opencode-skills-collection 2.0.70 → 2.0.72

package/bundled-skills/game-development/multiplayer/SKILL.md

@@ -135,3 +135,8 @@ Server: Validate → did projectile actually hit?
 
 ## 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/game-development/pc-games/SKILL.md

@@ -147,3 +147,8 @@ Map ACTIONS, not buttons:
 
 ## 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/game-development/vr-ar/SKILL.md

@@ -126,3 +126,8 @@ date_added: "2026-02-27"
 
 ## 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/game-development/web-games/SKILL.md

@@ -153,3 +153,8 @@ What type of game?
 
 ## 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/gcp-cloud-run/SKILL.md

@@ -1374,5 +1374,9 @@ Message: Singleton pattern - ensure thread safety if using concurrency > 1.
 - user needs workflow orchestration -> workflow-automation (Cloud Workflows, Eventarc)
 
 ## 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/gdb-cli/SKILL.md

@@ -237,3 +237,8 @@ gdb-cli thread-apply -s b2c3d4 bt --all
 - **Repository**: https://github.com/Cerdore/gdb-cli
 - **PyPI**: https://pypi.org/project/gdb-cli/
 - **Documentation**: https://github.com/Cerdore/gdb-cli#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/gdpr-data-handling/SKILL.md

@@ -34,3 +34,8 @@ Practical implementation guide for GDPR-compliant data processing, consent manag
 ## 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/gemini-api-dev/SKILL.md

@@ -131,3 +131,8 @@ This index contains links to all documentation pages in `.md.txt` format. Use we
 
 ## 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/gemini-api-integration/SKILL.md

@@ -186,3 +186,8 @@ try {
 
 **Problem:** `RESOURCE_EXHAUSTED` (quota exceeded)
 **Solution:** Check your quota in Google Cloud Console. Implement request queuing and exponential backoff.
+
+## 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/geo-fundamentals/SKILL.md

@@ -158,3 +158,8 @@ How AI engines select content to cite:
 
 ## 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/geoffrey-hinton/SKILL.md

@@ -1274,3 +1274,8 @@ pesquisa de alinhamento e subfinanciada; arrependimento de parte do trabalho e g
 - `elon-musk` - Complementary skill for enhanced analysis
 - `ilya-sutskever` - Complementary skill for enhanced analysis
 - `sam-altman` - 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/gh-review-requests/SKILL.md

@@ -13,7 +13,6 @@ Fetch unread `review_requested` notifications for open (unmerged) PRs, filtered
 **Requires**: GitHub CLI (`gh`) authenticated.
 
 ## When to Use
-
 - You need to find unread GitHub PR review requests for a specific team.
 - You want to check which open PRs currently need your review or a teammate's review.
 - You need a filtered review queue instead of manually browsing GitHub notifications.
@@ -83,3 +82,8 @@ Then for each `review_requested` notification, check:
 - `gh api repos/{repo}/pulls/{number}` — skip if `state == "closed"` or `merged_at` is set
 - `gh api repos/{repo}/pulls/{number}/requested_reviewers` — check `teams[].name`
 - `gh api orgs/{org}/teams/{slug}/members` — check if author is a member
+
+## 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/gha-security-review/SKILL.md

@@ -18,7 +18,6 @@ Find exploitable vulnerabilities in GitHub Actions workflows. Every finding MUST
 This skill encodes attack patterns from real GitHub Actions exploits — not generic CI/CD theory.
 
 ## When to Use
-
 - You are reviewing GitHub Actions workflows for exploitable security issues.
 - The task requires tracing a concrete attack path from an external attacker to workflow execution or secret exposure.
 - You need a security review of workflow files, composite actions, or workflow-related scripts with evidence-based findings only.
@@ -192,3 +191,8 @@ If any link is broken, mark MEDIUM (needs verification) or drop the finding.
 ````
 
 If no findings: "No exploitable vulnerabilities identified. All workflows reviewed and cleared."
+
+## 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/git-advanced-workflows/SKILL.md

@@ -413,3 +413,8 @@ git branch recovered-branch abc123
 - **assets/git-workflow-checklist.md**: Pre-PR cleanup checklist
 - **assets/git-aliases.md**: Useful Git aliases for advanced workflows
 - **scripts/git-clean-branches.sh**: Clean up merged and stale branches
+
+## 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/git-hooks-automation/SKILL.md

@@ -414,3 +414,8 @@ echo "npx --no -- commitlint --edit \$1" > .husky/commit-msg
 - `@verification-before-completion` - Verification before claiming work is done
 - `@bash-pro` - Advanced shell scripting for custom hooks
 - `@github-actions-templates` - CI/CD workflow 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/git-pr-workflows-git-workflow/SKILL.md

@@ -141,3 +141,8 @@ In case of issues after merge:
 - **Review Response**: Address review comments within 24 hours
 - **Merge Strategy**: Squash for feature branches, merge for release branches
 - **Sign-Off**: Require at least 2 approvals for main branch changes
+
+## 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/git-pr-workflows-onboard/SKILL.md

@@ -417,3 +417,8 @@ Ensuring onboarding effectiveness and iteration:
 6. **Maintain momentum**: Keep the new hire engaged and progressing daily
 
 Remember: Great onboarding reduces time-to-productivity from months to weeks while building lasting engagement and retention.
+
+## 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/git-pr-workflows-pr-enhance/SKILL.md

@@ -49,3 +49,8 @@ Focus on creating PRs that are a pleasure to review, with all necessary context
 ## 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/git-pushing/SKILL.md

@@ -33,3 +33,8 @@ bash skills/git-pushing/scripts/smart_commit.sh "feat: add feature"
 ```
 
 Script handles: staging, conventional commit message, Claude footer, push with -u flag.
+
+## 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/github/SKILL.md

@@ -11,7 +11,6 @@ date_added: "2026-03-25"
 Use the `gh` CLI to interact with GitHub. Always specify `--repo owner/repo` when not in a git directory, or use URLs directly.
 
 ## When to Use
-
 - When the user asks about GitHub issues, pull requests, workflow runs, or CI failures.
 - When you need `gh issue`, `gh pr`, `gh run`, or `gh api` from the command line.
 
@@ -74,3 +73,8 @@ Most commands support `--json` for structured output.  You can use `--jq` to fil
 ```bash
 gh issue list --repo owner/repo --json number,title --jq '.[] | "\(.number): \(.title)"'
 ```
+
+## 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/github-actions-templates/SKILL.md

@@ -346,3 +346,8 @@ jobs:
 - `gitlab-ci-patterns` - For GitLab CI workflows
 - `deployment-pipeline-design` - For pipeline architecture
 - `secrets-management` - For secrets handling
+
+## 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/github-automation/SKILL.md

@@ -228,3 +228,8 @@ All list endpoints use page-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/github-issue-creator/SKILL.md

@@ -141,3 +141,8 @@ Was working yesterday - possible permission/config change or service regression
 
 ## When to Use
 Use this skill when you have unstructured bug input such as pasted errors, support notes, screenshots, or voice dictation and need to turn it into a clean GitHub issue with a summary, reproduction steps, expected vs actual behavior, impact, and attachment references.
+
+## 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/github-workflow-automation/SKILL.md

@@ -847,3 +847,8 @@ Dockerfile @org/devops-team
 - [GitHub Actions Documentation](https://docs.github.com/en/actions)
 - [GitHub REST API](https://docs.github.com/en/rest)
 - [CODEOWNERS Syntax](https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners)
+
+## 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/gitlab-automation/SKILL.md

@@ -255,3 +255,8 @@ When using project paths as identifiers:
 
 ## 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/gitlab-ci-patterns/SKILL.md

@@ -284,3 +284,8 @@ trigger-child:
 - `github-actions-templates` - For GitHub Actions
 - `deployment-pipeline-design` - For architecture
 - `secrets-management` - For secrets handling
+
+## 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/gitops-workflow/SKILL.md

@@ -304,3 +304,8 @@ argocd app sync my-app --force
 
 - `k8s-manifest-generator` - For creating manifests
 - `helm-chart-scaffolding` - For packaging applications
+
+## 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/global-chat-agent-discovery/SKILL.md

@@ -117,3 +117,8 @@ Agent (via Global Chat MCP): 4 registries carry Kubernetes-related agents (23 to
 - `@mcp-client` - For general MCP client setup and configuration
 - `@agent-orchestration-multi-agent-optimize` - For orchestrating multiple discovered agents
 - `@agent-memory-mcp` - For persisting discovered agent information across sessions
+
+## 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/gmail-automation/SKILL.md

@@ -16,7 +16,6 @@ Lightweight Gmail integration with standalone OAuth authentication. No MCP serve
 > **⚠️ Requires Google Workspace account.** Personal Gmail accounts are not supported.
 
 ## When to Use
-
 - You need to search, read, or send Gmail messages from the command line without an MCP server.
 - You are automating inbox workflows for a Google Workspace account.
 - You want a lightweight Gmail integration backed by standalone OAuth scripts.
@@ -185,3 +184,8 @@ Tokens stored securely using the system keyring:
 Service name: `gmail-skill-oauth`
 
 Tokens automatically refresh when expired using Google's cloud function.
+
+## 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/go-concurrency-patterns/SKILL.md

@@ -34,3 +34,8 @@ Production patterns for Go concurrency including goroutines, channels, synchroni
 ## 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/goal-analyzer/SKILL.md

@@ -11,7 +11,6 @@ source: community
 分析健康目标数据,识别目标模式和进度,评估目标达成情况,并提供个性化目标管理建议。
 
 ## When to Use
-
 - 你需要评估健康目标是否符合 SMART 原则，并识别目标设定中的薄弱点。
 - 你想跟踪目标进度，并结合营养、运动、睡眠等健康数据做关联分析。
 - 你需要面向个人健康管理的目标优化建议、风险提示和阶段性调整方案。
@@ -611,3 +610,8 @@ def validate_smart_goal(goal):
 ---
 
 **使用此技能时,始终优先考虑用户的健康和安全!**
+
+## 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/godot-4-migration/SKILL.md

@@ -125,3 +125,8 @@ await get_tree().create_timer(1.0).timeout
 
 **Problem:** "Identifier 'Tween' is not a valid type."
 **Solution:** `Tween` is now `SceneTreeTween` or just an object returned by `create_tween()`. You rarely type it explicitly, just use `var tween = create_tween()`.
+
+## 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/godot-gdscript-patterns/SKILL.md

@@ -34,3 +34,8 @@ Production patterns for Godot 4.x game development with GDScript, covering archi
 ## 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/golang-pro/SKILL.md

@@ -174,3 +174,8 @@ Expert Go developer mastering Go 1.21+ features, modern development practices, a
 - "Implement a Redis-backed cache with connection pooling"
 - "Set up a modern Go project with proper testing and CI/CD"
 - "Debug and fix race conditions in this concurrent Go code"
+
+## 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/google-analytics-automation/SKILL.md

@@ -229,3 +229,8 @@ Automate Google Analytics 4 (GA4) reporting and property management through Comp
 
 ## 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/google-calendar-automation/SKILL.md

@@ -16,7 +16,6 @@ Lightweight Google Calendar integration with standalone OAuth authentication. No
 > **⚠️ Requires Google Workspace account.** Personal Gmail accounts are not supported.
 
 ## When to Use
-
 - You need to list, create, inspect, or update Google Calendar events from local scripts.
 - The task requires OAuth-backed calendar automation without standing up an MCP server.
 - You need quick operational access to calendars, schedules, attendees, or event details in a Workspace environment.
@@ -162,3 +161,8 @@ Tokens stored securely using the system keyring:
 Service name: `google-calendar-skill-oauth`
 
 Tokens are automatically refreshed when expired using Google's cloud function.
+
+## 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/google-docs-automation/SKILL.md

@@ -16,7 +16,6 @@ Lightweight Google Docs integration with standalone OAuth authentication. No MCP
 > **⚠️ Requires Google Workspace account.** Personal Gmail accounts are not supported.
 
 ## When to Use
-
 - You need to create, search, read, or edit Google Docs from local automation scripts.
 - The task involves document text extraction, append/insert operations, or content replacement in Workspace docs.
 - You want direct Docs automation without relying on an MCP server.
@@ -85,3 +84,8 @@ Tokens stored securely using the system keyring:
 Service name: `google-docs-skill-oauth`
 
 Access tokens are automatically refreshed when expired using Google's cloud function.
+
+## 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/google-drive-automation/SKILL.md

@@ -16,7 +16,6 @@ Lightweight Google Drive integration with standalone OAuth authentication. No MC
 > **Requires Google Workspace account.** Personal Gmail accounts are not supported.
 
 ## When to Use
-
 - You need to search, list, upload, download, move, or organize Google Drive files and folders.
 - The task requires direct Drive read/write automation through local scripts in a Workspace account.
 - You want file-level Drive operations without introducing an MCP server dependency.
@@ -139,3 +138,8 @@ Tokens stored securely using the system keyring:
 Service name: `google-drive-skill-oauth`
 
 Automatically refreshes expired tokens using Google's cloud function.
+
+## 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/google-sheets-automation/SKILL.md

@@ -142,3 +142,8 @@ Tokens automatically refresh when expired using Google's cloud function.
 
 ## 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/google-slides-automation/SKILL.md

@@ -16,7 +16,6 @@ Lightweight Google Slides integration with standalone OAuth authentication. No M
 > **Requires Google Workspace account.** Personal Gmail accounts are not supported.
 
 ## When to Use
-
 - You need to create, inspect, or modify Google Slides presentations from local automation.
 - The task involves reading slide text, adding/removing slides, or batch updating presentation content.
 - You want Slides automation for Workspace documents without using an MCP server.
@@ -144,3 +143,8 @@ Tokens stored securely using the system keyring:
 Service name: `google-slides-skill-oauth`
 
 Automatically refreshes expired tokens using Google's cloud function.
+
+## 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/googlesheets-automation/SKILL.md

@@ -198,3 +198,8 @@ Google Sheets enforces strict rate limits:
 
 ## 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/grafana-dashboards/SKILL.md

@@ -382,3 +382,8 @@ resource "grafana_folder" "monitoring" {
 
 - `prometheus-configuration` - For metric collection
 - `slo-implementation` - For SLO dashboards
+
+## 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/graphql/SKILL.md

@@ -1059,7 +1059,6 @@ Fix action: Use update function to modify cache directly
 Works well with: `backend`, `postgres-wizard`, `nextjs-app-router`, `react-patterns`
 
 ## When to Use
-
 - User mentions or implies: graphql
 - User mentions or implies: graphql schema
 - User mentions or implies: graphql resolver
@@ -1070,3 +1069,8 @@ Works well with: `backend`, `postgres-wizard`, `nextjs-app-router`, `react-patte
 - User mentions or implies: graphql codegen
 - User mentions or implies: graphql query
 - User mentions or implies: graphql mutation
+
+## 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/graphql-architect/SKILL.md

@@ -178,3 +178,8 @@ Expert GraphQL architect focused on building scalable, performant, and secure Gr
 - "Design field-level caching strategy for a high-traffic GraphQL API"
 - "Implement query complexity analysis and rate limiting for production safety"
 - "Create a schema evolution strategy that supports multiple client versions"
+
+## 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/growth-engine/SKILL.md

@@ -241,3 +241,8 @@ Dia 0 -- Boas-vindas (imediato apos cadastro)
 - `monetization` - Complementary skill for enhanced analysis
 - `product-design` - Complementary skill for enhanced analysis
 - `product-inventor` - 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/haskell-pro/SKILL.md

@@ -53,3 +53,8 @@ You are a Haskell expert specializing in strongly typed functional programming a
 - QuickCheck/Hspec tests with property-based reasoning
 
 Provide modern, maintainable Haskell that balances rigor with practicality.
+
+## 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/headline-psychologist/SKILL.md

@@ -8,7 +8,6 @@ date_added: "2026-04-04"
 You are a **Cognitive Psychologist specializing in attention and curiosity research**. Your task is to engineer headlines and subject-facing titles that capture attention, create information gaps, and trigger the emotional state needed for the reader to continue.
 
 ## When to Use
-
 - Use when headlines need stronger stopping power, curiosity, and relevance without becoming vague clickbait.
 - Use when testing multiple headline angles for ads, landing pages, emails, or social posts.
 
@@ -115,3 +114,8 @@ Before finalizing output, the agent asks:
 - [ ] Does it feel relevant, not generic?
 - [ ] Would the content actually satisfy the promise?
 - [ ] Does it preserve trust?
+
+## 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/health-trend-analyzer/SKILL.md

@@ -11,7 +11,6 @@ source: community
 分析一段时间内健康数据的趋势和模式，识别变化、相关性，并提供数据驱动的健康洞察。
 
 ## When to Use
-
 - 需要分析一段时间内健康数据的趋势、相关性或显著变化时使用。
 - 任务涉及体重、症状、用药、化验、情绪或睡眠等多维度随时间变化。
 - 用户询问“最近健康状况有什么变化”或需要趋势报告时使用。
@@ -457,3 +456,8 @@ function earlyWarnings(trends) {
 - 支持添加新的数据维度
 - 支持自定义图表类型
 - 支持自定义分析算法
+
+## 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.