick <commits-for-part-1>
 ## Resources
 
 - `resources/implementation-playbook.md` — Python helpers for automated PR analysis, coverage reports, and risk scoring
+
+## 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/computer-use-agents/SKILL.md

@@ -2149,7 +2149,6 @@ Message: Consider adding max_cost_per_task to prevent expensive runaway tasks.
 - user needs multi-agent coordination -> multi-agent-orchestration (Multiple computer use agents working together)
 
 ## When to Use
-
 - User mentions or implies: computer use
 - User mentions or implies: desktop automation agent
 - User mentions or implies: screen control AI
@@ -2160,3 +2159,8 @@ Message: Consider adding max_cost_per_task to prevent expensive runaway tasks.
 - User mentions or implies: browser agent
 - User mentions or implies: visual agent
 - User mentions or implies: RPA with AI
+
+## 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/computer-vision-expert/SKILL.md

@@ -71,3 +71,8 @@ To provide expert guidance on designing, implementing, and optimizing state-of-t
 
 ## Related Skills
 `ai-engineer`, `robotics-expert`, `research-engineer`, `embedded-systems`
+
+## 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/concise-planning/SKILL.md

@@ -66,3 +66,8 @@ Use the following structure:
 
 ## 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/conductor-implement/SKILL.md

@@ -387,3 +387,8 @@ If implementation is paused and resumed:
 4. **Keep plan.md updated** - Task status must reflect actual progress
 5. **Commit frequently** - Each task completion should be committed
 6. **Track all commits** - Record commit hashes in metadata.json for potential revert
+
+## 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/conductor-manage/SKILL.md

@@ -38,3 +38,8 @@ Manage the complete track lifecycle including archiving, restoring, deleting, re
 ## Resources
 
 - `resources/implementation-playbook.md` for detailed modes, prompts, and workflows.
+
+## 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/conductor-revert/SKILL.md

@@ -371,3 +371,8 @@ Alternatively, if not yet pushed:
 
 (Use with caution - this discards the revert commits)
 ```
+
+## 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/conductor-setup/SKILL.md

@@ -13,7 +13,6 @@ metadata:
 Set up this Rails project for Conductor, the Mac app for parallel coding agents.
 
 ## When to Use
-
 - You need to configure a Rails project so it runs correctly inside Conductor workspaces.
 - The project should support parallel coding agents with isolated ports, Redis settings, and shared secrets.
 - You want the standard `conductor.json`, `bin/conductor-setup`, and `script/server` scaffolding for a Rails repo.
@@ -119,3 +118,8 @@ After creating the files:
 1. Confirm all Conductor files exist and scripts are executable
 2. Run `script/server` to verify it starts without errors
 3. Check that Rails configs properly reference `ENV['REDIS_URL']` or `ENV.fetch('REDIS_URL', ...)`
+
+## 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/conductor-status/SKILL.md

@@ -337,3 +337,8 @@ If invoked with `--json`:
   "blockers": []
 }
 ```
+
+## 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/conductor-validator/SKILL.md

@@ -63,3 +63,8 @@ ls conductor/index.md conductor/product.md conductor/tech-stack.md conductor/wor
 <type>_<name>_<YYYYMMDD>
 Example: feature_user_auth_20250115
 ```
+
+## 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/confluence-automation/SKILL.md

@@ -209,3 +209,8 @@ Confluence uses two pagination styles:
 
 ## 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/content-creator/SKILL.md

@@ -244,3 +244,8 @@ grep -f references/brand_guidelines.md content.txt
 # Create monthly calendar
 cp assets/content_calendar_template.md this_month_calendar.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/content-marketer/SKILL.md

@@ -165,3 +165,8 @@ Master content marketer focused on creating high-converting, SEO-optimized conte
 - "Optimize existing content for featured snippets and voice search"
 - "Develop a user-generated content campaign with influencer partnerships"
 - "Create a content calendar for Black Friday and holiday marketing"
+
+## 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/content-strategy/SKILL.md

@@ -13,7 +13,6 @@ metadata:
 You are a content strategist. Your goal is to help plan content that drives traffic, builds authority, and generates leads by being either searchable, shareable, or both.
 
 ## When to Use
-
 - Use when deciding what content to create, in what order, and for which audience.
 - Use when building topic clusters, content pillars, or an editorial roadmap.
 - Use when the user needs strategy and prioritization, not just copywriting.
@@ -372,3 +371,8 @@ Visual or structured representation of how content interconnects.
 - **site-architecture**: For page hierarchy, navigation design, and URL structure
 - **email-sequence**: For email-based content
 - **social-content**: For social media content
+
+## 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/context-agent/SKILL.md

@@ -186,3 +186,8 @@ e decisões tomadas — sem precisar de nenhuma ação manual.
 ## Related Skills
 
 - `context-guardian` - 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/context-compression/SKILL.md

@@ -264,3 +264,7 @@ External resources:
 **Author**: Agent Skills for Context Engineering Contributors
 **Version**: 1.1.0
 
+## 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/context-degradation/SKILL.md

@@ -230,3 +230,8 @@ External resources:
 **Last Updated**: 2025-12-20
 **Author**: Agent Skills for Context Engineering Contributors
 **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/context-driven-development/SKILL.md

@@ -397,3 +397,8 @@ If interrupted mid-task:
 8. **Preserve history**: Use git to track context evolution over time
 9. **Question staleness**: If context feels wrong, investigate and update
 10. **Keep it actionable**: Every context item should inform a decision or behavior
+
+## 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/context-fundamentals/SKILL.md

@@ -184,3 +184,8 @@ External resources:
 **Last Updated**: 2025-12-20
 **Author**: Agent Skills for Context Engineering Contributors
 **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/context-guardian/SKILL.md

@@ -318,3 +318,8 @@ Proximo Claude continua com precisao total, zero re-trabalho.
 ## Related Skills
 
 - `context-agent` - 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/context-management-context-restore/SKILL.md

@@ -180,3 +180,8 @@ context-restore project:ml-pipeline --query "model training strategy"
 - Quantum-inspired vector search algorithms
 - Self-healing context reconstruction
 - Adaptive learning context strategies
+
+## 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/context-manager/SKILL.md

@@ -180,3 +180,8 @@ Master context engineer specializing in building dynamic systems that provide th
 - "Design context handoff protocols for multi-stage AI processing pipelines"
 - "Create a privacy-preserving context system for regulated industries"
 - "Optimize context window usage for complex reasoning tasks with limited tokens"
+
+## 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/context-optimization/SKILL.md

@@ -178,3 +178,8 @@ External resources:
 **Last Updated**: 2025-12-20
 **Author**: Agent Skills for Context Engineering Contributors
 **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/context-window-management/SKILL.md

@@ -302,10 +302,14 @@ Workflow:
 Works well with: `rag-implementation`, `conversation-memory`, `prompt-caching`, `llm-npc-dialogue`
 
 ## When to Use
-
 - User mentions or implies: context window
 - User mentions or implies: token limit
 - User mentions or implies: context management
 - User mentions or implies: context engineering
 - User mentions or implies: long context
 - User mentions or implies: context overflow
+
+## 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/context7-auto-research/SKILL.md

@@ -37,3 +37,8 @@ See the GitHub repository for troubleshooting guides.
 
 ## Related Skills
 - tavily-web, exa-search, firecrawl-scraper, codex-review
+
+## 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/conversation-memory/SKILL.md

@@ -487,9 +487,13 @@ Workflow:
 Works well with: `context-window-management`, `rag-implementation`, `prompt-caching`, `llm-npc-dialogue`
 
 ## When to Use
-
 - User mentions or implies: conversation memory
 - User mentions or implies: remember
 - User mentions or implies: memory persistence
 - User mentions or implies: long-term memory
 - User mentions or implies: chat 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.